{"as_of":"2026-08-12T06:16:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ac498753c3e71aa9815350bafd412d4b2a88387a06af6f7d7f22537908600f54","coverage":[{"denominator":68,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":68,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-24T08:05:33.251722Z","state":"measured"},{"denominator":115,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":115,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+00:00","state":"measured"},{"denominator":47,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":47,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T19:55:12.200771Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-07-04T19:10:05.832087Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":"2308.03303","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-07-04T19:10:05.832087Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","venue":"cs.CL","work_id":"caf23d24-5176-4330-bd2a-6cf699d152cd","year":2023},"citing_paper":{"arxiv_id":"2403.03507","last_updated":"2024-06-02T21:24:12Z","snapshot_observed_at":"2026-07-06T17:40:15.746482Z","submitted_at":"2024-03-06T07:29:57Z","title":"GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection","version":2},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-05-16T23:51:50.163520Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2403.03507"},"observation_digest":"sha256:ff9e08615c359ceed7c75f70a71aefb25f9ac5ca81ff5ba108cb69312326f0eb","observation_id":"f521ea77-83c2-48b8-9a45-46a795f2ff7e","resolution":{"observed_at":"2026-05-16T23:51:50.289941Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":"2308.03303","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-07-04T19:10:05.832087Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","venue":"cs.CL","work_id":"caf23d24-5176-4330-bd2a-6cf699d152cd","year":2023},"citing_paper":{"arxiv_id":"2403.14608","last_updated":"2024-09-16T02:54:50Z","snapshot_observed_at":"2026-08-04T09:07:42.158421Z","submitted_at":"2024-03-21T17:55:50Z","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","version":7},"reference_index":135,"source":"pdf_text","source_observed_at":"2026-05-13T11:32:36.738536Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2403.14608"},"observation_digest":"sha256:c6ed1f579835abcca36f16c8eceef3e89ff196320e2a38cf1fb1000f5113c302","observation_id":"93f9cac5-41b7-462f-982d-65b80acaf1f2","resolution":{"observed_at":"2026-05-13T11:32:37.178423Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-08-11T19:55:12.200771Z","title":"Lora-fa: Memory-efficient low-rank adaptation for large language models fine-tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.06289","last_updated":"2024-12-19T18:47:54Z","snapshot_observed_at":"2026-08-12T02:34:18.675246Z","submitted_at":"2024-12-09T08:24:11Z","title":"S$^{2}$FT: Efficient, Scalable and Generalizable LLM Fine-tuning by Structured Sparsity","version":3},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-11T19:55:12.200771Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2412.06289"},"observation_digest":"sha256:0290fe775ad0236a0e9dfd26a48b4194b5bd952179698dc39dd7ec53fab2da8b","observation_id":"4b0853ef-8030-41db-8f0c-af7a20ee9c2e","resolution":{"observed_at":"2026-08-11T19:55:12.200771Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-08-11T13:37:39.104166Z","title":"Lora-fa: Memory- efficient low-rank adaptation for large language models fine-tuning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.12951","last_updated":"2024-12-17T14:33:05Z","snapshot_observed_at":"2026-08-11T13:31:29.852026Z","submitted_at":"2024-12-17T14:33:05Z","title":"FineGates: LLMs Finetuning with Compression using Stochastic Gates","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T13:37:39.104166Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2412.12951"},"observation_digest":"sha256:534a35f44248c660a0b1301242826262a1c048a8d615b11ed9d227c0774bac85","observation_id":"4cdab6a2-10f5-4154-b204-6b905bddb292","resolution":{"observed_at":"2026-08-11T13:37:39.104166Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-08-10T23:42:24.264635Z","title":"Lora-fa: Memory- efficient low-rank adaptation for large language models fine-tuning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.20064","last_updated":"2024-12-28T07:38:23Z","snapshot_observed_at":"2026-08-11T21:12:24.366048Z","submitted_at":"2024-12-28T07:38:23Z","title":"VELoRA: A Low-Rank Adaptation Approach for Efficient RGB-Event based Recognition","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-10T23:42:24.264635Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2412.20064"},"observation_digest":"sha256:de5fe85422079e123659459f49bf9d187fc3547e0b28292e744a8e782bea96ac","observation_id":"17fef881-e036-41be-82e7-83a9fe7e10c2","resolution":{"observed_at":"2026-08-10T23:42:24.264635Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-08-10T23:21:34.334979Z","title":"Lora-fa: Memory-efficient low-rank adaptation for large language models fine-tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.21065","last_updated":"2025-06-21T20:56:52Z","snapshot_observed_at":"2026-08-11T03:48:40.215954Z","submitted_at":"2024-12-30T16:34:11Z","title":"Efficient Multi-Task Inferencing with a Shared Backbone and Lightweight Task-Specific Adapters for Automatic Scoring","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:34.334979Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2412.21065"},"observation_digest":"sha256:6496d1493a41017dd6dd3b76fa80f1e50d23e666b742f7099c535ee5c7a0c089","observation_id":"f090a718-778b-461d-b209-45b1fc8c6f7a","resolution":{"observed_at":"2026-08-10T23:21:34.334979Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":"2308.03303","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-07-04T19:10:05.832087Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","venue":"cs.CL","work_id":"caf23d24-5176-4330-bd2a-6cf699d152cd","year":2023},"citing_paper":{"arxiv_id":"2501.07237","last_updated":"2026-04-27T13:03:55Z","snapshot_observed_at":"2026-07-06T20:20:14.452585Z","submitted_at":"2025-01-13T11:35:09Z","title":"GWT: Scalable Optimizer State Compression for Large Language Model Training","version":5},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-05-23T05:57:09.276224Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2501.07237"},"observation_digest":"sha256:45cca77778b495d1ab64a5d5ba4ba1954a0851e8f6ebb54a6ef950da4ce9b3f5","observation_id":"5f93ced4-668b-445d-be71-f5ac8c0f261a","resolution":{"observed_at":"2026-05-23T05:57:36.661753Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-08-10T20:13:25.230824Z","title":"Lora-fa: Memory-efficient low-rank adaptation for large language models fine-tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.09284","last_updated":"2025-01-17T04:59:32Z","snapshot_observed_at":"2026-08-12T02:36:48.797167Z","submitted_at":"2025-01-16T04:17:56Z","title":"SEAL: Entangled White-box Watermarks on Low-Rank Adaptation","version":2},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-10T20:13:25.230824Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2501.09284"},"observation_digest":"sha256:929f14a7bc9361e72e685004d4dc58594a469c470d73247ced12be454fda33e3","observation_id":"ff930418-18d6-4fb7-9ccc-6b2f49bd7a61","resolution":{"observed_at":"2026-08-10T20:13:25.230824Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-08-10T20:26:11.243027Z","title":"Lora-fa: Memory-efficient low-rank adaptation for large language models fine-tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.09767","last_updated":"2025-01-15T05:17:12Z","snapshot_observed_at":"2026-08-11T16:31:10.641403Z","submitted_at":"2025-01-15T05:17:12Z","title":"LeMo: Enabling LEss Token Involvement for MOre Context Fine-tuning","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-10T20:26:11.243027Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2501.09767"},"observation_digest":"sha256:bb9ff6af355eb79e04d82ce1dbf9aaca034fda83114fb8ddbb0dd935b7b29cb2","observation_id":"563cc2d6-bbed-48de-888f-94e29d3af971","resolution":{"observed_at":"2026-08-10T20:26:11.243027Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-08-10T15:38:03.179096Z","title":"Lora-fa: Memory-efficient low-rank adaptation for large language models fine-tuning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.13787","last_updated":"2025-01-23T16:04:23Z","snapshot_observed_at":"2026-08-10T19:15:37.342583Z","submitted_at":"2025-01-23T16:04:23Z","title":"Parameter-Efficient Fine-Tuning for Foundation Models","version":1},"reference_index":107,"source":"pdf_text","source_observed_at":"2026-08-10T15:38:03.179096Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2501.13787"},"observation_digest":"sha256:4d62e5efd8033c3778a15d41683b0b834613f72fcf408d61fade2715212fa6e1","observation_id":"7fc55bd4-7136-4912-a961-96153773d3e0","resolution":{"observed_at":"2026-08-10T15:38:03.179096Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-08-10T11:16:55.848370Z","title":"Lora-fa: Memory-efficient low-rank adaptation for large language models fine-tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.16720","last_updated":"2025-01-28T05:54:55Z","snapshot_observed_at":"2026-08-10T19:57:44.460070Z","submitted_at":"2025-01-28T05:54:55Z","title":"One Head Eight Arms: Block Matrix based Low Rank Adaptation for CLIP-based Few-Shot Learning","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-10T11:16:55.848370Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2501.16720"},"observation_digest":"sha256:4d64f8dee56dec1a56670971ec8230964073c399e62b5ba315d9a3249d867a44","observation_id":"f63ec6af-3d41-4fc2-acda-9c46899a1baf","resolution":{"observed_at":"2026-08-10T11:16:55.848370Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-08-09T22:27:57.499818Z","title":"In Proceedings of the 60th Annual Meeting of the As- sociation for Computational Linguistics (Volume 2: Short Papers), ACL 2022, Dublin, Ireland, May 22- 27, 2022, pages 1–9","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.18824","last_updated":"2025-01-31T00:43:50Z","snapshot_observed_at":"2026-08-11T00:46:21.232608Z","submitted_at":"2025-01-31T00:43:50Z","title":"Memory-Efficient Fine-Tuning of Transformers via Token Selection","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-09T22:27:57.499818Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2501.18824"},"observation_digest":"sha256:7d6c2c948fdbb197b78f831d152d3dcbf8715a5987003ae6724d9cf4b820f6b4","observation_id":"b1a0b597-b711-43eb-8665-10a9fb8ca343","resolution":{"observed_at":"2026-08-09T22:27:57.499818Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":"2308.03303","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-07-04T19:10:05.832087Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","venue":"cs.CL","work_id":"caf23d24-5176-4330-bd2a-6cf699d152cd","year":2023},"citing_paper":{"arxiv_id":"2505.19075","last_updated":"2026-05-20T08:13:51Z","snapshot_observed_at":"2026-07-30T16:12:36.732031Z","submitted_at":"2025-05-25T10:19:10Z","title":"Universal Reasoner: A Single, Composable Plug-and-Play Reasoner for Frozen LLMs","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-05-22T01:16:51.288077Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2505.19075"},"observation_digest":"sha256:06596685bf42bfcfc0f1c9e4ef2cbc330bfa67363e1d8dbfa3cc56a5420e7e86","observation_id":"d78bc88d-8e1a-4fcd-a8da-02a88cfa8749","resolution":{"observed_at":"2026-05-22T01:20:52.118075Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-08-07T13:42:47.242333Z","title":"Lora-fa: Memory-efficient low-rank adaptation for large language models fine-tuning.arXiv preprint arXiv:2308.03303, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.21382","last_updated":"2025-05-27T16:10:53Z","snapshot_observed_at":"2026-08-09T22:42:41.800500Z","submitted_at":"2025-05-27T16:10:53Z","title":"DeCAF: Decentralized Consensus-And-Factorization for Low-Rank Adaptation of Foundation Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T13:42:47.242333Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2505.21382"},"observation_digest":"sha256:22babc70ff7699d33ddec40e5d4903e2307bb1864c22f6e403ef6d31429f9e40","observation_id":"49414622-fb2a-4468-919f-2ecbc9b10f6c","resolution":{"observed_at":"2026-08-07T13:42:47.242333Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-08-07T13:15:58.292460Z","title":"Lora-fa: Memory-efficient low-rank adaptation for large language models fine-tuning.arXiv preprint arXiv:2308.03303, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.22370","last_updated":"2025-06-11T12:54:39Z","snapshot_observed_at":"2026-08-09T11:32:10.109018Z","submitted_at":"2025-05-28T13:57:56Z","title":"SplitLoRA: Balancing Stability and Plasticity in Continual Learning Through Gradient Space Splitting","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:58.292460Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2505.22370"},"observation_digest":"sha256:921482f758883a8a2cfb99ed715bd62360becc6e9a63356e1d7512c299bdecc1","observation_id":"96b3f61c-4fb1-4f8d-9233-9d71a06b255c","resolution":{"observed_at":"2026-08-07T13:15:58.292460Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-08-07T12:09:15.974806Z","title":"Lora-fa: Memory-efficient low-rank adaptation for large language models fine-tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.00495","last_updated":"2025-05-31T10:27:08Z","snapshot_observed_at":"2026-08-09T08:51:32.281143Z","submitted_at":"2025-05-31T10:27:08Z","title":"FLoE: Fisher-Based Layer Selection for Efficient Sparse Adaptation of Low-Rank Experts","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T12:09:15.974806Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2506.00495"},"observation_digest":"sha256:56b870735a45dd8361e2cd8dead9f730c81e66e00c2ff493bcb6427b2d7cdd6b","observation_id":"6f6c7e3b-f613-4e7b-aa57-f37df9495d79","resolution":{"observed_at":"2026-08-07T12:09:15.974806Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":"2308.03303","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-07-04T19:10:05.832087Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","venue":"cs.CL","work_id":"caf23d24-5176-4330-bd2a-6cf699d152cd","year":2023},"citing_paper":{"arxiv_id":"2506.01897","last_updated":"2026-04-25T01:06:47Z","snapshot_observed_at":"2026-07-30T09:10:38.260173Z","submitted_at":"2025-06-02T17:21:10Z","title":"MLorc: Momentum Low-rank Compression for Memory Efficient Large Language Model Adaptation","version":5},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-19T10:50:36.629493Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2506.01897"},"observation_digest":"sha256:2e007019f9b40773c061a44658fa21bd483a33c66b30df260dfb79fce250a8b6","observation_id":"1104e002-17bf-48f4-8cf3-3e7905f4bbe2","resolution":{"observed_at":"2026-05-19T10:52:15.099126Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-08-07T10:18:25.577452Z","title":"LoRA-FA: Memory-efficient low-rank adaptation for large language models fine-tuning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.05713","last_updated":"2025-07-27T08:06:57Z","snapshot_observed_at":"2026-08-08T06:35:08.618663Z","submitted_at":"2025-06-06T03:33:06Z","title":"Come Together, But Not Right Now: A Progressive Strategy to Boost Low-Rank Adaptation","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T10:18:25.577452Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2506.05713"},"observation_digest":"sha256:4a796d8f1571a961466e45dd5554c6ad4cb4034c0cdeeb247df3d7c1a36d2dd4","observation_id":"c57aa437-3d80-4c92-a19d-af80e240946c","resolution":{"observed_at":"2026-08-07T10:18:25.577452Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-08-07T04:15:17.585257Z","title":"Lora-fa: Memory-efficient low-rank adaptation for large language models fine-tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.11449","last_updated":"2025-06-13T04:01:34Z","snapshot_observed_at":"2026-08-09T02:24:19.544777Z","submitted_at":"2025-06-13T04:01:34Z","title":"Dynamic Sparse Training of Diagonally Sparse Networks","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-07T04:15:17.585257Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2506.11449"},"observation_digest":"sha256:a02f88d3dbcea9d6faf1564a2a2327768a28dc19a20d0b94f2a888bf06eebb43","observation_id":"73226ca3-5aff-4b80-840d-df22a66609df","resolution":{"observed_at":"2026-08-07T04:15:17.585257Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-08-07T00:43:55.915303Z","title":"Lora-fa: Memory- efficient low-rank adaptation for large language models fine-tuning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.13187","last_updated":"2025-06-16T07:55:14Z","snapshot_observed_at":"2026-08-08T09:44:47.898265Z","submitted_at":"2025-06-16T07:55:14Z","title":"Dynamic Context-oriented Decomposition for Task-aware Low-rank Adaptation with Less Forgetting and Faster Convergence","version":1},"reference_index":112,"source":"pdf_text","source_observed_at":"2026-08-07T00:43:55.915303Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2506.13187"},"observation_digest":"sha256:4d612866b05a043b128758c085c196b06473141183282b6d1632308bf276a256","observation_id":"a31cc8e6-f2e0-45ba-8641-ba4a9f8e9296","resolution":{"observed_at":"2026-08-07T00:43:55.915303Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-08-07T00:25:29.312251Z","title":"LoRA-FA: Memory-efficient low-rank adaptation for large language models fine-tuning.arXiv:2308.03303, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.14280","last_updated":"2025-06-17T07:49:43Z","snapshot_observed_at":"2026-08-10T00:45:16.592204Z","submitted_at":"2025-06-17T07:49:43Z","title":"Improving LoRA with Variational Learning","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T00:25:29.312251Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2506.14280"},"observation_digest":"sha256:78b0401a835e58cbbccad7ab1c1328af70318c31fd8455640d66363b45c8438f","observation_id":"86159505-56da-466d-b389-dda41e029302","resolution":{"observed_at":"2026-08-07T00:25:29.312251Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-08-06T22:50:12.331356Z","title":"Lora-fa: Memory- efficient low-rank adaptation for large language models fine-tuning, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20629","last_updated":"2025-06-25T17:25:02Z","snapshot_observed_at":"2026-08-10T06:54:37.501703Z","submitted_at":"2025-06-25T17:25:02Z","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T22:50:12.331356Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2506.20629"},"observation_digest":"sha256:a188131012fb52af88e8ffad303fc03766fa44979e4f37997a5f033f281e8c9b","observation_id":"5c6837c7-1911-4314-905f-1ef8bbbf7e3a","resolution":{"observed_at":"2026-08-06T22:50:12.331356Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-08-06T17:20:42.301515Z","title":"arXiv preprint arXiv:2308.03303 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.11071","last_updated":"2025-07-15T08:04:31Z","snapshot_observed_at":"2026-08-06T17:14:32.548539Z","submitted_at":"2025-07-15T08:04:31Z","title":"LogTinyLLM: Tiny Large Language Models Based Contextual Log Anomaly Detection","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T17:20:42.301515Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2507.11071"},"observation_digest":"sha256:d541530914dbe998b1cb706e39010aef98bf4606331012bf639f2cda573ca924","observation_id":"0c77f119-3df5-4ca2-88b5-d56227742f61","resolution":{"observed_at":"2026-08-06T17:20:42.301515Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-08-05T17:33:16.928324Z","title":"Lora-fa: Memory-efficient low-rank adaptation for large language models fine-tuning, 2023 a","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.16191","last_updated":"2025-08-22T08:12:06Z","snapshot_observed_at":"2026-08-09T16:09:26.472798Z","submitted_at":"2025-08-22T08:12:06Z","title":"GEM: A Scale-Aware and Distribution-Sensitive Sparse Fine-Tuning Framework for Effective Downstream Adaptation","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-05T17:33:16.928324Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2508.16191"},"observation_digest":"sha256:07ed6f87592ac3148c690cdc20424f0ca07a21c9e0bef48aca2315066b37f859","observation_id":"73a82e9a-bf96-4f26-b2c0-8f502bab158e","resolution":{"observed_at":"2026-08-05T17:33:16.928324Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":"2308.03303","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-07-04T19:10:05.832087Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","venue":"cs.CL","work_id":"caf23d24-5176-4330-bd2a-6cf699d152cd","year":2023},"citing_paper":{"arxiv_id":"2510.24561","last_updated":"2026-06-05T08:45:23Z","snapshot_observed_at":"2026-08-04T07:37:39.304054Z","submitted_at":"2025-10-28T15:55:36Z","title":"LoRA-DA: Data-Aware Initialization for Low-Rank Adaptation via Asymptotic Analysis","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-18T03:00:59.958379Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2510.24561"},"observation_digest":"sha256:4c69f68ef5cc09f79d6ac5c8b9b9fefcaa6838fb49e43a30dac2036565661887","observation_id":"15a616a7-8ec7-4a1c-aca6-a600fc46f61e","resolution":{"observed_at":"2026-05-18T03:02:22.018781Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":"2308.03303","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-07-04T19:10:05.832087Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","venue":"cs.CL","work_id":"caf23d24-5176-4330-bd2a-6cf699d152cd","year":2023},"citing_paper":{"arxiv_id":"2511.11051","last_updated":"2026-05-22T01:46:51Z","snapshot_observed_at":"2026-08-03T00:41:31.601511Z","submitted_at":"2025-11-14T08:06:01Z","title":"NP-LoRA: Null Space Projection for Subject-Style LoRA Fusion","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-25T07:58:25.211030Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2511.11051"},"observation_digest":"sha256:05874075668da089b20acf531b3475e4e86e9387548c5053b485502904d308ee","observation_id":"35b39784-16d7-4b74-b2eb-3271b3df96d6","resolution":{"observed_at":"2026-05-25T08:00:29.669192Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-08-03T20:20:35.847031Z","title":"Lora-fa: Memory-efficient low-rank adapta- tion for large language models fine-tuning.arXiv preprint arXiv:2308.03303, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2511.20302","last_updated":"2026-06-17T13:44:19Z","snapshot_observed_at":"2026-08-10T02:12:40.380732Z","submitted_at":"2025-11-25T13:41:59Z","title":"CrossEarth-Gate: Fisher-Guided Adaptive Tuning Engine for Efficient Adaptation of Cross-Domain Remote Sensing Semantic Segmentation","version":3},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-03T20:20:35.847031Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2511.20302"},"observation_digest":"sha256:494e2c87620202d7bd5b94e56c108fe0f2a512d5a6627cd7fdfbdab5fad33591","observation_id":"8dfc3724-26c7-4709-910e-631d36d1b756","resolution":{"observed_at":"2026-08-03T20:20:35.847031Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":"2308.03303","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-07-04T19:10:05.832087Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","venue":"cs.CL","work_id":"caf23d24-5176-4330-bd2a-6cf699d152cd","year":2023},"citing_paper":{"arxiv_id":"2604.08526","last_updated":"2026-04-09T17:57:50Z","snapshot_observed_at":"2026-08-11T18:25:52.625739Z","submitted_at":"2026-04-09T17:57:50Z","title":"FIT: A Large-Scale Dataset for Fit-Aware Virtual Try-On","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-10T17:47:01.122910Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2604.08526"},"observation_digest":"sha256:43b0eccf1270ab3c340f8d2cedad9a060148350fb378e7f7abc15a7e91bc367c","observation_id":"1c7d63e2-e9a6-41a4-8dac-b02c75dcd1fe","resolution":{"observed_at":"2026-05-11T06:10:58.946249Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":"2308.03303","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-07-04T19:10:05.832087Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","venue":"cs.CL","work_id":"caf23d24-5176-4330-bd2a-6cf699d152cd","year":2023},"citing_paper":{"arxiv_id":"2604.16826","last_updated":"2026-04-18T04:33:16Z","snapshot_observed_at":"2026-08-11T13:00:29.738440Z","submitted_at":"2026-04-18T04:33:16Z","title":"Crowded in B-Space: Calibrating Shared Directions for LoRA Merging","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-10T07:27:21.900575Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2604.16826"},"observation_digest":"sha256:bae8ba2f9ccf07e7fd8ac7d754bdf7d0ef0927bf205d1221a656f8aae79a6f27","observation_id":"1b28dcc7-149e-4566-8590-0c65fcacd896","resolution":{"observed_at":"2026-05-10T07:52:14.020077Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":"2308.03303","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-07-04T19:10:05.832087Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","venue":"cs.CL","work_id":"caf23d24-5176-4330-bd2a-6cf699d152cd","year":2023},"citing_paper":{"arxiv_id":"2604.18124","last_updated":"2026-04-20T11:43:55Z","snapshot_observed_at":"2026-08-11T15:43:26.823470Z","submitted_at":"2026-04-20T11:43:55Z","title":"TLoRA: Task-aware Low Rank Adaptation of Large Language Models","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-05-10T05:07:10.885133Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2604.18124"},"observation_digest":"sha256:221855312ffc8a6db5065ac985fa609f18dba2d1c5015e88e81d24d032654c4f","observation_id":"b8f23920-a24a-4004-b011-f34e6d03f989","resolution":{"observed_at":"2026-05-10T09:48:48.151092Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":"2308.03303","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-07-04T19:10:05.832087Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","venue":"cs.CL","work_id":"caf23d24-5176-4330-bd2a-6cf699d152cd","year":2023},"citing_paper":{"arxiv_id":"2604.19118","last_updated":"2026-04-21T05:56:51Z","snapshot_observed_at":"2026-07-06T23:05:48.885141Z","submitted_at":"2026-04-21T05:56:51Z","title":"DP-FlogTinyLLM: Differentially private federated log anomaly detection using Tiny LLMs","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-05-10T02:49:21.124253Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2604.19118"},"observation_digest":"sha256:7855ff71d206274c5a47774c70f02b09f0ac923e38c2cffab645d6bb5992d6c1","observation_id":"552578cf-06ff-4bc1-b346-0d38db437de0","resolution":{"observed_at":"2026-05-10T02:53:29.815446Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":"2308.03303","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-07-04T19:10:05.832087Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","venue":"cs.CL","work_id":"caf23d24-5176-4330-bd2a-6cf699d152cd","year":2023},"citing_paper":{"arxiv_id":"2604.22018","last_updated":"2026-04-23T19:18:41Z","snapshot_observed_at":"2026-07-06T23:08:28.444591Z","submitted_at":"2026-04-23T19:18:41Z","title":"Foundation models for discovering robust biomarkers of neurological disorders from dynamic functional connectivity","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-08T12:55:43.452286Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2604.22018"},"observation_digest":"sha256:3f3e13b332589d7926eacfaeb351276cc12427cbb607c6aba10b24b2b369afb5","observation_id":"0e183019-9b92-4903-bf8c-387eeb47bcd1","resolution":{"observed_at":"2026-05-11T19:01:17.868182Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":"2308.03303","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-07-04T19:10:05.832087Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","venue":"cs.CL","work_id":"caf23d24-5176-4330-bd2a-6cf699d152cd","year":2023},"citing_paper":{"arxiv_id":"2605.07063","last_updated":"2026-05-08T00:16:11Z","snapshot_observed_at":"2026-08-11T07:15:19.934764Z","submitted_at":"2026-05-08T00:16:11Z","title":"Dr. Post-Training: A Data Regularization Perspective on LLM Post-Training","version":1},"reference_index":205,"source":"arxiv_source","source_observed_at":"2026-05-11T01:57:40.347786Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2605.07063"},"observation_digest":"sha256:0ba8a5aeb95e0666a20d9bc1c4cfd45e80bfc76494b4b79cc141ce8257e76707","observation_id":"ccde1026-bc00-4991-88c8-e11a7f4816dc","resolution":{"observed_at":"2026-05-11T04:05:56.672805Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":"2308.03303","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-07-04T19:10:05.832087Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","venue":"cs.CL","work_id":"caf23d24-5176-4330-bd2a-6cf699d152cd","year":2023},"citing_paper":{"arxiv_id":"2605.08589","last_updated":"2026-05-09T01:10:26Z","snapshot_observed_at":"2026-08-10T23:32:59.772691Z","submitted_at":"2026-05-09T01:10:26Z","title":"S2FT: Parameter-Efficient Fine-Tuning in Sparse Spectrum Domain","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-05-12T01:00:57.628771Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2605.08589"},"observation_digest":"sha256:49ea380717073ab8ec6bc084243f57558163f3f8c35f7d935446b8afa2f72aa6","observation_id":"d10301c7-b707-4ba1-bbc0-008be6f55349","resolution":{"observed_at":"2026-05-12T08:31:25.620627Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":"2308.03303","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-07-04T19:10:05.832087Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","venue":"cs.CL","work_id":"caf23d24-5176-4330-bd2a-6cf699d152cd","year":2023},"citing_paper":{"arxiv_id":"2605.18795","last_updated":"2026-05-11T06:43:14Z","snapshot_observed_at":"2026-07-06T23:29:38.069295Z","submitted_at":"2026-05-11T06:43:14Z","title":"HELLoRA: Hot Experts Layer-Level Low-Rank Adaptation for Mixture-of-Experts Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-20T23:28:16.851459Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2605.18795"},"observation_digest":"sha256:05404edf1aedab48567b6d376cc1842eaf5df66e8c9a068d4c4d9813f6fb29a3","observation_id":"a5f2bf24-d43a-449c-be6a-9307452c5147","resolution":{"observed_at":"2026-05-20T23:29:12.682709Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":"2308.03303","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-07-04T19:10:05.832087Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","venue":"cs.CL","work_id":"caf23d24-5176-4330-bd2a-6cf699d152cd","year":2023},"citing_paper":{"arxiv_id":"2606.03209","last_updated":"2026-06-02T06:08:31Z","snapshot_observed_at":"2026-07-06T23:43:31.629075Z","submitted_at":"2026-06-02T06:08:31Z","title":"DECA: Decentralizing Block-Wise Adam for Efficient LLM Full-Parameter Fine-Tuning on Non-IID Data","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-06-28T11:23:55.146868Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2606.03209"},"observation_digest":"sha256:98909c8d7203e1751bd50672f2930e66e08dbda934d11b3dc786905b74a0ede1","observation_id":"cd70d297-c054-4ca4-8849-2c017704d3e5","resolution":{"observed_at":"2026-07-02T01:56:28.096334Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":"2308.03303","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-07-04T19:10:05.832087Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","venue":"cs.CL","work_id":"caf23d24-5176-4330-bd2a-6cf699d152cd","year":2023},"citing_paper":{"arxiv_id":"2606.08687","last_updated":"2026-06-07T15:39:28Z","snapshot_observed_at":"2026-08-06T05:04:31.914763Z","submitted_at":"2026-06-07T15:39:28Z","title":"Shift-Dependent Asymmetry: Orthogonal Inverse Low-Rank Adaptation for Federated Medical Segmentation","version":1},"reference_index":85,"source":"arxiv_source","source_observed_at":"2026-06-27T18:27:47.338007Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2606.08687"},"observation_digest":"sha256:5c6667b86adc6d15d9ad82d0708862f783af929677d05ef0405c6dd712dd3177","observation_id":"5b54bc41-8cba-4070-89bf-9e90f5f5ef78","resolution":{"observed_at":"2026-07-02T23:07:27.005466Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":"2308.03303","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-07-04T19:10:05.832087Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","venue":"cs.CL","work_id":"caf23d24-5176-4330-bd2a-6cf699d152cd","year":2023},"citing_paper":{"arxiv_id":"2606.12883","last_updated":"2026-06-11T04:19:32Z","snapshot_observed_at":"2026-08-02T22:02:12.932569Z","submitted_at":"2026-06-11T04:19:32Z","title":"The Hidden Power of Scaling Factor in LoRA Optimization","version":1},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-06-27T07:14:08.479610Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2606.12883"},"observation_digest":"sha256:01fec62ed77d94171c8c29a23260eee7903ba83f72e56f73fb28ce62096f49b6","observation_id":"d58a409b-8565-4ebe-bb71-0134865a0b72","resolution":{"observed_at":"2026-07-03T14:08:21.886190Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":"2308.03303","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-07-04T19:10:05.832087Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","venue":"cs.CL","work_id":"caf23d24-5176-4330-bd2a-6cf699d152cd","year":2023},"citing_paper":{"arxiv_id":"2606.19528","last_updated":"2026-06-17T19:20:06Z","snapshot_observed_at":"2026-08-02T10:25:23.230319Z","submitted_at":"2026-06-17T19:20:06Z","title":"Techniques for Peak Memory Reduction for LoRA Fine-tuning of LLMs on Edge Devices","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-26T21:05:49.893508Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2606.19528"},"observation_digest":"sha256:8ebbc5912bfb7108e34e2d4a85a28fe72e0c5e6144a563f2f81426a6fb69fab1","observation_id":"7f614484-6c83-42ac-b4ad-a670d18a609f","resolution":{"observed_at":"2026-07-04T00:39:16.823803Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":"2308.03303","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-07-04T19:10:05.832087Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","venue":"cs.CL","work_id":"caf23d24-5176-4330-bd2a-6cf699d152cd","year":2023},"citing_paper":{"arxiv_id":"2606.25285","last_updated":"2026-06-24T01:37:27Z","snapshot_observed_at":"2026-08-05T16:07:49.390070Z","submitted_at":"2026-06-24T01:37:27Z","title":"EPTS: Elastic Post-Training Sparsity for Efficient Large Language Model Compression","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-06-25T21:35:44.591342Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2606.25285"},"observation_digest":"sha256:3004bf5036afb4ee2c4ae6e7441dbb89e5352b971611d28541266139bbe5d6db","observation_id":"defdf4e7-d3f4-49ba-b0e0-ca44150a045b","resolution":{"observed_at":"2026-07-04T19:10:05.834097Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":"2308.03303","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-07-04T19:10:05.832087Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","venue":"cs.CL","work_id":"caf23d24-5176-4330-bd2a-6cf699d152cd","year":2023},"citing_paper":{"arxiv_id":"2606.29184","last_updated":"2026-06-28T04:08:09Z","snapshot_observed_at":"2026-08-04T15:21:29.245858Z","submitted_at":"2026-06-28T04:08:09Z","title":"BaRA: Bayesian Adaptive Rank Allocation for Parameter-Efficient Fine-Tuning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-06-30T07:55:13.502149Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2606.29184"},"observation_digest":"sha256:a9514d7741a61312ed62a13be3187eeb2146f352170542b3aee628b11b621499","observation_id":"771d6e7a-818a-4f19-b56d-a54699744e9f","resolution":{"observed_at":"2026-06-30T08:04:28.526837Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":"2308.03303","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-07-04T19:10:05.832087Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","venue":"cs.CL","work_id":"caf23d24-5176-4330-bd2a-6cf699d152cd","year":2023},"citing_paper":{"arxiv_id":"2606.29209","last_updated":"2026-06-28T05:20:37Z","snapshot_observed_at":"2026-08-02T09:04:26.737793Z","submitted_at":"2026-06-28T05:20:37Z","title":"AnyBody: Free-Form Whole-Body Humanoid Control from Arbitrary Keypoint Guidance","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-06-30T07:44:51.002937Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2606.29209"},"observation_digest":"sha256:52c4e4eef22a96a704d05ea48864e248ad0fcf54cf52eee81d7902238c913215","observation_id":"6bdfe00a-0218-4701-a7d5-c8f6269c0520","resolution":{"observed_at":"2026-06-30T08:04:28.836451Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":"2308.03303","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-07-04T19:10:05.832087Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","venue":"cs.CL","work_id":"caf23d24-5176-4330-bd2a-6cf699d152cd","year":2023},"citing_paper":{"arxiv_id":"2606.31208","last_updated":"2026-06-30T06:40:36Z","snapshot_observed_at":"2026-08-01T15:26:30.335537Z","submitted_at":"2026-06-30T06:40:36Z","title":"Probing Memorization of Tabular In-Context Learning","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-07-01T06:37:44.328625Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2606.31208"},"observation_digest":"sha256:a806dcf348cb12a0177007d5fba4b1ed5be854293959cb92423f3039b798e048","observation_id":"cc95c155-6589-4428-96f8-331a15f479da","resolution":{"observed_at":"2026-07-01T09:25:40.747132Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-07-14T16:23:01.601553Z","title":"Lora-fa: Memory-efficient low-rank adaptation for large language models fine-tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.09757","last_updated":"2026-08-01T14:09:44Z","snapshot_observed_at":"2026-08-06T23:11:23.484259Z","submitted_at":"2026-07-05T13:58:38Z","title":"RSRA: Training-Free Probing of Representation Sensitivity for Efficient LoRA Rank Allocation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-14T16:23:01.601553Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2607.09757"},"observation_digest":"sha256:549d9724e68e78133d471d93aec6cc4b4b69f18961622ac0bc294e591af98c32","observation_id":"c692bccc-4448-4a9d-b0d3-3062d758ed51","resolution":{"observed_at":"2026-07-14T16:23:01.601553Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-08-04T04:34:34.499526Z","title":"arXiv preprint arXiv:2308.03303 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.09757","last_updated":"2026-08-01T14:09:44Z","snapshot_observed_at":"2026-08-06T23:11:23.484259Z","submitted_at":"2026-07-05T13:58:38Z","title":"RSRA: Training-Free Probing of Representation Sensitivity for Efficient LoRA Rank Allocation","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-04T04:34:34.499526Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2607.09757"},"observation_digest":"sha256:148ed1a355939ca930d6e4665411e46c1bea9a35dca35c1992693ccc66705588","observation_id":"5bf00fb3-5a5b-494b-bb28-606af656d52d","resolution":{"observed_at":"2026-08-04T04:34:34.499526Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-08-01T18:39:20.155492Z","title":"Lora-fa: Memory-efficient low-rank adaptation for large language models fine-tuning.arXiv preprint arXiv:2308.03303, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.17244","last_updated":"2026-08-03T10:33:00Z","snapshot_observed_at":"2026-08-09T05:11:54.050471Z","submitted_at":"2026-07-19T13:25:05Z","title":"DynImmune-BERT: Dynamic Immune Repertoire Modeling with Neural ODE Driven Continuous Transformers","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-01T18:39:20.155492Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2607.17244"},"observation_digest":"sha256:7b4247351baa2bb2d65e18b69088f3134dac449b83a56988aa4f561c6c4a3890","observation_id":"c69e299f-8a47-4127-bd18-e32f58305c61","resolution":{"observed_at":"2026-08-01T18:39:20.155492Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-08-04T04:12:47.933215Z","title":"Lora-fa: Memory-efficient low-rank adaptation for large language models fine-tuning.arXiv preprint arXiv:2308.03303, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.17244","last_updated":"2026-08-03T10:33:00Z","snapshot_observed_at":"2026-08-09T05:11:54.050471Z","submitted_at":"2026-07-19T13:25:05Z","title":"DynImmune-BERT: Dynamic Immune Repertoire Modeling with Neural ODE Driven Continuous Transformers","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-04T04:12:47.933215Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2607.17244"},"observation_digest":"sha256:ce84265653894ee9bd238a5a5d57e286f08f7730ec25a9116e89296b6bf2d8df","observation_id":"93916948-413b-4e24-8539-f4cfe80c125d","resolution":{"observed_at":"2026-08-04T04:12:47.933215Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2308.03303/citation-record","integrity":"/paper/2308.03303/integrity","json":"/paper/2308.03303/citation-record.json","paper":"/paper/2308.03303"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-09T00:05:48.311803Z","title":"write newline","venue":null,"work_id":"8e5fda61-e601-4df4-8204-015bee341570","year":null},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:6e80a668f1b76e5dc4e6a0b3937ef866a775b7f73ec19543f66ef90c1f4bfe39","observation_id":"442f23a6-d0ab-4d2c-b40d-982dbcc8f0de","resolution":{"observed_at":"2026-05-24T08:06:04.230444Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-08T23:55:44.012295Z","title":"@esa (Ref","venue":null,"work_id":"b058608d-98d0-4821-a4ae-403d2b7cd411","year":null},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:3a7ba976b8e82d0d2beb33ac2725ea4db5fb91237fdcc076c369349c7e7a398f","observation_id":"358f292c-2d0b-4243-b7a6-51a1a7154194","resolution":{"observed_at":"2026-05-24T08:06:04.220231Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-09T00:05:48.337191Z","title":null,"venue":null,"work_id":"ea79bfb8-d434-45e9-8607-416d3839ec5c","year":null},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:a29e1f960b16f8a4787e6d8b2ebe9b64992406c3ff35eb4bdd7d76c3576cef2e","observation_id":"60059079-eb52-47d5-90f2-369a577b972c","resolution":{"observed_at":"2026-05-24T08:06:04.210366Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"247b6d3b-d445-452a-be73-2b003de65f5c","year":null},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:da9c1bc7bd98c0a20728c072092e689a6ee039f99164ee3cb650250478078ab0","observation_id":"7cf47b25-1dc1-4d77-90f7-e23051196be7","resolution":{"observed_at":"2026-05-24T08:06:04.215943Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Falcon-40b: an open large language model with state-of-the-art performance","venue":null,"work_id":"d3ddabd0-4165-4be6-a3bc-40121f35b863","year":2023},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:f9e817dd42b15961647c93df08ee363d43c50fbeec94581d81fa7e126cb906f1","observation_id":"572d5c97-b652-484b-9c16-885c64d2f665","resolution":{"observed_at":"2026-05-24T08:06:04.213111Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Dai, Orhan Firat, Melvin Johnson, Dmitry Lepikhin, Alexandre Passos, Siamak Shakeri, Emanuel Taropa, Paige Bailey, Zhifeng Chen, and Eric Chu et al","venue":null,"work_id":"2cd554d6-a45a-4eb4-8ce5-2007ced14356","year":2023},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:d94dcec1445344da70c8775885ace20590ad5fbeee7fa0c90dbea083f7ebd64d","observation_id":"49c786c7-f4e5-4bd5-8f99-b5c5608ec20b","resolution":{"observed_at":"2026-05-24T08:06:04.226668Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.05862","last_updated":"2022-04-12T15:02:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-04-12T15:02:38Z","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","version":1},"cited_work":{"arxiv_id":"2204.05862","doi":"10.1016/j.respol.2005.01.014","metadata_source":"pith","pith_arxiv_id":"2204.05862","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","venue":"cs.CL","work_id":"a1f2574b-a899-4713-be60-c87ba332656c","year":2022},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"cited_paper":"/paper/2204.05862","citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:7eb7a4e0ce4453956751c01eb96c44ab1dfe8337212db31e014b0e15a53e7fd0","observation_id":"52f2f4c5-f1d1-4fec-8f45-ceae88803e2c","resolution":{"observed_at":"2026-05-24T08:06:03.871751Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2022.acl-short.1","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"B it F it: Simple parameter-efficient fine-tuning for transformer-based masked language-models","venue":null,"work_id":"377562cd-e5ee-4074-b449-3282a6a345c6","year":2022},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:853e42bb17e1d88ab9c2380577420be275176414601d2d557bd17930ea1c0343","observation_id":"45ed7e35-1f4c-4545-81e4-224636cbc880","resolution":{"observed_at":"2026-05-24T08:06:03.711687Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-03T23:38:06.825036+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-03T23:38:06.825036+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Language models are few-shot learners","venue":null,"work_id":"b5af3a68-2622-4421-b39b-b1d2fbde2d8d","year":1901},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:70ae502e52f60e840305ce50ebec5d40acc6f2b198e2bf7ac9cea76dc856b701","observation_id":"20e3d23b-06fe-4dfd-84e0-135fb463bb3b","resolution":{"observed_at":"2026-05-24T08:06:04.109913Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"One-for-all: Generalized lora for parameter-efficient fine-tuning","venue":null,"work_id":"c534d49f-a716-4efb-a17d-c02cbe9e3d0d","year":2023},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:97be70eff25d7da9d704ce6ca71b5df955f6a11ca3609912a0ce2d14bb447605","observation_id":"4ca78237-8d2f-4aa1-aaaf-b5c783adaa78","resolution":{"observed_at":"2026-05-24T08:06:04.086527Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1604.06174","last_updated":"2016-04-22T19:21:36Z","snapshot_observed_at":"2026-08-08T09:03:25.135475Z","submitted_at":"2016-04-21T04:15:27Z","title":"Training Deep Nets with Sublinear Memory Cost","version":2},"cited_work":{"arxiv_id":"1604.06174","doi":"10.48550/arxiv.1604.06174","metadata_source":"pith","pith_arxiv_id":"1604.06174","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Training Deep Nets with Sublinear Memory Cost","venue":"cs.LG","work_id":"f2c5c287-a500-40e4-a136-e7e3172db1d7","year":2016},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"cited_paper":"/paper/1604.06174","citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:faddf36e28c1239f19e0dbdd7fcb231d057c6d02ac8160cca3aa7b4280ac79a7","observation_id":"0cd47c57-7d9c-486d-9d53-d3fc9268b5d9","resolution":{"observed_at":"2026-05-24T08:06:03.867002Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-05-21T12:26:33.666045+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-21T12:26:33.666045+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Gonzalez, Ion Stoica, and Eric P","venue":null,"work_id":"fc02f9f4-cc6e-40b8-89c3-6214feb7c9cc","year":2023},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:82db19ed3ce8cf309e3a58a46051cb3be5282d8aa619fe92eec0d2766e0bd80d","observation_id":"a020ae7e-a545-4a55-b25b-bbfbeb13026e","resolution":{"observed_at":"2026-05-24T08:06:04.120019Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.11416","last_updated":"2022-12-06T21:39:48Z","snapshot_observed_at":"2026-07-06T14:08:18.855958Z","submitted_at":"2022-10-20T16:58:32Z","title":"Scaling Instruction-Finetuned Language Models","version":5},"cited_work":{"arxiv_id":"2210.11416","doi":"10.48550/arxiv.2210.11416","metadata_source":"pith","pith_arxiv_id":"2210.11416","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Scaling Instruction-Finetuned Language Models","venue":"cs.LG","work_id":"8405abb1-7558-4fdf-af24-f4c52fa77a06","year":2022},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"cited_paper":"/paper/2210.11416","citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:19e74cd1e157dccd7bb947d56dcb6c0a3729e90f10a8e8ae987b931e5c75941a","observation_id":"86a16296-e5e0-4732-b759-4fc8f9f517d3","resolution":{"observed_at":"2026-05-24T08:06:03.862532Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Unimax: Fairer and more effective language sampling for large-scale multilingual pretraining","venue":null,"work_id":"4c4cb3ce-8ac1-44ed-bf80-fcd49958a9c6","year":2023},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:cd4e174fd9c2e74d38910c2b610d4de6b0e5edd4d37f8b5ce927155429362e01","observation_id":"b951a25f-4cf7-42f0-885e-de71ad7cffdc","resolution":{"observed_at":"2026-05-24T08:06:04.188696Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Think you have solved question answering? try arc, the ai2 reasoning challenge","venue":null,"work_id":"a6879b4b-4c12-4298-8700-5de5c6bc4bcb","year":2018},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:60a436f98d86b6cdefa6156684b33d21a9cbc5230abe00654bc02f8fb9828599","observation_id":"47fe3c8c-d391-4f85-93ac-a7433d5cef1e","resolution":{"observed_at":"2026-05-24T08:06:04.180138Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Flashattention: Fast and memory-efficient exact attention with io-awareness","venue":null,"work_id":"9aca31c0-c7f0-47a1-94d9-b519eea26f77","year":2022},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:62e75eac838895d2824abead0f305c851563744d8f18fc9161ee67e0a2687c2c","observation_id":"45eca4cc-8b90-454c-98cc-317ccd9792ce","resolution":{"observed_at":"2026-05-24T08:06:04.177414Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"c1985219-0cc0-4802-9f00-28ad47fdd262","year":2022},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:f3a5dcd50a6b386e90f59398e05e20a66517f57ace2be328ab0efd511a9c506e","observation_id":"a000ebd1-4b44-4bfc-8176-ed8ca9963dc1","resolution":{"observed_at":"2026-05-24T08:06:04.174635Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"8-bit optimizers via block-wise quantization","venue":null,"work_id":"1fc67171-9080-4a05-a7fe-b41b9eb45446","year":2022},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:dd04439607555c8e8bed4dcefebf2f677fa242a1009de95c1ba821bfb6d98853","observation_id":"1b122660-5cd2-4515-bca8-7cd995f662f7","resolution":{"observed_at":"2026-05-24T08:06:04.143899Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.14314","last_updated":"2023-05-23T17:50:33Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-05-23T17:50:33Z","title":"QLoRA: Efficient Finetuning of Quantized LLMs","version":1},"cited_work":{"arxiv_id":"2305.14314","doi":"10.1007/978-3-031-86644-9","metadata_source":"pith","pith_arxiv_id":"2305.14314","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"QLoRA: Efficient Finetuning of Quantized LLMs","venue":"cs.LG","work_id":"d3fdf68e-3a5e-48b5-8a18-7a9137479c55","year":2023},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"cited_paper":"/paper/2305.14314","citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:7312a281b4c15bdc95d1d589b585cc4becd9e0810cb1aa88ed81ac7c30c92c8e","observation_id":"639896a1-47ff-4c28-bec9-dc8726028eea","resolution":{"observed_at":"2026-05-24T08:06:03.880596Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/n19-1423","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"BERT : Pre-training of Deep Bidirectional Transformers for Language Understanding","venue":"Proceedings of the 2019 Conference of the North","work_id":"3e3c8ac8-b858-4b22-af32-393d98c883e0","year":2019},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:dc5132654fb26db6eecddbc5a89818308191036ed1de54b4dd436960249f43d3","observation_id":"003c5c9f-723a-4065-a862-02b62558041a","resolution":{"observed_at":"2026-05-24T08:06:03.703452Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-10T21:38:27.423116+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-10T21:38:27.423116+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Open llm leaderboard","venue":null,"work_id":"34c0d03e-9e66-481c-af53-82a15e0fedb3","year":2023},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:f9cf0a516e77a5387b4073ad5f6d572f99871ab418720f77acb5714928f4a70b","observation_id":"6cdea12f-e901-413f-95e9-3ebdbf80dd3c","resolution":{"observed_at":"2026-05-24T08:06:04.223071Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.5281/zenodo.5371628","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"A framework for few-shot language model evaluation, September 2021","venue":"Zenodo (CERN European Organization for Nuclear Research)","work_id":"27d00efc-1c8b-4af4-bd30-5dfa575d0989","year":2021},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:cabfffc46c9c99ec18b84a4803ea6576314ba1d61fb1703fa3fb4030ed215749","observation_id":"264be4f7-6f64-41c4-9549-4a07da1b2c20","resolution":{"observed_at":"2026-05-24T08:06:03.706414Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-07-12T10:19:41.045161+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-12T10:19:41.045161+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2022.acl-long.576","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"PPT : Pre-trained prompt tuning for few-shot learning","venue":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","work_id":"cee3c16e-991f-4ba2-ac95-7cf886dbef0b","year":2022},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:8f1c60e67d854dac66ce4cdba8092b9886dc160bdb88661844d3c7bfec1d80c9","observation_id":"c6cfed2f-40b4-46d7-aa8e-99d3ff568a69","resolution":{"observed_at":"2026-05-24T08:06:03.701064Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Deberta: Decoding-enhanced bert with disentangled attention","venue":null,"work_id":"dc096e50-7e06-4298-b7cb-10b498e3b100","year":2020},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:91654ae3a19142fecabacc08da94a22963d6eacf95fa8df6e89f3b09e6ff5c34","observation_id":"b26856ca-ca56-48d9-825f-f4e78c48c25d","resolution":{"observed_at":"2026-05-24T08:06:04.154310Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-09T12:46:15.047800Z","title":"Measuring massive multitask language understanding","venue":null,"work_id":"919cb2d6-3af1-449e-bdb7-3701fe2984a4","year":2021},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:207591535a8e8082bf84293c2f2d4c1a7b629bd5267e89d135cb481fb4b42910","observation_id":"53edb4d7-8638-400b-888d-b163f9595e19","resolution":{"observed_at":"2026-05-24T08:06:04.145621Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09689","last_updated":"2022-12-19T18:21:00Z","snapshot_observed_at":"2026-07-06T14:32:33.541029Z","submitted_at":"2022-12-19T18:21:00Z","title":"Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor","version":1},"cited_work":{"arxiv_id":"2212.09689","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2212.09689","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Unnatural instructions: Tuning language models with (almost) no human labor.arXiv preprint arXiv:2212.09689","venue":null,"work_id":"5f39ecf9-90b2-43a6-afa0-31c49f589257","year":2022},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"cited_paper":"/paper/2212.09689","citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:6750baef9da2b43a2bcafce7c3c2203a482e8010613586ab5e389f9fd54879c0","observation_id":"c10bb012-c057-4b71-9780-514004942810","resolution":{"observed_at":"2026-05-24T08:06:03.876259Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Parameter-efficient transfer learning for nlp","venue":null,"work_id":"34fc2971-b2f2-4b08-9fe5-a66e3ab7cd5f","year":2019},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:b21ed6d914bc7052c5f94c13bba4df9ea849673fe2d29d284789f93eed945d9a","observation_id":"0e438317-165c-43fb-9563-12d63e4d180f","resolution":{"observed_at":"2026-05-24T08:06:04.166533Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Lo RA : Low-rank adaptation of large language models","venue":null,"work_id":"4afaf8a7-3e8b-4c4b-94bf-defa14899539","year":2022},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:b3e912b59297afab6455a161b93ad06bbe09b18f9bcaffdbf017e89d17b6e3fb","observation_id":"939c912c-be8b-4d42-97b9-aadd8a91cd77","resolution":{"observed_at":"2026-05-24T08:06:04.165326Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Lorahub: Efficient cross-task generalization via dynamic lora composition","venue":null,"work_id":"b698f120-4706-40e2-a638-e2f926b3648d","year":2023},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:4d2f347b33a36a2b45572996a8cdee9a368783e931af999cf166b963f9df62bc","observation_id":"062f81f4-ff5c-4f1d-9525-00d4181ac7e6","resolution":{"observed_at":"2026-05-24T08:06:04.155524Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Quantization and training of neural networks for efficient integer-arithmetic-only inference","venue":null,"work_id":"9d524691-d700-4ec9-9c62-bea5f6682b2e","year":2017},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:2b1b97f12238baa520e77194b81e4de648dbfeb82c9badffe3f223833ca6b10e","observation_id":"103e7785-229d-40c2-8b80-50e7007ad897","resolution":{"observed_at":"2026-05-24T08:06:04.121996Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Gonzalez","venue":null,"work_id":"c7e1fae6-9e39-403d-b510-0322b02728c3","year":2020},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:ff4a8c5d9f9d9f0c6c9aa2297aaedbe1c69361c96b83bdfe314064a92acaf425","observation_id":"de38019a-ff8f-4e5d-bbd7-150ce4adcc36","resolution":{"observed_at":"2026-05-24T08:06:04.127068Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Bert: Pre-training of deep bidirectional transformers for language understanding","venue":null,"work_id":"14025c4b-3a7d-43b9-a62f-5ee4310673dc","year":2019},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:099025b32b4d8a30071762e4834bf9cf8fc94635a0930a98329786dd2ec04611","observation_id":"4264a361-e2ff-4a8a-9dd4-e81c14bf387a","resolution":{"observed_at":"2026-05-24T08:06:04.200730Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1609/aaai.v33i01.33016586","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Semantic sentence matching with densely-connected recurrent and co-attentive information","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","work_id":"6584fc9a-708c-4580-b7ff-a3f3e8305ebd","year":2019},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:d80f75a4e03a08225aa7c1611cd2cd1713f7c3a2e59dc5496b587a3bd35368eb","observation_id":"7a16d951-64e3-40c0-b019-a67ff313a7b3","resolution":{"observed_at":"2026-05-24T08:06:03.698828Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Reducing activation recomputation in large transformer models","venue":null,"work_id":"539789ca-61c2-4026-9728-680268845d35","year":2023},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:cd726c7ca2a901e2eab617b7b7982e561fc18e67a63b21ecc5ff673bd825a59e","observation_id":"433e8d73-fb7e-40a6-88bd-a93d6a4626b9","resolution":{"observed_at":"2026-05-24T08:06:04.124722Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"The power of scale for parameter-efficient prompt tuning","venue":null,"work_id":"0b35d7c3-0c21-4434-ba75-537e268630fa","year":2021},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:edcc089a331fab7fd86ff938f7c75f46e2c6c4a3c297e2b857c9d2e4e7820ac1","observation_id":"85fb1ccc-aea6-41d1-86bb-24396d892beb","resolution":{"observed_at":"2026-05-24T08:06:04.152856Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Prefix-tuning: Optimizing continuous prompts for generation","venue":null,"work_id":"53039ea2-3d16-4667-931a-ee1c65d0e977","year":2021},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:f21de7f31902e9a19a3637d1259b122dca8db6f49e9ba0a245f35e881b7c76e3","observation_id":"2feef5f0-4623-4f51-9866-ad8061ffc5ef","resolution":{"observed_at":"2026-05-24T08:06:04.183120Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Stack more layers differently: High-rank training through low-rank updates","venue":null,"work_id":"ced03c34-c142-4957-8dc7-aa65921d993e","year":2023},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:ae22b450260d3f69b07eda0911e2221c207b5132f54c3eea104e856d37ae9bd9","observation_id":"b71385c3-589b-433d-bea5-52e826fe6dec","resolution":{"observed_at":"2026-05-24T08:06:04.169576Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Truthfulqa: Measuring how models mimic human falsehoods","venue":null,"work_id":"66c287a5-ac6b-4acf-b207-6703a9d3274d","year":2022},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:2ab3cd266675d2d9342736aa8dec27417946c7836771b366b473cf59bb18096d","observation_id":"05ebadec-728d-4c4a-9191-47cadbaec473","resolution":{"observed_at":"2026-05-24T08:06:04.157045Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning","venue":null,"work_id":"0d5123d5-eb7d-47ac-9ac9-26aa385f1b9e","year":2022},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:1742c0adf51aa237005aa180652b57c9ed7cb767a1b792efcfc39c0d2284a632","observation_id":"a70ba7b4-42b0-44a3-8dd1-4eef4c442f34","resolution":{"observed_at":"2026-05-24T08:06:04.197978Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Gpt understands, too","venue":null,"work_id":"ebd65f8b-afcc-42c1-a1dd-e932e0f05a2e","year":2021},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:bee296c97fc5d998bf4691ceffc92e992685dbbb97ab88387e85c70a68c46614","observation_id":"5b5a90ae-63d3-42b8-9557-3bb39e62bef2","resolution":{"observed_at":"2026-05-24T08:06:04.181264Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Roberta: A robustly optimized bert pretraining approach","venue":null,"work_id":"681a238e-f94c-4b16-a3d7-8c9da755aecf","year":2019},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:b59d0a51e5877876ca434de05486087c9f028a92c3551ec61947eb4862ed78b8","observation_id":"1f79757a-5031-4f12-b636-32264ffeba97","resolution":{"observed_at":"2026-05-24T08:06:04.191950Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Decoupled weight decay regularization","venue":null,"work_id":"99cd1b21-8953-47c8-9cc2-97f5714d5c5f","year":2017},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:bfbde36021529b407e3858ea8e2b84bbfca7ca94b0eeb800e6c41d232107aba4","observation_id":"89287c10-b913-44ae-9cb9-355e1b4850fa","resolution":{"observed_at":"2026-05-24T08:06:04.140645Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-10T07:26:54.787661Z","title":"Gpt-4 technical report","venue":null,"work_id":"388f534c-855a-4366-b933-f07bf3e2db5f","year":2023},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:4d16c0e7aa53fa43a99da8d2ac24bbb4aa4cc77859b211b221c064970459d473","observation_id":"39da7f75-5e7f-4ad3-ac6f-6efcd4dc7c09","resolution":{"observed_at":"2026-05-24T08:06:04.206098Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Training language models to follow instructions with human feedback","venue":null,"work_id":"419d5fd7-fcec-439f-b29a-d31dcb6533dc","year":2022},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:c32910b213c7bf13153c4fec411868448dd6cdb2b71c107362e37b5469c154e0","observation_id":"c1368b10-3152-48cd-a3d3-979c70e5b929","resolution":{"observed_at":"2026-05-24T08:06:04.137637Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"77f70b47-1236-4fbb-bed7-c80cb9eda994","year":2020},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:e06a7ededfa4518a3c0a523f8cac9276996133508f3a1c0072538b53f4be5d2b","observation_id":"64089540-560c-4f25-be53-aabf13aaa8ac","resolution":{"observed_at":"2026-05-24T08:06:04.161495Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Zero: Memory optimizations toward training trillion parameter models","venue":null,"work_id":"503632b8-f687-4c7b-96d1-b3006b40d3b6","year":2020},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:ff0805ddd57ce4d15a1d41f28ebbc900ee4337fdf8635fe9c3b831b3da4171c8","observation_id":"f88f6c02-ec99-4394-b5b8-5de0afd15d0f","resolution":{"observed_at":"2026-05-24T08:06:04.194926Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Zero-offload: Democratizing billion-scale model training","venue":null,"work_id":"6036585d-4bae-44d8-ac59-8a8528abc3ad","year":2021},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:745b9ec965bf7b5dc5e7224162bd431c7aafc8fb3513a45e99199ef2e190cd9e","observation_id":"8e93b333-92f9-4278-85f8-3ca18ccbd760","resolution":{"observed_at":"2026-05-24T08:06:04.202848Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-10T17:07:26.483530Z","title":"Megatron-lm: Training multi-billion parameter language models using model parallelism","venue":null,"work_id":"23281401-4f0f-4944-a9aa-59b314d8a477","year":2020},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:f104fa2105efbc4d656b77e83d66a55c307b179e29824a84d7680cacf3637590","observation_id":"288152c9-da21-4440-9f5f-761290cb083c","resolution":{"observed_at":"2026-05-24T08:06:04.172445Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Using deepspeed and megatron to train megatron-turing nlg 530b, a large-scale generative language model","venue":null,"work_id":"ba0a38cc-b0f9-438f-ad02-42b6aa7231f6","year":2022},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:5daf5a06e44a4075c02acac5b8bb662ad120fbf5bf1bc6af3d8aff913b307ffa","observation_id":"9c86b226-4fd5-4f2f-87ce-e0fe11e7baaf","resolution":{"observed_at":"2026-05-24T08:06:04.059791Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Manning, Andrew Ng, and Christopher Potts","venue":null,"work_id":"b8013881-42dc-4112-9866-691c776adc4b","year":2013},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:df5cc05c8c3462b0b94cbce61d0890c84f10cebf9dd92829272e88b7015f52af","observation_id":"0c3de994-c53c-4dcc-9680-687fb38d3911","resolution":{"observed_at":"2026-05-24T08:06:04.099663Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-09T02:55:53.827539Z","title":"Hashimoto","venue":null,"work_id":"35104f7e-ffc3-488e-b66a-a4d3d230e657","year":2023},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:402ac584cef4b8d583a05eef2bafd19ac80d4da0193ef26ab02366354cbfb4b3","observation_id":"41d3285f-4a40-4d12-9406-db9eac259952","resolution":{"observed_at":"2026-05-24T08:06:04.136603Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Llama: Open and efficient foundation language models, 2023 a","venue":null,"work_id":"0f9bdd97-cf09-4fd5-bb4c-83abce3e07eb","year":2023},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:5bc35d934c2e2e50996fc166c08f8ddbed8ba94c494b935b6049969cf9cbe72a","observation_id":"ac85a8ab-b792-4914-a303-53d135d5b054","resolution":{"observed_at":"2026-05-24T08:06:04.099185Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Llama 2: Open foundation and fine-tuned chat models, 2023 b","venue":null,"work_id":"ac639a94-0a2a-4b78-9e51-82b4e3345cbb","year":2023},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:26fe130621c6d9055aea82c649ea729462a1088df5b5a766ab8442c736ed1a9c","observation_id":"1288c17f-6afb-4b7f-80b1-2a544a80e0bc","resolution":{"observed_at":"2026-05-24T08:06:04.203377Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Attention is all you need","venue":null,"work_id":"9097e3f1-2892-4999-afad-052280788dad","year":2017},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:943980ace26baa7735a18aa30aadbd59893e1ba2fdebb171aa277b2686baf6b6","observation_id":"84e3185b-3778-40cf-ba02-4838f2c19480","resolution":{"observed_at":"2026-05-24T08:06:04.126786Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Powersgd: Practical low-rank gradient compression for distributed optimization","venue":null,"work_id":"b24c3dd3-bf96-4b81-bbfd-fbd03623fe2a","year":2019},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:fefa28e1f3b28407a1010a350620608e03695bbd9cbfdcead0835acb8252f8b9","observation_id":"d401b4b1-4478-4d4a-8257-5118debdc895","resolution":{"observed_at":"2026-05-24T08:06:04.083079Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"ef9a5ce8-599d-4ca7-87f9-7a103bb36471","year":2019},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:ce6f2902172ac7ad28aa5f4f3c92c91b4fefd55532c8dc574368cd9da73f7171","observation_id":"1d74bad4-1afb-4bf3-81bc-c0aeb27ecc7c","resolution":{"observed_at":"2026-05-24T08:06:04.149916Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Smith, Daniel Khashabi, and Hannaneh Hajishirzi","venue":null,"work_id":"ef66df99-d7e7-4bf0-90fd-9f2727b65358","year":2022},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:8e0ccaf4a35465dacd752a3e1bae60d0e5468cb1c7131b1bc809cf86f9e53f98","observation_id":"415b37ec-a5d5-4b8f-ab4d-41d7ff74b838","resolution":{"observed_at":"2026-05-24T08:06:04.077866Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"23f13e1e-639a-4b99-800b-d5c3ef3fa0ae","year":2022},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:f5f6cc69e923d05eed55698c395138acb14a89dee5a4c673d69db8945ca4acb4","observation_id":"34f3bd10-cd6a-4b68-a01b-4ff44187de92","resolution":{"observed_at":"2026-05-24T08:06:04.186011Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"da0829ff-2e8e-4c37-8f60-2cb265a24440","year":2019},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:d7cb5fd2dbc8fdf9f93e5bc741eea878d4efb70d7678f8294d707007bf628558","observation_id":"1804d4a1-fb82-4e64-b269-78b78ab1b8c7","resolution":{"observed_at":"2026-05-24T08:06:04.093034Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Finetuned language models are zero-shot learners","venue":null,"work_id":"a83beaab-d957-4a11-b0dd-5f7f4dc99560","year":2021},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:724f81190cfd2b1041dcc60ac34ba56f5b076e9620e70f565e0b9120dfe1cbcd","observation_id":"82a84a5a-eb6c-4b9b-8a9d-b55f085f1933","resolution":{"observed_at":"2026-05-24T08:06:04.187692Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"805ff701-3aff-4452-a1c4-4c655115b5a8","year":2020},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:97e6bf3a4f90362df4b390670bb68a13f5aaf3f823bb8c1f29a24fbcafc58e7b","observation_id":"469d0048-a69d-432c-bc91-2c16b128db80","resolution":{"observed_at":"2026-05-24T08:06:04.184347Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2021.naacl-main.41","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"m T 5: A massively multilingual pre-trained text-to-text transformer","venue":null,"work_id":"dfd5e52f-7d86-495f-9b43-5e2968d26f22","year":2021},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:7239e1f9166f9608958382e1c24777d97e2f5739304c7f9019820cfee3c209ec","observation_id":"e0da3654-6adc-4144-893a-8693eeda1daf","resolution":{"observed_at":"2026-05-24T08:06:03.709304Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T01:08:26.654534+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-11T01:08:26.654534+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1162/tacl_a_00461","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"ByT5: Towards a Token-Free Future with Pre-trained Byte-to-Byte Models","venue":"Transactions of the Association for Computational Linguistics","work_id":"331c5416-83c6-49ce-b1e1-74fccb7fb9bc","year":2022},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:a3ef5b882348cde325f27c5aedc9d2b8ddf4873b0b7d939316f3e8e8898363b9","observation_id":"1f231075-f618-41d2-b4db-36d6d22b3884","resolution":{"observed_at":"2026-05-24T08:06:03.696222Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-07-20T15:52:54.089962+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-20T15:52:54.089962+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Hellaswag: Can a machine really finish your sentence?","venue":null,"work_id":"5ab70cfb-db2b-44c7-b495-9fc286cd931d","year":2019},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:d3d71fdda05422d105a533cd50c4ad415b8acbf620e927738697aece786a19db","observation_id":"649611cd-7a2f-48d3-a373-8e2633c3139e","resolution":{"observed_at":"2026-05-24T08:06:04.088787Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Evaluation and optimization of gradient compression for distributed deep learning","venue":null,"work_id":"7ef67238-0543-450d-b580-62dbe3f0089e","year":2023},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:a7cf6a317cd45d2093840b2535f9a96a9b34cf300aea34e7dbda288b0056ff1e","observation_id":"6df7512b-fef0-4e41-8e16-9757165ca005","resolution":{"observed_at":"2026-05-24T08:06:04.169870Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Adaptive budget allocation for parameter-efficient fine-tuning","venue":null,"work_id":"ad9cd8a7-24f8-43fa-be80-ad10a0f6d0b7","year":2023},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:77fbcfa59a2932c116d7807aaac5b4f5ad4ddad720c15b00db4ba264e773ab17","observation_id":"d562ddec-c324-4a5b-9d17-fba6a41466e1","resolution":{"observed_at":"2026-05-24T08:06:04.158387Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Pytorch fsdp: Experiences on scaling fully sharded data parallel","venue":null,"work_id":"62f689c7-6c80-4b9e-bd6f-d02b79814329","year":2023},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:42fc2fcfc6ffbd50ca97008e54322f24ba736dd1299d6765d5c316a2ef019a8d","observation_id":"ee0010ba-1927-4b27-852d-5da38f47acf3","resolution":{"observed_at":"2026-05-24T08:06:04.191642Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"d051d6aa-efca-49eb-a66d-8ea01bf21294","year":null},"citing_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-05-24T08:05:33.251722Z"},"links":{"citing_paper":"/paper/2308.03303"},"observation_digest":"sha256:ff991d4fc2ee0ef0c07248357a8c677398b095b2bcac77cf958797bfbe0ba457","observation_id":"ca963b53-725b-4cb2-8b79-8b25cbcec6bf","resolution":{"observed_at":"2026-05-24T08:06:04.199196Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-08T14:14:26.000056Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning"},"reference_resolution":{"displayed":68,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":9,"verified_exact":11,"verified_fuzzy":47},"total_outbound_references":68},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 68 of 68 outbound references and 47 inbound Pith citation observations for arXiv:2308.03303."}