{"as_of":"2026-08-09T13:09:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:64d28d8f62179d2dd6c00d9eb19029ad5817a4bc1a95042ec2974e9e3e53fb00","coverage":[{"denominator":64,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":64,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T23:22:20.741949Z","state":"measured"},{"denominator":64,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":64,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2502.08905/citation-record","integrity":"/paper/2502.08905/integrity","json":"/paper/2502.08905/citation-record.json","paper":"/paper/2502.08905"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:22:21.277220Z","title":"Dtllm-vlt: Diverse text generation for visual language tracking based on llm,","venue":null,"work_id":"0a89fa7b-9d76-4aa8-bb3b-d5a4705cc782","year":2024},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.478822Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:c5d20045014bdba1b32961a13a1aa92df0250a0da45cbabdb67322eb6a071d21","observation_id":"156914e9-0875-4a1f-b661-2b34e636fb97","resolution":{"observed_at":"2026-08-07T23:22:21.280687Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:21.267767Z","title":"Layoutllm-t2i: Eliciting layout guidance from llm for text-to-image generation,","venue":null,"work_id":"666232b4-7586-444c-9038-c210f352a294","year":2023},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.484328Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:948d85cb884cca12e4fe14c1461e0666b94aa9622a575690c5ff860ad7c64a1d","observation_id":"07b8d3a0-13f9-4825-9d30-fff4ee4bb992","resolution":{"observed_at":"2026-08-07T23:22:21.271014Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:21.258851Z","title":"Contrastive prefer- ence optimization: Pushing the boundaries of llm performance in machine translation,","venue":null,"work_id":"a06daeb6-b56d-4995-b7e1-931c86ab998b","year":2024},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.487887Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:e7e09d632c939159378f3e317adb3cb84a3b790703844a462658e9b46d4ec8c3","observation_id":"6b3fbfb2-c287-4b3a-8136-2091caab10b7","resolution":{"observed_at":"2026-08-07T23:22:21.262003Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:21.249668Z","title":"Designing heterogeneous llm agents for financial sentiment analysis,","venue":null,"work_id":"eb281613-314f-4541-b14f-d78c2150b1bf","year":2024},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.491362Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:64ade695065d385900fbdf3c0813717d4795db6299445d13cbbd03dfde0d5a34","observation_id":"6c29e67a-01b0-49dd-baaf-a650e8db2e2d","resolution":{"observed_at":"2026-08-07T23:22:21.253147Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:21.241013Z","title":"Toolqa: A dataset for llm question answering with external tools,","venue":null,"work_id":"91512a79-10e6-494b-bd11-f5cc835497bf","year":2023},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.494498Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:2a9cab188b4e6afb38e05be1b2a89c87fad407eb7116b702facc18cec2e3360c","observation_id":"345ba1ab-49d3-4239-96c6-724d1a968c86","resolution":{"observed_at":"2026-08-07T23:22:21.244011Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:21.232858Z","title":"P-tuning: Prompt tuning can be comparable to fine-tuning across scales and tasks,","venue":null,"work_id":"9c03e23b-a776-474b-9e07-0f17b5e0ba7e","year":2022},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.497574Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:898a942a5e731ea0b93891e5a146a6ca8c9909c46f8b63e403e29fccf108ec14","observation_id":"313bd9b9-3393-48a1-b5e6-11a84bc6bf22","resolution":{"observed_at":"2026-08-07T23:22:21.235709Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:22:20.500828Z","title":"The power of scale for parameter-efficient prompt tuning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.500828Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:e224ea3c87dcd67116c307ee8e65125bb59a565cafcf61dda82f4c7bb1a1d8a9","observation_id":"c093b9bd-c325-48b0-ae7a-760f2d94eee0","resolution":{"observed_at":"2026-08-07T23:22:20.500828Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:22:21.220191Z","title":"Parameter-efficient transfer learning with diff pruning,","venue":null,"work_id":"da56eba6-29b8-49f6-a78f-30935a6ffc27","year":2021},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.503798Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:9b810bf824a46c6b87acf9fc539b1e119c7d03d7f6e96eeccb596c948030e6ff","observation_id":"a90539e0-0cf1-42b3-87bb-aa4d33a18375","resolution":{"observed_at":"2026-08-07T23:22:21.222698Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:21.212629Z","title":"LoRA: Low-rank adaptation of large language models,","venue":null,"work_id":"14e5f971-41ab-4e7c-ab66-0f00cb8ccb8e","year":2022},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.507017Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:47c067954461c7633a5cbd2aef7abf518622c4dd3a4c8e895340c5a45cbaa192","observation_id":"1530f6a0-8edb-4a1f-823b-48e691a8d4e1","resolution":{"observed_at":"2026-08-07T23:22:21.215221Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:21.205007Z","title":"Autolora: Automatically tuning matrix ranks in low-rank adaptation based on meta learning,","venue":null,"work_id":"7897b3ce-9c84-4230-b365-e2f3f66e8637","year":2024},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.509836Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:12bf1b424bdc04e794ce13a7d11bebc58c271aed704c9656261ccef533089507","observation_id":"d4ddf4e3-7d07-4b4a-80b8-9381cb9140aa","resolution":{"observed_at":"2026-08-07T23:22:21.207701Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:21.197763Z","title":"Adaptive budget allocation for parameter-efficient fine-tuning,","venue":null,"work_id":"d288d1e8-7950-4d56-9154-4eff0915717e","year":2023},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.512666Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:dc30c2eb45da816ad43c04c5641b19ea6b0ff58f5ac3ca113ef4f5f64001ed6d","observation_id":"528359a7-f464-4943-8b99-d6f6ccd1e8fc","resolution":{"observed_at":"2026-08-07T23:22:21.200276Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:21.190435Z","title":"Alora: Allocating low-rank adaptation for fine-tuning large language models,","venue":null,"work_id":"050bce3f-520c-4596-bf4e-c086ba3604eb","year":2024},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.515761Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:a1a276bfb666eca243f24464ca663451291c643b46a66d0b548f22597a82ab2d","observation_id":"f60bc43d-b76c-44fa-915c-c46f230ce661","resolution":{"observed_at":"2026-08-07T23:22:21.193093Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.17357","last_updated":"2024-06-26T14:41:33Z","snapshot_observed_at":"2026-07-06T18:20:44.070255Z","submitted_at":"2024-05-27T17:02:27Z","title":"DoRA: Enhancing Parameter-Efficient Fine-Tuning with Dynamic Rank Distribution","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.17357","snapshot_observed_at":"2026-08-07T23:22:20.518775Z","title":"Dora: Enhancing parameter-efficient fine-tuning with dynamic rank distribution,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.518775Z"},"links":{"cited_paper":"/paper/2405.17357","citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:eee92b4aea91cc0e1aad37dd220d04a9522833da635f2d970b4f02e68eeb560b","observation_id":"cb97b640-3f7e-4d4e-8995-cf21e2fcac97","resolution":{"observed_at":"2026-08-07T23:22:20.518775Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.07721","last_updated":"2024-06-18T15:13:12Z","snapshot_observed_at":"2026-08-02T02:46:52.569687Z","submitted_at":"2024-02-12T15:34:56Z","title":"LoRA-drop: Efficient LoRA Parameter Pruning based on Output Evaluation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.07721","snapshot_observed_at":"2026-08-07T23:22:20.522370Z","title":"Lora-drop: Efficient lora parameter pruning based on output evaluation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.522370Z"},"links":{"cited_paper":"/paper/2402.07721","citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:675f5b609f0cfd9414c250b5e4d66350c0f4351a1bd9d16bca831ec0fd1d83af","observation_id":"6e110f34-5562-4b07-bc7c-60e1f2167ae3","resolution":{"observed_at":"2026-08-07T23:22:20.522370Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:22:21.182591Z","title":"Unveiling lora intrinsic ranks via salience analysis,","venue":null,"work_id":"66fd1634-6750-4c46-a472-77fcdd794ac4","year":2024},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.525560Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:d82831c03467e4be7a70c93bbdde471a22a6a7eabe82eae14e91f89316e6e551","observation_id":"7cd543ea-000a-42f8-bde7-325810eacfea","resolution":{"observed_at":"2026-08-07T23:22:21.185590Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:21.174225Z","title":"GLUE: A multi-task benchmark and analysis platform for natural language understanding,","venue":null,"work_id":"57e793c1-182a-4cfe-abd8-cbacb353cd36","year":2019},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.528611Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:dd4c6cd3381b971cc0742232880864dd0f6a39cc8e3f451d8c481336cfc03809","observation_id":"0dbb49a7-8355-4ff2-a2c4-1908b4a96ef7","resolution":{"observed_at":"2026-08-07T23:22:21.177320Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:21.165599Z","title":"Efficient parametrization of multi-domain deep neural networks,","venue":null,"work_id":"37a54eda-b00a-47f2-afd4-e3596d673cf1","year":2018},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.531356Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:42ca1d31d38f957939d7677142e699f52c7c470da42eaa2a8a98bec0a57c7381","observation_id":"da6d89b5-cf11-4f39-b2eb-03c5215de3bd","resolution":{"observed_at":"2026-08-07T23:22:21.169031Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:21.157090Z","title":"Velora: Memory efficient training using rank-1 sub-token projections,","venue":null,"work_id":"0217138f-c21c-469e-9007-4c5735c04e56","year":2024},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.534402Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:d8ae7e544e3bfcb42275bc80238a37fd682bdfee16bd10f261dc9c611f3832a9","observation_id":"07c532fd-fae1-4a99-8134-3e8fc7341a66","resolution":{"observed_at":"2026-08-07T23:22:21.160273Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:21.148942Z","title":"Hifi: High-information attention heads hold for parameter-efficient model adaptation,","venue":null,"work_id":"634ff75a-54d6-4504-b8a4-2aa4a8717e05","year":2023},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.537231Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:fafd526801fea5419ec00b0fd59e021b767dff8e825a32dc948dc84ff8847c71","observation_id":"8e903b95-d8d8-4f35-8db7-45fc0cfa28d4","resolution":{"observed_at":"2026-08-07T23:22:21.151976Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:21.140671Z","title":"Bitfit: Simple parameter-efficient fine-tuning for transformer- based masked language-models,","venue":null,"work_id":"730c7de3-6425-4f82-9e7e-679ee2fd3428","year":2022},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.540191Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:163fce165c0c8befa8c8c3709ae38778e3e41867e63efd6fc89222986126c70e","observation_id":"fd2120ea-e1b8-4715-9a11-f4447c58949e","resolution":{"observed_at":"2026-08-07T23:22:21.143575Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1911.03090","last_updated":"2019-11-08T07:05:20Z","snapshot_observed_at":"2026-07-06T08:35:28.740170Z","submitted_at":"2019-11-08T07:05:20Z","title":"What Would Elsa Do? Freezing Layers During Transformer Fine-Tuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.03090","snapshot_observed_at":"2026-08-07T23:22:20.543117Z","title":"What would elsa do? freezing layers during transformer fine-tuning,","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.543117Z"},"links":{"cited_paper":"/paper/1911.03090","citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:ad03e0520e9783ae73683839c86558235568d8a0a85edbd8be1d14b80cb03b5a","observation_id":"4e5bda04-9ed4-4bdb-a057-09ae1b3682f0","resolution":{"observed_at":"2026-08-07T23:22:20.543117Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:22:21.132017Z","title":"VeRA: Vector-based random matrix adaptation,","venue":null,"work_id":"c420cafb-588e-4b0b-a2cf-1a0d486abcdd","year":2024},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.545841Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:b2af1ab3c51848c1a4b0cc2e823b9770b568be656c70fad02a14270fdf2da4ba","observation_id":"ac3e3331-17ec-4e35-94c5-52199248e275","resolution":{"observed_at":"2026-08-07T23:22:21.135141Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:21.123237Z","title":"LoRA+: Efficient low rank adaptation of large models,","venue":null,"work_id":"815f6660-43ef-441e-a3d1-87ed51524534","year":2024},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.548229Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:81ebed70dd0550296d6dd46388688a01bf30e556b74dcd55c0cd660f1fa6a7df","observation_id":"9237c61f-3f78-46e5-9ffa-612e79581e0e","resolution":{"observed_at":"2026-08-07T23:22:21.126500Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:21.114905Z","title":"DoRA: Weight-decomposed low-rank adaptation,","venue":null,"work_id":"950bf177-181f-4494-b513-446876831892","year":2024},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.550841Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:980f575cb3bc64169a2d55c66823c5d1e707d2092dcf7da458965b54f47be980","observation_id":"4a76f080-a544-4e7b-82ae-3c25df6ed50f","resolution":{"observed_at":"2026-08-07T23:22:21.117568Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:21.107032Z","title":"Qlora: Efficient finetuning of quantized llms,","venue":null,"work_id":"0e7e55cc-42b9-43c4-a57f-4618c25bd056","year":2024},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.553421Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:63b217dcb08bdd8446c1ea7736868306585b6c43a2cf2591f4d1a8e706b055e4","observation_id":"cec22598-bb7b-4f5b-9ed1-d482b5c15c0b","resolution":{"observed_at":"2026-08-07T23:22:21.109804Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:21.098614Z","title":"Tied-lora: Enhancing parameter efficiency of lora with weight tying,","venue":null,"work_id":"1d144532-acc2-47b4-b6d3-b9f6c1bb29b2","year":2024},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.555687Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:b9b832e22f875bb7eb3001713a5ddab7002f1e41eff3f8f432aab45683d87ed5","observation_id":"577d88d8-f4c6-46c6-b4ab-ec6f386af1b0","resolution":{"observed_at":"2026-08-07T23:22:21.101685Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:21.090328Z","title":"Lora+: Efficient low rank adaptation of large models,","venue":null,"work_id":"2024ae50-3973-4a5a-afa1-2547a46dbe6f","year":2024},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.557921Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:4ac508c919882278bf1e76a4c2ecffc5d207e68bb6417cae5294c5469435a484","observation_id":"254ac9b7-a447-4767-b19a-70158068e712","resolution":{"observed_at":"2026-08-07T23:22:21.093072Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:21.082406Z","title":"LoRA-pro: Are low-rank adapters properly optimized?","venue":null,"work_id":"872b43f5-dbbb-4faf-92f3-dab4820e191d","year":2025},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.560485Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:93162369b2670f82a95db7e149bc153ed324d3d4bbfd7e30170504907203cf04","observation_id":"114a2b6c-2305-4ba0-a18f-be93885a6f2b","resolution":{"observed_at":"2026-08-07T23:22:21.085081Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:21.074382Z","title":"Hydralora: An asymmetric lora architecture for efficient fine-tuning,","venue":null,"work_id":"df3c734f-4f42-41bc-98a2-38c5ebac54c9","year":2024},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.562941Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:e435583dbc36e8e7fe3476d8c43a2f40d9cea94e3c4d1178f45374fff6d53660","observation_id":"f1f867d2-76bd-4a84-993e-6bb42b449032","resolution":{"observed_at":"2026-08-07T23:22:21.077103Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:21.066131Z","title":"Sparse low-rank adaptation of pre-trained language models,","venue":null,"work_id":"9992fcdb-7d99-45af-8ed6-115d701d87f5","year":2023},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.565379Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:06706b7be5a07ed1fcd5628a25ee160292180529aa0db5bfbc532e194fa2d48d","observation_id":"f0fca4b5-255a-44eb-b3ab-d917ae877c9a","resolution":{"observed_at":"2026-08-07T23:22:21.069202Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:21.057545Z","title":"Gradient descent provably optimizes over-parameterized neural networks,","venue":null,"work_id":"fdd46221-45ef-4c13-b238-cb9818406199","year":2019},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.567917Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:a4325c616ea21ef9c740fc0f3f280bf00216a256ec6defbea145013a872723a3","observation_id":"053e2748-19e1-4562-98af-8d689db1f614","resolution":{"observed_at":"2026-08-07T23:22:21.060782Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:22:20.570583Z","title":"Visualizing the loss landscape of neural nets,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.570583Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:0ae3bf65ac19cc48ee305ef73dd351bf671f7246b6c8a5ea999f7382cb0ebaca","observation_id":"4bb6158b-e3eb-4dc6-9836-c29a00652103","resolution":{"observed_at":"2026-08-07T23:22:20.570583Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:22:21.043795Z","title":"Meco: zero-shot nas with one data and single forward pass via minimum eigenvalue of correlation,","venue":null,"work_id":"d7d88781-3417-4716-9372-1e7d504647fc","year":2024},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.573063Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:b13ebdf5f480c6c8aed10851f5fff9da6aa730fd99ee9936868f2163f5a14838","observation_id":"10fb0e32-78d2-467f-965a-f3749589e2e6","resolution":{"observed_at":"2026-08-07T23:22:21.047116Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:22:20.575357Z","title":null,"venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.575357Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:44734b7a8fca5b279d203f0cc3fcc3ddcecc8d4de6d2b328fd90c678b62b4379","observation_id":"9181c037-48c7-4bee-9a86-649d6d2d6509","resolution":{"observed_at":"2026-08-07T23:22:20.575357Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:22:21.029431Z","title":"Generalization bounds of stochastic gradient descent for wide and deep neural networks,","venue":null,"work_id":"e9b91bde-565c-4c32-96d6-e15145bbfa3a","year":2019},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.577746Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:3ce248c047d28f5ffdf5cfd8117a1dab6d5c4801a20fd61a0270e0801a6946fe","observation_id":"520853a7-e6e5-4b15-82a9-41ec1dfbc421","resolution":{"observed_at":"2026-08-07T23:22:21.032705Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:21.020129Z","title":"Generalization properties of nas under activation and skip connection search,","venue":null,"work_id":"d21850d7-7d6f-4edd-8dbf-647a65033d79","year":2022},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.580290Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:4ce18b7882aa029db7f03f0b02ecc0a1a408e8fc5ae83e92989748ed3eec72bd","observation_id":"6f40befa-3e4a-44e0-af8c-68f17b509cf4","resolution":{"observed_at":"2026-08-07T23:22:21.023626Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:21.010368Z","title":"DeBERTav3: Improving deBERTa using ELECTRA-style pre-training with gradient-disentangled embedding sharing,","venue":null,"work_id":"b4671706-23d8-404e-a81d-a4ae8ea9556a","year":2023},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.582565Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:046b3371d13ba39d8a90620fe9a05b27c49d62bd247552c674e4b46744d9cdb9","observation_id":"080bc6aa-f9b6-4507-8730-2f1a03d25a76","resolution":{"observed_at":"2026-08-07T23:22:21.013578Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:21.001233Z","title":"GLUE: A multi-task benchmark and analysis platform for natural language understanding,","venue":null,"work_id":"d76fac32-c9e4-40ff-853b-1f4dbcf0993b","year":2018},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.584919Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:a59b04da67accd6f1d8b890c448cdc43eeaa2a9c5568b13693f9dbd28eb4bbaf","observation_id":"6bd1a59f-f17c-4269-b1a0-6db4cdae15f6","resolution":{"observed_at":"2026-08-07T23:22:21.004605Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:20.992198Z","title":"SQuAD: 100,000+ questions for machine comprehension of text,","venue":null,"work_id":"04df4348-58ea-4bf0-a5e9-50890a4b2bb2","year":2016},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.587195Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:604742e4f6abc4058db6663ac8ae065097a56c257714d566563999f5f9a4cb4f","observation_id":"1647e718-579b-44f4-a6ad-6db063ead0c6","resolution":{"observed_at":"2026-08-07T23:22:20.995590Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:20.982847Z","title":"Know what you don’t know: Unanswerable questions for SQuAD,","venue":null,"work_id":"6ffe827b-c839-4c78-826b-be8eead58344","year":2018},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.589789Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:2873fc6ce3277899f28f6c7f37a06133a778740ffae22e105add6becee185498","observation_id":"0b63be53-6c84-4277-b5e4-641fc40efaa7","resolution":{"observed_at":"2026-08-07T23:22:20.986174Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-07-06T18:55:11.576666Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-07T23:22:20.592640Z","title":"The llama 3 herd of models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.592640Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:a6f08315cc12315a1527fa2b080467f21a7caff673265ed9a6b6645ddb0b8be7","observation_id":"979ad495-1e65-4ea5-be0b-6a0304004ae4","resolution":{"observed_at":"2026-08-07T23:22:20.592640Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09288","last_updated":"2023-07-19T17:08:59Z","snapshot_observed_at":"2026-08-07T12:56:43.323460Z","submitted_at":"2023-07-18T14:31:57Z","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.09288","snapshot_observed_at":"2026-08-07T23:22:20.595794Z","title":"Llama 2: Open foundation and fine-tuned chat models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.595794Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:cf701bf6f4f2ff591dfafd94102ec4f1f4290bd6f196de0ae6bb44853add425c","observation_id":"8aa3c1db-8218-4bb4-9d66-18c33b7cf9d2","resolution":{"observed_at":"2026-08-07T23:22:20.595794Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1907.11692","last_updated":"2019-07-26T17:48:29Z","snapshot_observed_at":"2026-07-31T22:31:37.910868Z","submitted_at":"2019-07-26T17:48:29Z","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.11692","snapshot_observed_at":"2026-08-07T23:22:20.598963Z","title":"Roberta: A robustly optimized bert pretraining approach,","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.598963Z"},"links":{"cited_paper":"/paper/1907.11692","citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:342348baaea5ecf4605487027e61e8230775d206dcad2461d931624b4b96784a","observation_id":"e46c3201-d875-472c-b862-927997b779d5","resolution":{"observed_at":"2026-08-07T23:22:20.598963Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:22:20.974319Z","title":"Magnus and H","venue":null,"work_id":"22621a23-c0b4-4549-a639-52f0bd781333","year":1999},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.602506Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:fb7a5c04103ceb41f45fa5e2a5881093d7b21f70cac9fec9e7401612646e14c4","observation_id":"d6f5cf2e-fb0a-40ac-a31b-03946e616a48","resolution":{"observed_at":"2026-08-07T23:22:20.977087Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:22:20.605297Z","title":null,"venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.605297Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:d0ab9be55d122b1a9f61209a145118dd8d740cb2565678f7c5cae15e56b3c865","observation_id":"a087289f-35a4-4850-8180-8758eda8cab7","resolution":{"observed_at":"2026-08-07T23:22:20.605297Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:22:20.608084Z","title":"Parameter-efficient transfer learning for nlp,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.608084Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:d3db4a6ab621099e5a2ba13007d01209968ae26a6c9d13266d35e9a84d30be7c","observation_id":"6016e1fe-1ddb-426c-bf66-3a628c417a7b","resolution":{"observed_at":"2026-08-07T23:22:20.608084Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T23:22:20.955937Z","title":"Adapterfusion: Non-destructive task composition for transfer learning,","venue":null,"work_id":"f70df30a-b9c4-49e3-a45e-3917c131b40c","year":2021},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.610938Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:9385ae669671b65065a8296f5c19fde33dc9f40accec4602e67e86bed025e11e","observation_id":"ced63b0d-d566-4804-8710-5eef14af44bb","resolution":{"observed_at":"2026-08-07T23:22:20.958798Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:20.948130Z","title":"(vii) LoRA+ [27] employs different learning rates to update the low-rank matrices","venue":null,"work_id":"17a96d7e-a25e-4c87-9ff0-e1e932873e18","year":null},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.614188Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:18512a3c9e218464f1ce5da7ebaf98bef3a8482bf2241f97a04c3387005e7550","observation_id":"330972af-c10f-428f-8ba0-43810babcf15","resolution":{"observed_at":"2026-08-07T23:22:20.950846Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:20.940492Z","title":"Guidelines: • The answer NA means that the abstract and introduction do not include the claims made in the paper","venue":null,"work_id":"a4d26a75-4f5d-4ad2-872d-855ef292002c","year":null},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.617652Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:27a1c967f63a5cecb700505b4171c1d3bfd64a2080e4fedaa4e5a501049d472a","observation_id":"317b0b82-7ff3-407c-b8a8-eaa542980a97","resolution":{"observed_at":"2026-08-07T23:22:20.943300Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:20.933383Z","title":"Limitations","venue":null,"work_id":"4cc68559-d661-430c-bfe1-c911ab1b3938","year":null},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.620668Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:ca104d2bb3dd40a66ac979af15adc2ab8f2bd87d3fce3744bc84a071673b8895","observation_id":"63ff2f14-3d0d-4045-a338-f0caa06613bb","resolution":{"observed_at":"2026-08-07T23:22:20.935745Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:20.925992Z","title":"Guidelines: • The answer NA means that the paper does not include theoretical results","venue":null,"work_id":"437b3cd9-89f3-4dc5-b37c-0dd3f8d7bd5c","year":null},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.623746Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:c6477d72c85cf8f6c96e56d08e0de6b31ec80b3e23e30c7c4008cde2d90142ac","observation_id":"7e7417d2-a811-4b0e-8e78-4af49850f0e3","resolution":{"observed_at":"2026-08-07T23:22:20.928575Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:20.918562Z","title":"Guidelines: • The answer NA means that the paper does not include experiments","venue":null,"work_id":"c826b9c0-98a7-46ce-a6a7-4883954b77b3","year":null},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.627247Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:fc72f1e3756674502b2330d15a400a69720471e2cf21144c11820b522cb5a9a9","observation_id":"5e53a778-8094-4001-9c94-30bbde956e13","resolution":{"observed_at":"2026-08-07T23:22:20.921263Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:20.911065Z","title":"All the datasets we used are public","venue":null,"work_id":"a6a5344e-f7d9-4c8a-bc7e-fafa79686ee3","year":null},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.630488Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:e0a2ded9f3780da722326df7a5b71f06d99f91c4274b225c60eeb85dcdf18359","observation_id":"e465f94a-3f96-46e0-8801-e1524d9b9f25","resolution":{"observed_at":"2026-08-07T23:22:20.913776Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:20.902391Z","title":"For additional experimental settings on various benchmarks, we provided the details in Appendix D","venue":null,"work_id":"a56c229e-49d7-454c-973e-cf949e972bab","year":null},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.634044Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:ba1e1e9d7eacc2eeea3f4a63bed10e22d0d35c02a38071c644c486563a1ef3d0","observation_id":"795902c1-0969-48fb-9718-27833f040db0","resolution":{"observed_at":"2026-08-07T23:22:20.905746Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:20.893383Z","title":"We have run our experiments multiple times with different seeds and provided the mean and standard deviation values in Section 5","venue":null,"work_id":"336fed96-f2e1-4545-abbc-a4addceb39f5","year":null},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.636925Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:bf3c6da14306fb1d30b1de3b91f34f32233ec93e6249a7a1aeac2461b25cd54b","observation_id":"4130467a-18b2-4dd4-b945-f879bdd14d96","resolution":{"observed_at":"2026-08-07T23:22:20.896773Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:20.884042Z","title":"Guidelines: • The answer NA means that the paper does not include experiments","venue":null,"work_id":"5b5a9742-4b8c-4639-82f8-3287d57426ee","year":null},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.639484Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:9c1388379adef001952e9bf6fca700cafd035d35dcbec6834f3ad8219e9c9f9d","observation_id":"62148de5-31bd-4745-8cee-528b8d32e83a","resolution":{"observed_at":"2026-08-07T23:22:20.887280Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:20.875316Z","title":"Guidelines: • The answer NA means that the authors have not reviewed the NeurIPS Code of Ethics","venue":null,"work_id":"2b7ed1bd-36ac-430f-92b5-3708c10c17e4","year":null},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.642091Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:f9b8c4911f493d4f3f48f90f30d1b082252f212c08638bc2dddf2f7c63dc11c8","observation_id":"486e6e0b-819d-4484-9e05-c2da5beee003","resolution":{"observed_at":"2026-08-07T23:22:20.878372Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:20.866285Z","title":"Guidelines: • The answer NA means that there is no societal impact of the work performed","venue":null,"work_id":"ebfdaf9e-1778-4213-ab4a-1880fd19afb5","year":null},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.644431Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:c1207c0a14ae06b85e6b190633dfcc8d4a11cd6550264d488f78f58251772a3a","observation_id":"ec0e2f8d-c2ad-4590-89cf-271b04a3a04c","resolution":{"observed_at":"2026-08-07T23:22:20.869739Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:20.856722Z","title":"Guidelines: • The answer NA means that the paper poses no such risks","venue":null,"work_id":"e1c64f78-d5e9-4e53-a0a4-8e4e776cc409","year":null},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.647000Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:b24d9be2598725febd91cf68ff2a561dee0c1436d9c297f7c412482f20704740","observation_id":"6e885e51-4b6d-4fdb-ab4a-db9212839b9e","resolution":{"observed_at":"2026-08-07T23:22:20.860142Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:20.847151Z","title":"We have properly cited these resources in our paper","venue":null,"work_id":"ef5853c2-ace8-44fa-8884-0f8e58b0a062","year":null},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.730546Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:450269ec0ac5f071a6835971dd6f1ae22ea2b9578d2fba809e3f2644a06e719a","observation_id":"f48657ea-6c94-4feb-8943-0b2275d8a2df","resolution":{"observed_at":"2026-08-07T23:22:20.850484Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:20.837736Z","title":"Guidelines: • The answer NA means that the paper does not release new assets","venue":null,"work_id":"bc49815b-bf18-4990-a262-2e6d540bb706","year":null},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.733707Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:f9c107128f788140bbbe1d13f64864ffcd01bdcf3afb81048b8b0b1e870786c0","observation_id":"7ebbf6da-f897-4ccc-93e8-522af3ade967","resolution":{"observed_at":"2026-08-07T23:22:20.841199Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:20.829420Z","title":"Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects","venue":null,"work_id":"69960af4-0a81-4d6c-8fcf-b73ac92f4269","year":null},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.736513Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:2224f8343f1b501d9892da9356c7d0f225a7d19352a5477e178a9bf83d09171f","observation_id":"22c03add-6f7f-4cc3-8f90-2d1945eb44b3","resolution":{"observed_at":"2026-08-07T23:22:20.832249Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:20.820980Z","title":"Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects","venue":null,"work_id":"89a38489-b38f-4ae5-b6f4-d5dd0205510e","year":null},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.739334Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:620e212c0155f5bd2fa2974fd98c5cfbebff5db1342316abd3ed2b40beec4931","observation_id":"f95ab010-44fc-4c54-a638-f564dfdfc86a","resolution":{"observed_at":"2026-08-07T23:22:20.823863Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T23:22:20.809402Z","title":"Answer: [NA] Justification: We utilize LLM only for grammar and formatting purposes","venue":null,"work_id":"2e334f7f-cdaa-45a6-bd11-41901f4c93b0","year":2025},"citing_paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-07T23:22:20.741949Z"},"links":{"citing_paper":"/paper/2502.08905"},"observation_digest":"sha256:269ff48774bdff1ce50c236aa92d86a902d592699f8c8e4e9db25a4befe5c4ab","observation_id":"d1f7ad08-7e5a-4870-8964-f4cbdd9dfc4f","resolution":{"observed_at":"2026-08-07T23:22:20.813831Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2502.08905","last_updated":"2025-06-04T07:14:31Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T23:14:02.644714Z","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection"},"reference_resolution":{"displayed":64,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":11,"verified_exact":0,"verified_fuzzy":53},"total_outbound_references":64},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 64 of 64 outbound references and 0 inbound Pith citation observations for arXiv:2502.08905."}