{"as_of":"2026-08-09T05:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f0e46e4431c81055128d3156a2dcfd03374bfd72c71fc4e65d23fc1a88dd9442","coverage":[{"denominator":60,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":60,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T10:26:45.549571Z","state":"measured"},{"denominator":60,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":60,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2502.08141/citation-record","integrity":"/paper/2502.08141/integrity","json":"/paper/2502.08141/citation-record.json","paper":"/paper/2502.08141"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2112.00861","last_updated":"2021-12-09T21:40:22Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2021-12-01T22:24:34Z","title":"A General Language Assistant as a Laboratory for Alignment","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.00861","snapshot_observed_at":"2026-08-08T10:26:45.397594Z","title":"A general language assistant as a laboratory for alignment","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.397594Z"},"links":{"cited_paper":"/paper/2112.00861","citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:77f60b12dad85da37d0d017803dd7aaf15dfa23d75f4f49d6feebf6f5d9572ad","observation_id":"d6990451-723b-4d06-a0f9-d9db7e3b5f15","resolution":{"observed_at":"2026-08-08T10:26:45.397594Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.15701","last_updated":"2021-07-22T13:13:45Z","snapshot_observed_at":"2026-08-09T02:05:22.710890Z","submitted_at":"2020-12-31T16:34:54Z","title":"BinaryBERT: Pushing the Limit of BERT Quantization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.15701","snapshot_observed_at":"2026-08-08T10:26:45.401487Z","title":"Binarybert: Pushing the limit of bert quantization","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.401487Z"},"links":{"cited_paper":"/paper/2012.15701","citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:c341f56ecb4a531cc094ea3405ba8afc2b23a5c931bc00827f7aff510aa44a18","observation_id":"9abab17f-77bd-4d0e-a91c-861f6ccbcf46","resolution":{"observed_at":"2026-08-08T10:26:45.401487Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.05862","snapshot_observed_at":"2026-08-08T10:26:45.404631Z","title":"Training a helpful and harmless assistant with reinforcement learning from human feedback","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.404631Z"},"links":{"cited_paper":"/paper/2204.05862","citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:110d90ab915e3eaa5dfb5463a8c1a37f0ab7b0c7ec260f5d192ae65634ea4393","observation_id":"dd80d76c-b57a-4df6-908d-b13b849ee9a9","resolution":{"observed_at":"2026-08-08T10:26:45.404631Z","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":"2026-08-08T10:26:46.155241Z","title":"Flexquant: Elastic quantization framework for locally hosted llm on edge devices, 2025","venue":null,"work_id":"6b2ebbc2-8104-45a1-857c-ffdda324a255","year":2025},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.407671Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:61bdaec643d6632fee02037b3e2bea6469ef95f05c340fb46b16353c9439b99c","observation_id":"4e36b23a-237b-4cf4-9205-d3beb6d7f372","resolution":{"observed_at":"2026-08-08T10:26:46.157981Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T10:26:46.147920Z","title":"Punica: Multi-tenant lora serving","venue":null,"work_id":"304bffc9-1eb8-4c44-a14b-e885e17fbfad","year":2024},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.410378Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:13f84546674e026fabecd03c5d48070eee236254a7c9fe7235f2267baa109ecd","observation_id":"23f88b5c-ff22-461d-a4c9-da189fa6a9f4","resolution":{"observed_at":"2026-08-08T10:26:46.150700Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T10:26:46.140732Z","title":"Tesla P100 GPU Accelerator","venue":null,"work_id":"17375df6-7b87-4a2b-86d2-2cb739f76302","year":2016},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.413348Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:634303d81314c76e803ee647d08588e9b137a2057398822924531bdec7e162ee","observation_id":"c7c7cffb-e576-4097-960d-4348e178a6a3","resolution":{"observed_at":"2026-08-08T10:26:46.143526Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T10:26:46.133568Z","title":"Tesla V100 GPU Accelerator Datasheet","venue":null,"work_id":"f7f7b1f4-d910-4444-9f14-49f8943b7ed1","year":null},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.416175Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:66e0cd5fc2893d3059552d626642d5e41b780f02a6aed97e3ae7db41ae0c76ab","observation_id":"73b673c1-a8e4-423a-af09-ff75019a2336","resolution":{"observed_at":"2026-08-08T10:26:46.136136Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T10:26:46.118903Z","title":"NVIDIA T4 Virtualization Datasheet","venue":null,"work_id":"030a39e5-ef88-4af7-b176-ec826af87a48","year":2021},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.421123Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:f0a0a6f7987707895adcd8afdef5b4014e39d0266f9ffe748677c17d7c9225d5","observation_id":"31bebd33-6b8b-4123-8c26-e9ad8542eeb3","resolution":{"observed_at":"2026-08-08T10:26:46.121596Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T10:26:46.111953Z","title":"Qlora: Efficient finetuning of quantized llms","venue":null,"work_id":"bdaad53e-c5bf-4b79-9319-cc7694f7a10a","year":2024},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.423713Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:12555167bb4b54ee170b2e0a3c1257835a6ee8b810e9c85c8c164a85ca4088b4","observation_id":"abdc270d-ead1-417c-9388-c76def8d3b4b","resolution":{"observed_at":"2026-08-08T10:26:46.114308Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T10:26:45.426320Z","title":"The llama 3 herd of models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.426320Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:96d7d8991f3135fb3c399b187c54a6f83e18f11908b8c45ab8715f39cf43c960","observation_id":"7f50ccf5-f7dd-4b9e-b5e1-378bdbc3842a","resolution":{"observed_at":"2026-08-08T10:26:45.426320Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-08T10:26:45.429133Z","title":"Learned step size quantization","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.429133Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:519ce6a7e3f6f136c6b8625164b23d84fdd704e3c45ae0da816d94fa2579f93e","observation_id":"a684b590-357e-4f2b-823d-84224357e7ff","resolution":{"observed_at":"2026-08-08T10:26:45.429133Z","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":"2026-08-08T10:26:46.105779Z","title":"Raspberry Pi 4 Model B","venue":null,"work_id":"16670363-7ebd-4ee4-8c92-c9707248a92e","year":2019},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.432056Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:4ee161655419bd45436b022651961e87a47eda019decbbe5491f37d8c07f8a8b","observation_id":"319f8cc4-c076-4f97-8ef1-4eff675a06fd","resolution":{"observed_at":"2026-08-08T10:26:46.107892Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T10:26:46.099412Z","title":"Teaching machines to read and comprehend","venue":null,"work_id":"924c4804-6e24-435a-ade3-8629637e4abe","year":2015},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.434541Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:d48adf19221bc2f38be9df09b19404572691ba6fcc269d71718d9e3705a1bd77","observation_id":"eb18376b-748c-4542-9b11-6e01f3117408","resolution":{"observed_at":"2026-08-08T10:26:46.101710Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09685","last_updated":"2021-10-16T18:40:34Z","snapshot_observed_at":"2026-08-07T07:43:16.294957Z","submitted_at":"2021-06-17T17:37:18Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09685","snapshot_observed_at":"2026-08-08T10:26:45.437168Z","title":"Lora: Low-rank adaptation of large language models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.437168Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:112560d28af55bc05963b1eeaa6f3d9506b080c8cd44746c2eabe4a2d6074a6e","observation_id":"af8e7f52-34a9-4568-a7bc-dd60bb8b3467","resolution":{"observed_at":"2026-08-08T10:26:45.437168Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.11267","last_updated":"2024-06-17T07:16:07Z","snapshot_observed_at":"2026-08-07T22:55:07.093482Z","submitted_at":"2024-06-17T07:16:07Z","title":"Mitigating Large Language Model Hallucination with Faithful Finetuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.11267","snapshot_observed_at":"2026-08-08T10:26:45.439858Z","title":"Mitigating large language model hallucination with faithful finetuning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.439858Z"},"links":{"cited_paper":"/paper/2406.11267","citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:deb967c4872438f21ab1452dd4bd13b6e9f84c94380a9776130acf0b72761575","observation_id":"5098cfae-e73a-4342-93af-15739d74458a","resolution":{"observed_at":"2026-08-08T10:26:45.439858Z","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":"2026-08-08T10:26:45.442590Z","title":"Accurate post training quantization with small calibration sets","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.442590Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:0c0e709694b8f02f59f33228dd8a54b18fa0901b81fe2291e08a7c15b2a4b10e","observation_id":"61b82f9b-76ce-42c4-a723-d65fc4e5b694","resolution":{"observed_at":"2026-08-08T10:26:45.442590Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04902","last_updated":"2025-07-22T01:10:11Z","snapshot_observed_at":"2026-07-06T17:26:51.461337Z","submitted_at":"2024-02-07T14:35:05Z","title":"L4Q: Parameter Efficient Quantization-Aware Fine-Tuning on Large Language Models","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.04902","snapshot_observed_at":"2026-08-08T10:26:45.444990Z","title":"L4q: Parameter efficient quantization-aware training on large language models via lora-wise lsq","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.444990Z"},"links":{"cited_paper":"/paper/2402.04902","citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:a12537d24201b0dd32b154af28bd9320ac087be431576a12c16b4c253a319e6d","observation_id":"f3a392f7-95dc-4c83-b71e-024c83b9fa6a","resolution":{"observed_at":"2026-08-08T10:26:45.444990Z","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":"2026-08-08T10:26:46.088525Z","title":"The singular value decomposition: Its computation and some applications","venue":null,"work_id":"6772daab-51c4-4379-b2bf-cdf73c222f71","year":1980},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.447414Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:b5dda22fde176b0cd0bed60b47f7fe64983c46b311f3af23a007cc5c9b09d5da","observation_id":"79c5014d-cf73-4840-831c-58aed8a892a3","resolution":{"observed_at":"2026-08-08T10:26:46.091205Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T10:26:46.080857Z","title":"Openassistant conversations-democratizing large language model alignment","venue":null,"work_id":"7ed8edcf-034d-42c2-a4b5-9e7dfdc37dfa","year":2024},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.449811Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:f68eefe0bfbfd92276c37c7a4abd32ccaeb6aa28289539a98a0655b75e48653a","observation_id":"a5629304-6a57-46b4-b57d-bb4ac4e0f5b3","resolution":{"observed_at":"2026-08-08T10:26:46.083733Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.13461","last_updated":"2019-10-29T18:01:00Z","snapshot_observed_at":"2026-07-06T08:33:12.534026Z","submitted_at":"2019-10-29T18:01:00Z","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.13461","snapshot_observed_at":"2026-08-08T10:26:45.451835Z","title":"Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.451835Z"},"links":{"cited_paper":"/paper/1910.13461","citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:08f01abec288d8db2b2c786c143031eb6ddf255907192437e1a3fbed9ff9d0c7","observation_id":"6690ef9f-0803-4b8c-b84d-325a3b84a39b","resolution":{"observed_at":"2026-08-08T10:26:45.451835Z","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":"2026-08-08T10:26:46.073637Z","title":"BART-Large Model Card","venue":null,"work_id":"703acd06-e16c-460c-a229-29e0cae2264e","year":2023},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.454190Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:0b2f347a798400821c58827683c8e8d4f74dab8692c58f986e81563546fcb3f2","observation_id":"93bde81c-815e-46cb-8ca3-7af5041ab17c","resolution":{"observed_at":"2026-08-08T10:26:46.076193Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T10:26:45.456282Z","title":"Svdqunat: Absorbing outliers by low-rank components for 4-bit diffusion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.456282Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:bddfc8d9a80689f3220f286213edc4f560ed4fc816e28c6580259a30e4330bdc","observation_id":"0a836f6d-54f9-4d5c-a003-5edab1b8c0a3","resolution":{"observed_at":"2026-08-08T10:26:45.456282Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.08659","last_updated":"2023-11-28T16:06:59Z","snapshot_observed_at":"2026-07-06T16:32:11.601334Z","submitted_at":"2023-10-12T18:34:08Z","title":"LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.08659","snapshot_observed_at":"2026-08-08T10:26:45.458342Z","title":"Loftq: Lora-fine-tuning-aware quantization for large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.458342Z"},"links":{"cited_paper":"/paper/2310.08659","citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:f0488a333bbe1822efb433391cb2a56b81b142afc47fbba0d3f0eef45c2e9e0a","observation_id":"618795ae-8671-44ed-974f-c1d124e659d9","resolution":{"observed_at":"2026-08-08T10:26:45.458342Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.05147","last_updated":"2024-06-21T14:03:48Z","snapshot_observed_at":"2026-07-06T17:27:03.686119Z","submitted_at":"2024-02-07T09:36:54Z","title":"ApiQ: Finetuning of 2-Bit Quantized Large Language Model","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.05147","snapshot_observed_at":"2026-08-08T10:26:45.461175Z","title":"Apiq: Finetuning of 2-bit quantized large language model","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.461175Z"},"links":{"cited_paper":"/paper/2402.05147","citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:06dc1e37782b7eb35843e332c36a4198be7bdcbffda85efcb0653ca4cf6de0f1","observation_id":"d3ab3d55-0710-49e9-8b60-41d34adc59b3","resolution":{"observed_at":"2026-08-08T10:26:45.461175Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.19437","last_updated":"2025-02-18T17:26:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-27T04:03:16Z","title":"DeepSeek-V3 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.19437","snapshot_observed_at":"2026-08-08T10:26:45.463846Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.463846Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:4f0722b3fe8c9fa909b5bf36b017208a6017743eb6d9ffa67385d3e5548921b4","observation_id":"2786401a-3b35-43b9-adb6-26099075eb8a","resolution":{"observed_at":"2026-08-08T10:26:45.463846Z","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":"2026-08-08T10:26:46.066248Z","title":"Mitigating hallucination in large multi-modal models via robust instruction tuning","venue":null,"work_id":"1f844ca6-d2ae-4559-ac4f-e09ca62761a6","year":2023},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.466570Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:6f7fbcea6d6a71677394b5743558848b6d78358e72c548f433d6a906fad4c57b","observation_id":"4ad90552-c591-47fb-a926-9b624175e2f5","resolution":{"observed_at":"2026-08-08T10:26:46.069076Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T10:26:45.469184Z","title":"Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning","venue":null,"work_id":null,"year":1950},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.469184Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:bbb4b06d44da24251ffd56bded28870c15844e565acd3329d0f34541551af12f","observation_id":"b1b19805-8c90-476c-8ba4-79d95a1446d6","resolution":{"observed_at":"2026-08-08T10:26:45.469184Z","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":"2026-08-08T10:26:46.054983Z","title":"Nonuniform- to-uniform quantization: Towards accurate quantization via generalized straight-through estimation","venue":null,"work_id":"f1747809-be13-4aaf-bcab-69cdc9057f34","year":2022},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.471635Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:3588ed092fb6db49aac373fcc98c3207caa13fbf3a820123ba6c3b71a24d08da","observation_id":"bb152254-b936-4fb6-ac8a-9ec21308c61c","resolution":{"observed_at":"2026-08-08T10:26:46.057774Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T10:26:46.047814Z","title":"Least squares quantization in pcm","venue":null,"work_id":"81b527f7-c049-44de-b180-cacc60aa4978","year":1982},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.474051Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:1c6ceda131976b19db9c284d4c3a3e5dc93ec2ea086771315f5e9890b7b19468","observation_id":"27b7448e-6f32-43d3-b61e-8737223ede63","resolution":{"observed_at":"2026-08-08T10:26:46.050373Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.07577","last_updated":"2022-09-04T23:31:05Z","snapshot_observed_at":"2026-08-01T19:07:06.818808Z","submitted_at":"2021-10-14T17:40:08Z","title":"UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.07577","snapshot_observed_at":"2026-08-08T10:26:45.476583Z","title":"Unipelt: A unified framework for parameter-efficient language model tuning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.476583Z"},"links":{"cited_paper":"/paper/2110.07577","citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:bc03165905dafe38695733d603fbba69d27f758a26b54a109a7629ed7f2256db","observation_id":"4d2f4fbf-10c6-48e1-9e7d-02ed8692ae76","resolution":{"observed_at":"2026-08-08T10:26:45.476583Z","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":"2026-08-08T10:26:46.039673Z","title":"Quantizing for minimum distortion","venue":null,"work_id":"4f33681e-4319-4638-8ebb-931dd228a52e","year":1960},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.479240Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:aaf238b80f71bc408b7b8ec088466f872a323a491e63a1a6de52693e6f9aabca","observation_id":"0796e8a9-64ec-4727-8e7d-407af3185ddf","resolution":{"observed_at":"2026-08-08T10:26:46.042302Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.02948","last_updated":"2025-04-09T06:54:20Z","snapshot_observed_at":"2026-08-09T04:47:57.368711Z","submitted_at":"2024-04-03T15:06:43Z","title":"PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.02948","snapshot_observed_at":"2026-08-08T10:26:45.481730Z","title":"Pissa: Principal singular values and singular vectors adaptation of large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.481730Z"},"links":{"cited_paper":"/paper/2404.02948","citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:a5f8ad255f5757dd6fa9f4ff2077bd963650227de76b597bcfc4c5c2fc038520","observation_id":"ce1a28f6-cccc-48b0-a779-5da4c5c6e6f2","resolution":{"observed_at":"2026-08-08T10:26:45.481730Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1609.07843","last_updated":"2016-09-26T04:06:13Z","snapshot_observed_at":"2026-07-06T05:12:10.387914Z","submitted_at":"2016-09-26T04:06:13Z","title":"Pointer Sentinel Mixture Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.07843","snapshot_observed_at":"2026-08-08T10:26:45.484341Z","title":"Pointer sentinel mixture models","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.484341Z"},"links":{"cited_paper":"/paper/1609.07843","citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:29bfaab597e8460af89f6dadfd52f80ff06997b564d5964f15a7722a3d16f07d","observation_id":"2d682fcb-bc00-47ba-a256-0c4f9408fc74","resolution":{"observed_at":"2026-08-08T10:26:45.484341Z","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":"2026-08-08T10:26:45.487203Z","title":"Pulp: a linear programming toolkit for python","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.487203Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:8cb3b8eed25ea648083ef747adb0817ac4d936a0541161b1b7f8fdd9b1a5bc7e","observation_id":"3db9d43f-e4ae-44e5-8dcc-03b58c8e2cb5","resolution":{"observed_at":"2026-08-08T10:26:45.487203Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1808.08745","last_updated":"2018-08-27T09:08:18Z","snapshot_observed_at":"2026-07-06T06:57:36.335954Z","submitted_at":"2018-08-27T09:08:18Z","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1808.08745","snapshot_observed_at":"2026-08-08T10:26:45.489758Z","title":"Don’t give me the details, just the summary! topic-aware convolutional neural networks for extreme summarization","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.489758Z"},"links":{"cited_paper":"/paper/1808.08745","citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:fad33e612f7bdfacfe222927fb1db3351a32c1c4a79cf553f1419fcf4287a25b","observation_id":"f213ebf3-0a25-48d1-a453-9fd11e495be7","resolution":{"observed_at":"2026-08-08T10:26:45.489758Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.11157","last_updated":"2024-05-18T03:02:23Z","snapshot_observed_at":"2026-07-06T18:16:03.617132Z","submitted_at":"2024-05-18T03:02:23Z","title":"Towards Modular LLMs by Building and Reusing a Library of LoRAs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.11157","snapshot_observed_at":"2026-08-08T10:26:45.492458Z","title":"Towards modular llms by building and reusing a library of loras","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.492458Z"},"links":{"cited_paper":"/paper/2405.11157","citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:97922efe103733ab7bf1a3733ab18e463edffdfde105ae4b065d896ca27536eb","observation_id":"b7df3e0d-a8b4-4939-b669-b7335141063e","resolution":{"observed_at":"2026-08-08T10:26:45.492458Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.05445","last_updated":"2024-05-27T09:20:35Z","snapshot_observed_at":"2026-07-06T17:27:15.921312Z","submitted_at":"2024-02-08T06:53:31Z","title":"Accurate LoRA-Finetuning Quantization of LLMs via Information Retention","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.05445","snapshot_observed_at":"2026-08-08T10:26:45.495050Z","title":"Accurate lora-finetuning quantization of llms via information retention","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.495050Z"},"links":{"cited_paper":"/paper/2402.05445","citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:66337da665656fd963f84ff3a388e68d2c3d898d173613e5711b1ce30bbee61a","observation_id":"4b5db568-8ec7-4a57-89e1-3398c235b2fd","resolution":{"observed_at":"2026-08-08T10:26:45.495050Z","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":"2026-08-08T10:26:46.028221Z","title":"Coin-or: an open-source library for optimization","venue":null,"work_id":"c43689c2-420a-4082-a29d-570c7ca1315c","year":2002},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.497587Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:e358ff8f067cb78d2b2da55055cfd773cc984a55cdb3e561f9d594c5ffdeec63","observation_id":"3ea64354-6747-43a2-9ab4-73af997f142a","resolution":{"observed_at":"2026-08-08T10:26:46.030998Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T10:26:46.020532Z","title":"Not all bits have equal value: Heterogeneous precisions via trainable noise","venue":null,"work_id":"e028037c-acce-47ac-8cf0-57e885eda9f7","year":2022},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.499976Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:495805fb7a87f5d88bdd7e6069b4fe70990d976245c2bae8d3071d0768133dd6","observation_id":"fbb1305e-759d-432b-b8d3-1374f76f65c9","resolution":{"observed_at":"2026-08-08T10:26:46.023468Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T10:26:46.012955Z","title":"Q-bert: Hessian based ultra low precision quantization of bert","venue":null,"work_id":"524c2eb5-d864-4c34-9327-d5953bc5d34d","year":2020},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.502295Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:cb1ec6c02e2774123ce68a6bc79c93e3523bc1fc1a2ed76dbcd65193d004e2b8","observation_id":"365da2c4-5089-4932-b695-17c2d58df20f","resolution":{"observed_at":"2026-08-08T10:26:46.015677Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T10:26:46.005126Z","title":"Agile-quant: Activation-guided quantization for faster inference of llms on the edge, 2023","venue":null,"work_id":"62023783-b7cb-4ee5-8654-88e73f4461bf","year":2023},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.504770Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:b13bd3cffef425d9342a32a135b5c60a06668ba20614a669b150b20544d60888","observation_id":"12357522-6a68-4c6a-a1fc-649ca8b40115","resolution":{"observed_at":"2026-08-08T10:26:46.008113Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T10:26:45.997698Z","title":"Slora: Scalable serving of thousands of lora adapters","venue":null,"work_id":"d3e568d2-6420-49ed-9c38-3e571b0fb016","year":2024},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.507523Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:0b9d1b3c5152d74fbdb9db453a85016e79000c209bf8c4925badd06b7ef37a40","observation_id":"e8aa1cdc-a75e-471f-8a90-ec11923f4885","resolution":{"observed_at":"2026-08-08T10:26:46.000479Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T10:26:45.990612Z","title":"Mobilequant: Mobile-friendly quantization for on-device language models, 2024","venue":null,"work_id":"c3f9ac51-f36d-4f8d-9270-649c01b0d8a9","year":2024},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.509836Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:5eb550b329fd34a8575a0aeda84f4ce9fd40241684460b3e1425c28284d972e3","observation_id":"d29b73f3-23e2-485c-8a9f-6dbb7a456bf4","resolution":{"observed_at":"2026-08-08T10:26:45.993011Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-08T10:26:45.512286Z","title":"Llama: Open and efficient foundation language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.512286Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:72391c75277787c8bd6ddbac0862772ec9b1d65cbcfc1522448aeccb45d3e1d2","observation_id":"05c142c6-d0a2-4f45-9832-01906fe54a72","resolution":{"observed_at":"2026-08-08T10:26:45.512286Z","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":"2026-08-08T10:26:45.514738Z","title":"Llama 2: Open foundation and fine-tuned chat models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.514738Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:ea0921afa8c4bed982305000ad1fb1d022cafd60f40b913f281c3db72e577c8e","observation_id":"22c3c324-c0e7-434c-95f1-6d9378616ea3","resolution":{"observed_at":"2026-08-08T10:26:45.514738Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.05000","last_updated":"2024-07-16T07:32:23Z","snapshot_observed_at":"2026-07-06T18:42:18.289966Z","submitted_at":"2024-07-06T08:37:21Z","title":"LoRA-GA: Low-Rank Adaptation with Gradient Approximation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.05000","snapshot_observed_at":"2026-08-08T10:26:45.517130Z","title":"Lora-ga: Low-rank adaptation with gradient approxi- mation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.517130Z"},"links":{"cited_paper":"/paper/2407.05000","citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:5a40931dc2de39f53995b9fa6c53169623c8e18ca549dcce54362e65c709cda2","observation_id":"fd9232b5-9df6-49a1-ae56-1b4d57f1c518","resolution":{"observed_at":"2026-08-08T10:26:45.517130Z","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":"2026-08-08T10:26:45.983892Z","title":"Bitstack: Any-size compression of large language models in variable memory environments, 2025","venue":null,"work_id":"3b64b546-8346-4e3a-9b93-6f04ee8e6daf","year":2025},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.519297Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:7f20e6eeca223a9f4260a6555f7a6a59b90249455958393441c34a1c484a1b6c","observation_id":"b1539df9-4580-4d4a-b9f9-08a3884e0ec2","resolution":{"observed_at":"2026-08-08T10:26:45.986265Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.07705","last_updated":"2022-10-24T07:00:15Z","snapshot_observed_at":"2026-07-06T13:00:53.618234Z","submitted_at":"2022-04-16T03:12:30Z","title":"Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.07705","snapshot_observed_at":"2026-08-08T10:26:45.521338Z","title":"Super-naturalinstructions: Generalization via declarative instructions on 1600+ nlp tasks","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.521338Z"},"links":{"cited_paper":"/paper/2204.07705","citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:8d1b68c953623c3e7bb838ef44330e59a2bffacfddf2e4575d00d6578d4322bb","observation_id":"0c42d943-5018-4403-a3db-a25a1705382b","resolution":{"observed_at":"2026-08-08T10:26:45.521338Z","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":"2026-08-08T10:26:45.523543Z","title":"Attention is all you need","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.523543Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:ddf991c544747d223902876a6f73540230b67e92a5e666d1c8c2a81f9d8d3d2f","observation_id":"2c36b1fc-5c1f-44dd-bce8-395e117dd9ef","resolution":{"observed_at":"2026-08-08T10:26:45.523543Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.01652","last_updated":"2022-02-08T20:26:45Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2021-09-03T17:55:52Z","title":"Finetuned Language Models Are Zero-Shot Learners","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.01652","snapshot_observed_at":"2026-08-08T10:26:45.525644Z","title":"Finetuned language models are zero-shot learners","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.525644Z"},"links":{"cited_paper":"/paper/2109.01652","citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:fbbef24b0ebaac8b6d8ce0a932ee6034fa42fde2e0d904f34c7dbc869a81889c","observation_id":"d84f2852-f761-4ef8-b75d-6094eeb443bf","resolution":{"observed_at":"2026-08-08T10:26:45.525644Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.10462","last_updated":"2021-02-20T22:37:41Z","snapshot_observed_at":"2026-07-06T10:43:11.902082Z","submitted_at":"2021-02-20T22:37:41Z","title":"BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.10462","snapshot_observed_at":"2026-08-08T10:26:45.528383Z","title":"Bsq: Exploring bit-level sparsity for mixed-precision neural network quantization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.528383Z"},"links":{"cited_paper":"/paper/2102.10462","citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:41c810b46a4e8ad3285ebcb093edfd33443622cf1274f3ce856a85f15958de87","observation_id":"4b6c4bfa-8f5c-47dc-a14a-529e2f8848f6","resolution":{"observed_at":"2026-08-08T10:26:45.528383Z","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":"2026-08-08T10:26:45.531050Z","title":"Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked language-models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.531050Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:a13248179b617aecf87560988e7e51a8cf5e3f72200ae86d1fd62c3365f5672f","observation_id":"fea2afa2-80fe-42c3-9518-7ac136821915","resolution":{"observed_at":"2026-08-08T10:26:45.531050Z","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":"2026-08-08T10:26:45.973043Z","title":"Atom: Low-bit quantization for efficient and accurate llm serving","venue":null,"work_id":"0695db06-4529-45fb-9126-b1667ccb7036","year":2024},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.533497Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:66be4a0fd6083c5b5352228d11567e6e980ae48b4c1815a1707c3ed3a0d368c2","observation_id":"0e1f3ca7-b3f7-4062-8cc8-595ec780edcd","resolution":{"observed_at":"2026-08-08T10:26:45.975534Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T10:26:45.535838Z","title":"Sysmol: A hardware-software co-design framework for ultra-low and fine-grained mixed-precision neural networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.535838Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:837a7a766990613935cbc5c02aa53d7d3d6d601d85e38a40044396213d884466","observation_id":"b98012bd-752a-4427-a768-9d682f6ab1f7","resolution":{"observed_at":"2026-08-08T10:26:45.535838Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1909.08593","last_updated":"2020-01-08T23:02:36Z","snapshot_observed_at":"2026-08-08T07:44:49.921146Z","submitted_at":"2019-09-18T17:33:39Z","title":"Fine-Tuning Language Models from Human Preferences","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.08593","snapshot_observed_at":"2026-08-08T10:26:45.538339Z","title":"ND” indicates no data, “-","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.538339Z"},"links":{"cited_paper":"/paper/1909.08593","citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:60813f9657b552b5a8ccbf5be1458edd261c4f32d1fcbf68c829f1eabf1217f0","observation_id":"6651fd52-025c-4696-ba56-b122cca831a2","resolution":{"observed_at":"2026-08-08T10:26:45.538339Z","resolver_source":null,"status":"malformed_identifier"},"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":"2026-08-08T10:26:45.966480Z","title":null,"venue":null,"work_id":"48afc45a-96e5-4f9f-843f-81801cd7cdaa","year":null},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.541568Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:ff852a6b5b2875c41cf85a483d89477740218823e27e2e8848c5dee26e72bda4","observation_id":"3a5b2d99-c993-42a2-804d-18fa8ee9ce54","resolution":{"observed_at":"2026-08-08T10:26:45.968656Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T10:26:45.958262Z","title":"initializes","venue":null,"work_id":"3604ed1b-da04-4b9a-907d-a4e4b85b3575","year":1919},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.544148Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:441068f8f202c8170158384b385b749d1e886803890e98fd75a53a34d65f61f2","observation_id":"28a5915a-6acb-436e-af3d-57e230934208","resolution":{"observed_at":"2026-08-08T10:26:45.960914Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T10:26:45.951020Z","title":null,"venue":null,"work_id":"e51a8580-2f96-4e90-a6c5-27a79ea8dd7e","year":null},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.547080Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:3c97d846c010c8bff87d9a176eda4c7f0096f12dcadb33a5d42d1bec2ade2630","observation_id":"59aad7f4-5823-4c6b-9a56-337fb51d88cd","resolution":{"observed_at":"2026-08-08T10:26:45.953592Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T10:26:45.941246Z","title":"(M-step) These steps are repeated until convergence or until a stopping criterion (e.g., a maximum number of iterations) is met","venue":null,"work_id":"59242ef1-a5f6-42f0-948c-1cb27a22218d","year":null},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.549571Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:c3876408fcd6291a285d0dc5e5edfe3b2601541cecbe8543e6e02c1403c3927f","observation_id":"500d6b44-9e82-418b-9257-e1a42eaa1fc5","resolution":{"observed_at":"2026-08-08T10:26:45.945979Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T10:26:46.126090Z","title":null,"venue":null,"work_id":"156db393-e9d0-45d7-8502-95400ffa20fa","year":2025},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.418721Z"},"links":{"citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:04681bce2241a11f4cd42cba5188ad9fe79b581cf9b91ed6b65a9dafd9666a1d","observation_id":"2eead5f4-9ade-45bb-a442-c6085a03ee64","resolution":{"observed_at":"2026-08-08T10:26:46.128752Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T04:48:00.853366Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits"},"reference_resolution":{"displayed":60,"state_counts":{"malformed_identifier":2,"metadata_mismatch":0,"parse_uncertain":1,"unresolved":33,"verified_exact":0,"verified_fuzzy":24},"total_outbound_references":60},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 60 of 60 outbound references and 0 inbound Pith citation observations for arXiv:2502.08141."}