{"as_of":"2026-08-10T20:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e17a811354a5d2edd51649d6ae0033b16c8a6c85b109856d8d58fcdf0512576c","coverage":[{"denominator":71,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":71,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T14:28:16.230983Z","state":"measured"},{"denominator":71,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":71,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+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/2505.18877/citation-record","integrity":"/paper/2505.18877/integrity","json":"/paper/2505.18877/citation-record.json","paper":"/paper/2505.18877"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-07T14:28:13.330699Z","title":"Gpt-4 technical report.arXiv preprint arXiv:2303.08774, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:13.330699Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:b5664062ed102fb8a0373eac33cecfae0a676c5d9bfacb05dd70ec6455a9fccc","observation_id":"a527544c-2dc5-44f4-be14-866ca39c8cbd","resolution":{"observed_at":"2026-08-07T14:28:13.330699Z","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":"2026-08-07T14:28:23.758617Z","title":"A convergence analysis of gradient descent for deep linear neural networks","venue":null,"work_id":"c5b68dd3-a3d1-471e-b3ba-3f64c517f0f3","year":2018},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:13.425282Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:ddf052ca94e13c6b53c858cd1b72a06ec58ce3dd293b8c260d2da11ba43401d8","observation_id":"17df7105-13cc-44ee-98ba-2f66d91240cf","resolution":{"observed_at":"2026-08-07T14:28:23.885744Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:13.526884Z","title":"Nonlinear programming.Journal of the Operational Research Society, 48(3):334–334, 1997","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:13.526884Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:fffb06f017e34e9c9c1b6afe798ffb7e1312c0771eb3e1c8b33b273760bb19e5","observation_id":"d3e10a48-7a2b-4dcf-b898-77bdc4a75db5","resolution":{"observed_at":"2026-08-07T14:28:13.526884Z","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":"2026-08-07T14:28:23.572443Z","title":"Piqa: Reasoning about physical common- sense in natural language","venue":null,"work_id":"3a44760d-66b4-4c2a-af79-2f882015d9e9","year":2020},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:13.638997Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:50ad4c8754a8639da33184d69cea61359b704ef11b18eca7ad0d803426ef9bb8","observation_id":"b97127dd-fe64-4dde-bad6-c30526d90319","resolution":{"observed_at":"2026-08-07T14:28:23.661423Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:13.703115Z","title":"Cambridge University Press, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:13.703115Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:ee5d3c0b948d303fa0aa1ff69b30425d887534572353b5945f83cd511830bfb4","observation_id":"a8543f4e-9501-4d12-8bcd-cc3d3bd8a599","resolution":{"observed_at":"2026-08-07T14:28:13.703115Z","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":"2026-08-07T14:28:13.790264Z","title":"Cambridge university press, 2004","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:13.790264Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:2417d63ee94b22aaf8ab81c858b0b3b0bffac93cc27e7b2ac673d186fdfe7c01","observation_id":"5726069f-6790-4114-97b9-6ff693d3b722","resolution":{"observed_at":"2026-08-07T14:28:13.790264Z","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":"2026-08-07T14:28:23.339189Z","title":"SemEval-2017 task 1: Semantic textual similarity-multilingual and cross-lingual focused evaluation","venue":null,"work_id":"adb329d5-2e4d-402b-8233-e7809f4a7ab6","year":2017},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:13.873592Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:c141540fef1fadde53ab6cfe394017fe3fb7d8a3b687ebbf5b72eb8e6c208c88","observation_id":"f4eca558-f8c6-4d84-b5f6-c76db56a0e47","resolution":{"observed_at":"2026-08-07T14:28:23.420575Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2107.03374","last_updated":"2021-07-14T17:16:02Z","snapshot_observed_at":"2026-08-08T11:58:24.516369Z","submitted_at":"2021-07-07T17:41:24Z","title":"Evaluating Large Language Models Trained on Code","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.03374","snapshot_observed_at":"2026-08-07T14:28:13.955580Z","title":"Evaluating large language models trained on code.arXiv preprint arXiv:2107.03374, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:13.955580Z"},"links":{"cited_paper":"/paper/2107.03374","citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:4159d8748885dfb15de94869cc1a6c4ddf3c7d70772fda86bf932a2e8fda8686","observation_id":"b4624a27-371f-46a4-a5e5-82de3e793c60","resolution":{"observed_at":"2026-08-07T14:28:13.955580Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.01547","last_updated":"2019-11-25T13:02:04Z","snapshot_observed_at":"2026-07-06T08:34:41.399203Z","submitted_at":"2019-11-05T00:31:38Z","title":"On the Measure of Intelligence","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.01547","snapshot_observed_at":"2026-08-07T14:28:14.053341Z","title":"On the measure of intelligence.arXiv:1911.01547, 2019","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:14.053341Z"},"links":{"cited_paper":"/paper/1911.01547","citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:1a260fd59b9be8b1cc0b1737968c5257844816ab848921978ea432f8e4c26914","observation_id":"8e75e3dd-3f74-41fd-a384-c7f31bf8dbda","resolution":{"observed_at":"2026-08-07T14:28:14.053341Z","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":"2026-08-07T14:28:23.152453Z","title":"BoolQ: Exploring the surprising difficulty of natural yes/no questions","venue":null,"work_id":"4a020eb8-5669-4c2f-89db-6623f367875f","year":2019},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:14.155124Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:85c33daad53b1b37cd71d8377351ab9d0c290fa5e30345b645379147ddebb120","observation_id":"72510422-34f3-4feb-8fdd-094e834c3852","resolution":{"observed_at":"2026-08-07T14:28:23.240205Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:22.987795Z","title":"Jan Maire, Leiden, 1637","venue":null,"work_id":"73ba044e-cc38-4e39-80fc-74c3a7c4513a","year":null},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:14.227139Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:335ec769b788d636fef4106ee7222335d9c67c4a101a7817c07639c78aaba3f1","observation_id":"5b4042dd-e8b1-4ffd-a0e9-23c0e27fdcee","resolution":{"observed_at":"2026-08-07T14:28:23.043548Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:22.843682Z","title":"Qlora: Efficient finetuning of quantized llms","venue":null,"work_id":"d50598fe-9dea-4205-88af-24c8694259dd","year":2023},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:14.334115Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:a88dc77876467ad03d9da4f9c66272c8078d405fd12982eae687da9a3c6ad4e4","observation_id":"780c2984-885b-43b2-9dfc-025909159110","resolution":{"observed_at":"2026-08-07T14:28:22.899000Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:14.405053Z","title":"Automatically constructing a corpus of sentential paraphrases","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:14.405053Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:71dfb701332832ab2204fcc4fe5b1378e178e90d985ecc37bf44c965ae7cc26f","observation_id":"9ba36ac6-7c72-4f32-8102-702694602f09","resolution":{"observed_at":"2026-08-07T14:28:14.405053Z","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":"2026-08-07T14:28:22.610836Z","title":"Algorithmic regularization in learning deep homogeneous models: Layers are automatically balanced","venue":null,"work_id":"91c17513-a86b-456f-af46-157fecb5cb37","year":2018},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:14.484602Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:501e981203f58e6d077b5df51d9179368468e87fe8ab85e8aec1c811ef5f751a","observation_id":"9ad96af1-4dd5-4317-b18b-5d44fafb64be","resolution":{"observed_at":"2026-08-07T14:28:22.684381Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:22.468225Z","title":"Parameter- efficient fine-tuning with discrete fourier transform","venue":null,"work_id":"46e18852-70f1-4368-8505-add79cbe85db","year":2024},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:14.536806Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:99d50056a26eb111cccd2075448d579fd40a534b51054d13e0070d15fa244f29","observation_id":"8b706d0c-b3b6-44bf-842f-dc6adc72589e","resolution":{"observed_at":"2026-08-07T14:28:22.528368Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:14.626061Z","title":"MIT press Cambridge, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:14.626061Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:87fcc22e31228e6a2bf276da59d61d0e3a4f84a147dbf48885a686507a24cdd6","observation_id":"efdb8fe9-7841-425c-a564-e14a0a3569f1","resolution":{"observed_at":"2026-08-07T14:28:14.626061Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-08-10T16:40:37.411115Z","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":"2026-08-07T14:28:14.695895Z","title":"The Llama 3 herd of models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:14.695895Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:c08ef00d7f7b26820b03505352acc556d85a78c9fb7d7dcc46daddd29c4ed9f2","observation_id":"ffaa7396-aeed-439c-90f4-f8010d10d1b1","resolution":{"observed_at":"2026-08-07T14:28:14.695895Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.07463","last_updated":"2021-06-09T14:39:17Z","snapshot_observed_at":"2026-08-10T10:06:48.397353Z","submitted_at":"2020-12-14T12:34:01Z","title":"Parameter-Efficient Transfer Learning with Diff Pruning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.07463","snapshot_observed_at":"2026-08-07T14:28:14.757107Z","title":"Parameter-efficient transfer learning with diff pruning","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:14.757107Z"},"links":{"cited_paper":"/paper/2012.07463","citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:512784ea57993704171b45c0ed2934751c8de6a18a5f5103f8f5c244d7b711a6","observation_id":"c425fb2f-8e5b-4e30-94cc-9adf9af76ceb","resolution":{"observed_at":"2026-08-07T14:28:14.757107Z","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":"2026-08-07T14:28:22.232508Z","title":"FLORA: Low-rank adapters are secretly gradient compres- sors","venue":null,"work_id":"47d14346-4444-46d4-bedf-220f6109e209","year":2024},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:14.814500Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:6dd478413fa21cab37d6f59de6882361fefa157ec6791ac7483faf8e28f24101","observation_id":"9b8f5a68-6162-4d33-b75a-b78cc5326459","resolution":{"observed_at":"2026-08-07T14:28:22.334747Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:22.115146Z","title":"LoRA+: Efficient low rank adaptation of large models","venue":null,"work_id":"5d30f643-4ef4-400b-951b-173945ce0ec6","year":2024},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:14.891590Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:fb9461186b51ace42b9949ed95f1a6b04f9e87b6cc1fd014304e8de587a5c04b","observation_id":"0784d53f-2d5c-45bc-9552-7226dc72125d","resolution":{"observed_at":"2026-08-07T14:28:22.182538Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:14.960046Z","title":"DeBERTav3: Improving deBERTa using ELECTRA-style pre-training with gradient-disentangled embedding sharing","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:14.960046Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:c84ae16ea1b9e5d8a952cfeeaa75ebfdcfe6076b89493d2d22424a1357642b50","observation_id":"96dcaa18-5495-4e43-a474-77e84690d553","resolution":{"observed_at":"2026-08-07T14:28:14.960046Z","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":"2026-08-07T14:28:21.910142Z","title":"Parameter-efficient transfer learning for NLP","venue":null,"work_id":"da3fa45a-8679-4faa-83b2-f23cb0c499ee","year":2019},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:15.014268Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:b15b8b236cd668402dd2d3467fa76ec490d10ebb550af6ba4d8abe84087324e6","observation_id":"55f235b1-3920-4aee-aa4b-15be1d3bd929","resolution":{"observed_at":"2026-08-07T14:28:21.986716Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:15.077267Z","title":"LoRA: Low-rank adaptation of large language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:15.077267Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:d1d7901812c3c51ceca4ed9f9e72dd468d66a75fd805d46bc370378afb34b309","observation_id":"ee96db6b-9fa6-4f01-83cd-7ab6b000c28c","resolution":{"observed_at":"2026-08-07T14:28:15.077267Z","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":"2026-08-07T14:28:21.722590Z","title":"LLM-Adapters: An adapter family for parameter-efficient fine-tuning of large language models","venue":null,"work_id":"d9d4b9eb-f214-4c16-bc2c-99e7f9e8db85","year":2023},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:15.120561Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:119f9bd3be42f9517c4f84d637d3f7fb41fe76dea716104f71109a0e041ff019","observation_id":"c67298aa-25e8-4c90-8311-8cfcf1b7f768","resolution":{"observed_at":"2026-08-07T14:28:21.805509Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:15.158781Z","title":"FedPara: Low-rank hadamard product for communication-efficient federated learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:15.158781Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:fabc81f9f1d212a1c99214e092838fae6084b02f4d49ea1c5a03563c4fd33334","observation_id":"011d4730-1f16-466f-9129-eae6ba665df0","resolution":{"observed_at":"2026-08-07T14:28:15.158781Z","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":"2026-08-07T14:28:15.206746Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:15.206746Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:50cde3ca82b6c6528b01c822943a6740e9ab147a37a292cfca95b7ab2918fc86","observation_id":"8990b3db-2881-4fe5-a538-51c4eadfe384","resolution":{"observed_at":"2026-08-07T14:28:15.206746Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.05431","last_updated":"2025-03-07T14:01:25Z","snapshot_observed_at":"2026-08-07T17:22:06.049046Z","submitted_at":"2025-03-07T14:01:25Z","title":"Quantum-PEFT: Ultra parameter-efficient fine-tuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.05431","snapshot_observed_at":"2026-08-07T14:28:15.279162Z","title":"Quantum-peft: Ultra parameter-efficient fine-tuning.arXiv preprint arXiv:2503.05431, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:15.279162Z"},"links":{"cited_paper":"/paper/2503.05431","citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:609067c0a2c54d574553da8c50789bc8f664f5497f39488c2dc0da9fb455df55","observation_id":"b9e938e7-e4c8-4b82-9d3b-be251e0f39db","resolution":{"observed_at":"2026-08-07T14:28:15.279162Z","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":"2026-08-07T14:28:21.468559Z","title":"VeRA: Vector-based random matrix adaptation","venue":null,"work_id":"cbc0fea0-3f84-471b-8b21-38f357da2985","year":2024},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:15.371302Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:90d03a573563939ca6c9b59f1f2cb3a01aadc0af5e311f647df2d7a06a47946f","observation_id":"954d7b51-a8d1-4a1d-a1c7-b52d68989fab","resolution":{"observed_at":"2026-08-07T14:28:21.564535Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:21.309350Z","title":"The power of scale for parameter-efficient prompt tuning","venue":null,"work_id":"43899f24-528d-4579-bc32-66ad7c15418b","year":2021},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:15.419501Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:bf92dd32d48d5cd534fcd2e5217d594e5ccf97cbbfce95769720802c72fc49d8","observation_id":"3ca259db-8ba9-490d-a8d8-a3e6c41a668b","resolution":{"observed_at":"2026-08-07T14:28:21.391404Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:21.004516Z","title":"Implicit regularization of sharpness-aware minimization for scale-invariant problems","venue":null,"work_id":"4aa29093-00fa-49cb-94b2-3911571d4aac","year":2024},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:15.487732Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:ebb6eefb898ea1119f37d95c2a18339cfbda4ddfa7139b95ce4d908c19b5fb5b","observation_id":"9db08bc5-b526-42ee-9c5e-00780593f909","resolution":{"observed_at":"2026-08-07T14:28:21.122174Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:20.791825Z","title":"On the crucial role of initialization for matrix factorization","venue":null,"work_id":"eaae9696-74dc-4a25-9772-2c1e14ca4458","year":2025},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:15.539601Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:fa0e786e6c26cb8aa2c7701069951af750fa4ae6a94e1f9422863ef5153c3689","observation_id":"90ea32fa-4253-497d-8053-ec280b2d2d35","resolution":{"observed_at":"2026-08-07T14:28:20.882603Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:20.531379Z","title":"Geometric means.Linear algebra and its applications, 385:305–334, 2004","venue":null,"work_id":"e121d9c5-582e-49d8-b4dc-92adbeb1c660","year":2004},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:15.607555Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:52e13d37f64689f7f8e96d7c3480507f6e8346526aabc971e0a242bf00512449","observation_id":"4a2c7f07-7e33-4309-95ef-4b41e75dad37","resolution":{"observed_at":"2026-08-07T14:28:20.703577Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:20.326109Z","title":"Prefix-tuning: Optimizing continuous prompts for generation","venue":null,"work_id":"36824e94-845e-4882-889e-8b181f8b154c","year":2021},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:15.662276Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:f86264a1726589a904a74f6d0123935e92b220f9010105e156b70a12f4ce5d07","observation_id":"69fa7db9-eb84-4bcd-a569-07487157f3f5","resolution":{"observed_at":"2026-08-07T14:28:20.448025Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:15.720084Z","title":"LoftQ: LoRA-fine-tuning-aware quantization for large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:15.720084Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:dc509601ba5024f421aa671a8394cb28482947b22efd29bbc44d7ed9e39aeacc","observation_id":"cfa51c0c-a50a-4723-a225-9174b886f9c7","resolution":{"observed_at":"2026-08-07T14:28:15.720084Z","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":"2026-08-07T14:28:20.144043Z","title":"ReLoRA: High-rank training through low-rank updates","venue":null,"work_id":"7d68d24a-fc59-4267-93e5-6f49523270ac","year":2024},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:15.774254Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:4487b76c42b585a59be6483a0baf7e13b982cdeb3347732ae5f8fced7ba54f5d","observation_id":"ec8440a7-3c80-4ac4-ade4-239727e920b0","resolution":{"observed_at":"2026-08-07T14:28:20.233100Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:19.968386Z","title":"Exploring versatile generative language model via parameter-efficient transfer learning","venue":null,"work_id":"dc419515-a865-42bd-b7cb-f9b50d9ee785","year":2020},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:15.831610Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:1105aeaef96ce18bb0218d4d95cfc650670d2a53a5e893db7464e58945a39fb3","observation_id":"149affe7-bc63-488d-bbc2-b1af56bd062f","resolution":{"observed_at":"2026-08-07T14:28:20.013738Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.19597","last_updated":"2024-05-30T01:27:43Z","snapshot_observed_at":"2026-08-09T04:52:20.683968Z","submitted_at":"2024-05-30T01:27:43Z","title":"SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.19597","snapshot_observed_at":"2026-08-07T14:28:15.841023Z","title":"Svft: Parameter-efficient fine-tuning with singular vectors.arXiv:2405.19597, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:15.841023Z"},"links":{"cited_paper":"/paper/2405.19597","citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:d573c1ec61b4bc956daaf4f5db675d57220516fbd4c0ccf8c10329c1d4fb4b07","observation_id":"3850cd44-e170-4585-9935-af9e32d5b505","resolution":{"observed_at":"2026-08-07T14:28:15.841023Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.06243","last_updated":"2024-04-28T20:05:02Z","snapshot_observed_at":"2026-07-06T16:45:51.193825Z","submitted_at":"2023-11-10T18:59:54Z","title":"Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.06243","snapshot_observed_at":"2026-08-07T14:28:15.853890Z","title":"Parameter-efficient orthogonal finetuning via butterfly factorization.arXiv preprint arXiv:2311.06243, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:15.853890Z"},"links":{"cited_paper":"/paper/2311.06243","citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:c37030f664a11e7a98c0d52048cf71c598a194332f22e12ccf913bb4865a2336","observation_id":"0e78eefc-09f6-4faa-8402-957d1fee23f5","resolution":{"observed_at":"2026-08-07T14:28:15.853890Z","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":"2026-08-07T14:28:15.867691Z","title":"Cola: Compute-efficient pre-training of llms via low-rank activation.arXiv preprint arXiv:2502.10940, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:15.867691Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:5487538d23baabae4ff5694057233ade73fe639ea5a480620efff59c788e6c45","observation_id":"8ec18530-d6da-487a-a3a2-0054d8530c3a","resolution":{"observed_at":"2026-08-07T14:28:15.867691Z","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":"2026-08-07T14:28:15.876525Z","title":"Decoupled weight decay regularization","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:15.876525Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:87ee6973acea41da79a3bce3d244f603b59e74a23a36eedbafa720e3ccc656c2","observation_id":"61785207-2724-4dbf-b127-dbac7298f76c","resolution":{"observed_at":"2026-08-07T14:28:15.876525Z","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":"2026-08-07T14:28:19.864913Z","title":"Pissa: Principal singular values and singular vectors adap- tation of large language models","venue":null,"work_id":"d89f87f6-a07c-4333-8691-018433547e8b","year":2024},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:15.882310Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:339ede0b2193816ab5555c4f254ad57bb49f6de2226406a70c79456ea7c03a40","observation_id":"66d7b25d-149f-41e4-8f0a-4897fbfb3128","resolution":{"observed_at":"2026-08-07T14:28:19.900030Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1809.02789","last_updated":"2018-09-08T11:47:16Z","snapshot_observed_at":"2026-08-08T02:19:52.596062Z","submitted_at":"2018-09-08T11:47:16Z","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.02789","snapshot_observed_at":"2026-08-07T14:28:15.889901Z","title":"Can a suit of armor conduct electricity? A new dataset for open book question answering.arXiv:1809.02789, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:15.889901Z"},"links":{"cited_paper":"/paper/1809.02789","citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:7872c09cc054d3fee9236c98fa3c0b7fb6c5711d45c12d4a390f1f45584e1348","observation_id":"1a7e628e-12dc-4779-8dfb-70487c6e64db","resolution":{"observed_at":"2026-08-07T14:28:15.889901Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.04207","last_updated":"2024-10-15T00:21:38Z","snapshot_observed_at":"2026-07-06T19:28:26.436468Z","submitted_at":"2024-10-05T15:52:47Z","title":"Learning on LoRAs: GL-Equivariant Processing of Low-Rank Weight Spaces for Large Finetuned Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.04207","snapshot_observed_at":"2026-08-07T14:28:15.903127Z","title":"Learning on loras: Gl-equivariant processing of low-rank weight spaces for large finetuned models.arXiv:2410.04207, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:15.903127Z"},"links":{"cited_paper":"/paper/2410.04207","citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:7f71d28bfdba4a304bf5de973e8f8688765b08ca3625aa37cb436d1cc2cfc10f","observation_id":"79498881-79f0-4e2a-89d7-129f7491f198","resolution":{"observed_at":"2026-08-07T14:28:15.903127Z","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":"2026-08-07T14:28:19.740641Z","title":"Know what you don’t know: Unanswerable questions for SQuAD","venue":null,"work_id":"5d9751e8-5b4a-4942-915a-656fe332beb1","year":2018},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:15.913052Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:c1dda0a70130df3cd32878da987b8194cb53aaa221f22100731a0eae29b72293","observation_id":"45f55186-d930-4760-935d-fdb81b60060d","resolution":{"observed_at":"2026-08-07T14:28:19.777479Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:19.645048Z","title":"High-resolution image synthesis with latent diffusion models","venue":null,"work_id":"10407f73-6663-479d-9309-3907ffdbe574","year":2022},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:15.925988Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:10bfcffc3a2f0cff3d43bc04bedd6b15ef3d525ee89b2ada6a1a179306577ae6","observation_id":"b115734a-7935-403b-ac52-a434c251912d","resolution":{"observed_at":"2026-08-07T14:28:19.682501Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:19.504101Z","title":"AdapterDrop: On the efficiency of adapters in transformers","venue":null,"work_id":"8ca929ae-5c99-4adc-93dc-718c19634aaa","year":2021},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:15.936912Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:9c4d7e550ffe45e27844a15a3ee35b0dec3fb26a477270b7220150d671887161","observation_id":"7e5c48db-e302-4ede-8b59-7bea01c174db","resolution":{"observed_at":"2026-08-07T14:28:19.565489Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:15.950230Z","title":"McGraw-Hill, New York, 3rd edition, 1976","venue":null,"work_id":null,"year":1976},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:15.950230Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:f73a5db168404a0c51b2ac699980e71c85937ed5fb98712d3ce45ec34fa85d9c","observation_id":"c8ae42bb-06eb-46b5-abd9-a652af2670e6","resolution":{"observed_at":"2026-08-07T14:28:15.950230Z","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":"2026-08-07T14:28:19.350733Z","title":"Dream- booth: Fine tuning text-to-image diffusion models for subject-driven generation","venue":null,"work_id":"de5d0849-8c15-4d69-a9c7-6138830ea5d5","year":2023},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:15.975637Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:8dedd932e3a72e3097ff033369a83380f0f1d290345831d4463b5ac34cf07343","observation_id":"bc981061-040f-443e-a6c7-be004b13d0f8","resolution":{"observed_at":"2026-08-07T14:28:19.419673Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:15.986692Z","title":"Winogrande: An adversarial winograd schema challenge at scale.Communications of the ACM, 64(9):99–106, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:15.986692Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:5970c89535ee71ddae7c1c7148125d9cdeacdc61ff641dcc08cddd458d0bce20","observation_id":"085149b8-52f8-4660-8dfb-496d39b116f6","resolution":{"observed_at":"2026-08-07T14:28:15.986692Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1904.09728","last_updated":"2019-09-09T17:29:55Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2019-04-22T05:36:37Z","title":"SocialIQA: Commonsense Reasoning about Social Interactions","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.09728","snapshot_observed_at":"2026-08-07T14:28:16.004228Z","title":"Socialiqa: Commonsense reasoning about social interactions.arXiv:1904.09728, 2019","venue":null,"work_id":null,"year":1904},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:16.004228Z"},"links":{"cited_paper":"/paper/1904.09728","citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:0ec5ea756dda21ccc800fb08d2ec3c2a9cd19f419e63acd64a0bcf97a04bd1d6","observation_id":"048d6765-dd50-4d45-aac2-c38bc65d1ff8","resolution":{"observed_at":"2026-08-07T14:28:16.004228Z","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":"2026-08-07T14:28:19.188349Z","title":"Ge- oloRA: Geometric integration for parameter efficient fine-tuning","venue":null,"work_id":"95c4bc35-7710-44fe-a7b2-3de6b5566f08","year":2025},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:16.013604Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:336b40df4a8f45fdbca0280302bc50728885f5115fda5454fb8d9e8c5dec46a6","observation_id":"fa604ac7-b69e-4472-b550-72bfd21e993e","resolution":{"observed_at":"2026-08-07T14:28:19.237272Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:16.023260Z","title":"Cambridge university press, 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:16.023260Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:fc9c2119189a9460c27c9668313f3983efbb49e918820ebe9e63ba7727ce8507","observation_id":"165fd47c-539b-4985-961e-0c54b26049b5","resolution":{"observed_at":"2026-08-07T14:28:16.023260Z","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":"2026-08-07T14:28:19.035244Z","title":"Recursive deep models for semantic compositionality over a sentiment treebank","venue":null,"work_id":"e6c5b75a-6ad2-4d13-bbd8-6978c7c85148","year":2013},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:16.034109Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:87c0aafe8db1507aa22f63a8f91a0ea5d762de4962a40c3cc46a74385e067561","observation_id":"dceb3860-b33f-4969-a5eb-94541ea6fd7c","resolution":{"observed_at":"2026-08-07T14:28:19.110548Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:18.875786Z","title":"Training neural networks with fixed sparse masks","venue":null,"work_id":"a4a1710f-4f62-44a5-8cb6-aa1b987c5dc8","year":2021},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:16.042134Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:16901959b6349a6882830f35df5c91f58b144909a50a00770b47473702a86900","observation_id":"848506c5-9588-4309-8803-c489d91d19b2","resolution":{"observed_at":"2026-08-07T14:28:18.948854Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2211.09085","last_updated":"2022-11-16T18:06:33Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-11-16T18:06:33Z","title":"Galactica: A Large Language Model for Science","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.09085","snapshot_observed_at":"2026-08-07T14:28:16.047793Z","title":"Galactica: A large language model for science.arXiv preprint arXiv:2211.09085, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:16.047793Z"},"links":{"cited_paper":"/paper/2211.09085","citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:d9591e1d44b2d1c1e2e4d40ef7121e51b70bb6132620d444dbe2c7e8107d52f4","observation_id":"ce1c2f75-d5c3-4734-afc8-e6f347e3ae73","resolution":{"observed_at":"2026-08-07T14:28:16.047793Z","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":"2026-08-07T14:28:18.692205Z","title":"Accelerating ill-conditioned low-rank matrix estimation via scaled gradient descent.J","venue":null,"work_id":"f62ad203-3873-411f-ab95-e51fb55c7f16","year":2021},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:16.056137Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:4c0b39a84a8f49b7ef7b945786169841ef77d8ff27b8a631dd355b1ea9d0d6ad","observation_id":"28615673-0aeb-4843-9a2a-b17c237fff93","resolution":{"observed_at":"2026-08-07T14:28:18.786532Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:16.066259Z","title":"LLaMA: Open and efficient foundation language models.arXiv preprint arXiv:2302.13971, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:16.066259Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:dd5d2803288dc6063283b229c3e9b9bd85f5a1a0b05deee5b8bd1776229d9a84","observation_id":"ca9396cc-f70b-405a-9486-e97c4777c470","resolution":{"observed_at":"2026-08-07T14:28:16.066259Z","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":"2026-08-07T14:28:16.081344Z","title":"Llama 2: Open foundation and fine-tuned chat models.arXiv preprint arXiv:2307.09288, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:16.081344Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:f47d4d35a7e811647e4c89f8bce523f267585383bbc79af3fc2d2e1f33e0ab5e","observation_id":"4cb3ae27-d87b-47d2-918c-3ac307ee099c","resolution":{"observed_at":"2026-08-07T14:28:16.081344Z","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":"2026-08-07T14:28:18.552844Z","title":"GLUE: A multi-task benchmark and analysis platform for natural language understanding","venue":null,"work_id":"6c2e480e-78fb-4556-b0ff-fb441700ef38","year":2019},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:16.093833Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:0dfb12b512949385d098a941a53787e260d854e21fd83c0e9d0d573e53a6839d","observation_id":"23f182ac-72a6-4d49-9615-2d81ac6269fc","resolution":{"observed_at":"2026-08-07T14:28:18.593026Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:18.348840Z","title":"Lora-ga: Low-rank adaptation with gradient approximation","venue":null,"work_id":"46d2f5e6-daf4-4bd4-8b01-b9dab35daaf6","year":2024},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:16.104540Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:aadc1761639b1491e53a377f8aa5a1c17502cc41de4409f044954cbb4990ca08","observation_id":"263824d8-d999-43b8-946b-efd3fa874c7d","resolution":{"observed_at":"2026-08-07T14:28:18.459699Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:16.110697Z","title":"LoRA-pro: Are low-rank adapters properly optimized? InProc","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:16.110697Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:f7701de13dd0531c8a4212b5b01badba0d2236092b64a906a9eb4907dafbf6d8","observation_id":"628b48d0-ac1a-4c45-bc0e-84c85ef50d04","resolution":{"observed_at":"2026-08-07T14:28:16.110697Z","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":"2026-08-07T14:28:18.196667Z","title":"Neural network acceptability judgments.Trans","venue":null,"work_id":"c1fe32e1-9eac-40d9-aa6d-bc8743eabf88","year":2019},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:16.118034Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:edc6d2c9f9f89583e9f4cd58ac86f7e885fff12186f2577a51daad8b7df66252","observation_id":"f97d534e-53ec-471c-963c-9dd0a3d301ba","resolution":{"observed_at":"2026-08-07T14:28:18.253990Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:18.001377Z","title":"A broad-coverage challenge corpus for sentence understanding through inference","venue":null,"work_id":"513e2cde-093f-4b39-82b8-6843d8f0e475","year":2018},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:16.127508Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:2c5274518076ce7379c49c0e86a24c59f42483f1678b17a7893c53728e4c6034","observation_id":"4e1d806c-b054-48fd-87ce-98bb164de3d8","resolution":{"observed_at":"2026-08-07T14:28:18.032194Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:17.782273Z","title":"Reft: Representation finetuning for language models","venue":null,"work_id":"2a71fb05-93d3-48e0-814b-a4d4527e49cf","year":2024},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:16.139194Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:dc1cdac955d7b4ed017332c16a47e2144adba31e1a09d0fa4a65aa15d2d07540","observation_id":"57c49d2a-c882-42fc-88a6-d524e00ddc16","resolution":{"observed_at":"2026-08-07T14:28:17.885492Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:17.649462Z","title":"DoRA: Weight-decomposed low-rank adaptation","venue":null,"work_id":"32a4a46c-04f7-4f6e-96cd-e331ee8066c8","year":2024},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:16.147141Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:6b0e55d8c1da7c3ab36034089c43fbb43338fbcd837f36453598ca245e4b1950","observation_id":"f0229c86-8f6b-4deb-8833-32743bb8c0f8","resolution":{"observed_at":"2026-08-07T14:28:17.715773Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:17.472025Z","title":"Navigating text-to-image customization: From LyCORIS fine-tuning to model evaluation","venue":null,"work_id":"1ca6d664-2cc1-4141-a64e-f78eccbf5300","year":2024},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:16.156594Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:3fe97c843ed27f5bceb1f6454873068ee5a09f7987935e4a9163ae2620e4a9f6","observation_id":"95dee3c0-d29b-4039-8d41-e50f4d501659","resolution":{"observed_at":"2026-08-07T14:28:17.552027Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:16.165945Z","title":"LoRA done RITE: Robust invariant transformation equilibration for loRA optimization","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:16.165945Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:cee0711112e04236bffb692941dacb09dd0aec0afb788d7295003060f4dc5c55","observation_id":"dabc406a-828c-432f-ad3f-815560b0e73a","resolution":{"observed_at":"2026-08-07T14:28:16.165945Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1905.07830","last_updated":"2019-05-19T23:57:23Z","snapshot_observed_at":"2026-08-10T16:18:23.994244Z","submitted_at":"2019-05-19T23:57:23Z","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.07830","snapshot_observed_at":"2026-08-07T14:28:16.172157Z","title":"Hellaswag: Can a machine really finish your sentence?arXiv:1905.07830, 2019","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:16.172157Z"},"links":{"cited_paper":"/paper/1905.07830","citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:4dcebc2361f1e3a093fe0eac14d6777c1be33ff683bbe7ff78e750dc35b550c8","observation_id":"3bb47905-49dc-4ba2-b6e4-6c530a36562a","resolution":{"observed_at":"2026-08-07T14:28:16.172157Z","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":"2026-08-07T14:28:17.245969Z","title":"Riemannian preconditioned LoRA for fine-tuning foundation models","venue":null,"work_id":"bc4cefb3-6c5c-43ee-aff5-113644b41d7c","year":2024},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:16.186056Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:4d38fae41fa89eb6d6ec50afbe758043a7938cdd2bee807f47f61d36390b0bbb","observation_id":"9059868f-1951-4555-a7ac-48e31abff9bb","resolution":{"observed_at":"2026-08-07T14:28:17.358479Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:17.087811Z","title":"Limitations","venue":null,"work_id":"4437be48-c664-4f98-91c7-d239eabbd036","year":2023},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:16.205098Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:d8bc685d6d2200d165420f869ee5da048dc06527b426ea750c6baaa31bf935fa","observation_id":"689cc362-a8f6-4c9e-b460-78bfc93e1b1b","resolution":{"observed_at":"2026-08-07T14:28:17.144327Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T14:28:16.887694Z","title":"Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects","venue":null,"work_id":"edcb72c7-c776-49c4-8a52-6591bf9a1956","year":2025},"citing_paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","version":4},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:16.230983Z"},"links":{"citing_paper":"/paper/2505.18877"},"observation_digest":"sha256:7491f9b749abbfb58d07c867f5f908deedaa10df99923b187a43db5d7457a77f","observation_id":"89ed4b99-1755-4c21-b8e0-3097e0a1bd48","resolution":{"observed_at":"2026-08-07T14:28:16.944188Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.18877","last_updated":"2026-05-29T23:09:57Z","latest_version":4,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T17:15:55.413490Z","submitted_at":"2025-05-24T21:33:16Z","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models"},"reference_resolution":{"displayed":71,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":32,"verified_exact":0,"verified_fuzzy":38},"total_outbound_references":71},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 71 of 71 outbound references and 0 inbound Pith citation observations for arXiv:2505.18877."}