{"as_of":"2026-08-22T21:00:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3c6e6fbed88a3ffa226733ac26dae44a39db40487a9aefdf834aa0060df3ba73","coverage":[{"denominator":26,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":26,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T20:36:34.214216Z","state":"measured"},{"denominator":27,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":27,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T17:33:16.699502Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-05T17:33:17.721401Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.12579","last_updated":"2025-05-18T23:45:50Z","snapshot_observed_at":"2026-08-18T00:26:24.225628Z","submitted_at":"2025-05-18T23:45:50Z","title":"Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection","version":1},"cited_work":{"arxiv_id":"2505.12579","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.12579","snapshot_observed_at":"2026-08-05T17:33:17.721401Z","title":"Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection","venue":"cs.LG","work_id":"efda116c-2a00-46a9-87cb-013f9888d0a7","year":2025},"citing_paper":{"arxiv_id":"2508.16191","last_updated":"2025-08-22T08:12:06Z","snapshot_observed_at":"2026-08-21T16:37:30.257226Z","submitted_at":"2025-08-22T08:12:06Z","title":"GEM: A Scale-Aware and Distribution-Sensitive Sparse Fine-Tuning Framework for Effective Downstream Adaptation","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-05T17:33:16.699502Z"},"links":{"cited_paper":"/paper/2505.12579","citing_paper":"/paper/2508.16191"},"observation_digest":"sha256:941082b6ca5c24e366fea95581a524c82d34ac8f19fdd2d57216b646dbf9288c","observation_id":"84caad95-cdb8-415f-8e38-f0b3af41e05c","resolution":{"observed_at":"2026-08-05T17:33:17.784963Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2505.12579/citation-record","integrity":"/paper/2505.12579/integrity","json":"/paper/2505.12579/citation-record.json","paper":"/paper/2505.12579"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:36:34.521204Z","title":"LoRA learns less and forgets less.Transactions on Machine Learning Research, 2024","venue":null,"work_id":"55ede184-4290-42b6-87c5-898b3c9cadcc","year":2024},"citing_paper":{"arxiv_id":"2505.12579","last_updated":"2025-05-18T23:45:50Z","snapshot_observed_at":"2026-08-18T00:26:24.225628Z","submitted_at":"2025-05-18T23:45:50Z","title":"Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T20:36:34.109454Z"},"links":{"citing_paper":"/paper/2505.12579"},"observation_digest":"sha256:bb00036140144cd4a931dcae4561e1bdf1adb1843bea008e77bda87a4cdd9bcb","observation_id":"c54287d4-22ae-47fc-80e4-ae8fb27c7daf","resolution":{"observed_at":"2026-08-15T20:36:34.525219Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T20:36:34.509218Z","title":"Gradient descent with generalized newton’s method","venue":null,"work_id":"962db19c-6327-495d-bfea-d5525f72a14c","year":2024},"citing_paper":{"arxiv_id":"2505.12579","last_updated":"2025-05-18T23:45:50Z","snapshot_observed_at":"2026-08-18T00:26:24.225628Z","submitted_at":"2025-05-18T23:45:50Z","title":"Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T20:36:34.114191Z"},"links":{"citing_paper":"/paper/2505.12579"},"observation_digest":"sha256:34ad373c114b9e38ed16aef1c06d2ce52b8c19427ec0e28fe9a6aaa3395ed43a","observation_id":"713e2af5-ccf4-4eed-8ef0-fb7baaa33621","resolution":{"observed_at":"2026-08-15T20:36:34.513327Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T20:36:34.118166Z","title":"Parameter-efficient fine-tuning of large-scale pre-trained language models.Nature Machine Intelligence, 5(3):220–235, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.12579","last_updated":"2025-05-18T23:45:50Z","snapshot_observed_at":"2026-08-18T00:26:24.225628Z","submitted_at":"2025-05-18T23:45:50Z","title":"Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T20:36:34.118166Z"},"links":{"citing_paper":"/paper/2505.12579"},"observation_digest":"sha256:49619dbd94f9029c9d5312097da85a1d1114088aa87b517b1286a0a451279a1d","observation_id":"ce01dedd-f898-4c9e-8720-5699dc1f97d8","resolution":{"observed_at":"2026-08-15T20:36:34.118166Z","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":"2026-08-15T20:36:34.122182Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.12579","last_updated":"2025-05-18T23:45:50Z","snapshot_observed_at":"2026-08-18T00:26:24.225628Z","submitted_at":"2025-05-18T23:45:50Z","title":"Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T20:36:34.122182Z"},"links":{"citing_paper":"/paper/2505.12579"},"observation_digest":"sha256:8d9a91aa8fce98eff65a4aa07942eb4868052fef34f2c4f72b786a4f92bde7dd","observation_id":"f48f15d5-a9be-4cb9-88f4-bc73a97020c2","resolution":{"observed_at":"2026-08-15T20:36:34.122182Z","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":"2026-08-15T20:36:34.481545Z","title":"Qlabgrad: A hyperparameter-free and convergence- guaranteed scheme for deep learning","venue":null,"work_id":"fab4438b-2409-4b09-ad6e-fd76819b94e0","year":2024},"citing_paper":{"arxiv_id":"2505.12579","last_updated":"2025-05-18T23:45:50Z","snapshot_observed_at":"2026-08-18T00:26:24.225628Z","submitted_at":"2025-05-18T23:45:50Z","title":"Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T20:36:34.126730Z"},"links":{"citing_paper":"/paper/2505.12579"},"observation_digest":"sha256:ba6d03ad3820522e4a523bc8220b790d7f05b60b09a8341a18f67b134ccb4a10","observation_id":"f2bb6a7b-a7de-46a1-8683-73075b55fdb9","resolution":{"observed_at":"2026-08-15T20:36:34.485782Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.14608","last_updated":"2024-09-16T02:54:50Z","snapshot_observed_at":"2026-08-04T09:07:42.158421Z","submitted_at":"2024-03-21T17:55:50Z","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.14608","snapshot_observed_at":"2026-08-15T20:36:34.130806Z","title":"Parameter-efficient fine-tuning for large models: A comprehensive survey.arXiv preprint arXiv:2403.14608, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.12579","last_updated":"2025-05-18T23:45:50Z","snapshot_observed_at":"2026-08-18T00:26:24.225628Z","submitted_at":"2025-05-18T23:45:50Z","title":"Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T20:36:34.130806Z"},"links":{"cited_paper":"/paper/2403.14608","citing_paper":"/paper/2505.12579"},"observation_digest":"sha256:ce23a08e2dc9461b858661a4352e7b88ccfae56c68aaadf3c54abdf1da066c54","observation_id":"a161f71f-8a80-4dfb-b1d4-f6909c40a2fd","resolution":{"observed_at":"2026-08-15T20:36:34.130806Z","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":"2026-08-15T20:36:34.135540Z","title":"Parameter-efficient transfer learning for nlp","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.12579","last_updated":"2025-05-18T23:45:50Z","snapshot_observed_at":"2026-08-18T00:26:24.225628Z","submitted_at":"2025-05-18T23:45:50Z","title":"Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T20:36:34.135540Z"},"links":{"citing_paper":"/paper/2505.12579"},"observation_digest":"sha256:afda6efb26c45f25324914a4bbb6b343dd0618196c2b2f10878d5a757cdda91b","observation_id":"d5d832a5-1b16-4346-ae10-2993af35d739","resolution":{"observed_at":"2026-08-15T20:36:34.135540Z","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":"2026-08-15T20:36:34.139469Z","title":"LoRA: Low-rank adaptation of large language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.12579","last_updated":"2025-05-18T23:45:50Z","snapshot_observed_at":"2026-08-18T00:26:24.225628Z","submitted_at":"2025-05-18T23:45:50Z","title":"Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T20:36:34.139469Z"},"links":{"citing_paper":"/paper/2505.12579"},"observation_digest":"sha256:c512f8b1590502e7bc19894a86f2196ec4eeddbeb65c6c07d838cdf5215fcdb1","observation_id":"a026ee47-17c8-48c1-bad6-6f72b655d85a","resolution":{"observed_at":"2026-08-15T20:36:34.139469Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.08691","last_updated":"2021-09-02T17:34:41Z","snapshot_observed_at":"2026-08-16T20:01:36.160048Z","submitted_at":"2021-04-18T03:19:26Z","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.08691","snapshot_observed_at":"2026-08-15T20:36:34.143120Z","title":"The power of scale for parameter-efficient prompt tuning.arXiv preprint arXiv:2104.08691, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.12579","last_updated":"2025-05-18T23:45:50Z","snapshot_observed_at":"2026-08-18T00:26:24.225628Z","submitted_at":"2025-05-18T23:45:50Z","title":"Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T20:36:34.143120Z"},"links":{"cited_paper":"/paper/2104.08691","citing_paper":"/paper/2505.12579"},"observation_digest":"sha256:6f98153abedadb1fcf4b8db148b5a8917021c1a4955bce354abe03d21588f58e","observation_id":"c1fe831e-6a30-4668-a656-fb49a6678ee9","resolution":{"observed_at":"2026-08-15T20:36:34.143120Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.00190","last_updated":"2021-01-01T08:00:36Z","snapshot_observed_at":"2026-08-21T16:24:51.670091Z","submitted_at":"2021-01-01T08:00:36Z","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.00190","snapshot_observed_at":"2026-08-15T20:36:34.147162Z","title":"Prefix-tuning: Optimizing continuous prompts for generation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.12579","last_updated":"2025-05-18T23:45:50Z","snapshot_observed_at":"2026-08-18T00:26:24.225628Z","submitted_at":"2025-05-18T23:45:50Z","title":"Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T20:36:34.147162Z"},"links":{"cited_paper":"/paper/2101.00190","citing_paper":"/paper/2505.12579"},"observation_digest":"sha256:1fe78f9c05c8ef800111f9fa78c2a9add4650b7f91674dad0e4a567a68360edd","observation_id":"ef512fdd-50d4-4546-80e3-0ba0cf51c064","resolution":{"observed_at":"2026-08-15T20:36:34.147162Z","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":"2026-08-15T20:36:34.455336Z","title":"Loftq: Lora-fine-tuning-aware quantization for large language models","venue":null,"work_id":"e484385d-66f7-4f69-9975-c12a942d5fc7","year":2024},"citing_paper":{"arxiv_id":"2505.12579","last_updated":"2025-05-18T23:45:50Z","snapshot_observed_at":"2026-08-18T00:26:24.225628Z","submitted_at":"2025-05-18T23:45:50Z","title":"Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T20:36:34.151582Z"},"links":{"citing_paper":"/paper/2505.12579"},"observation_digest":"sha256:c3d69d4c01ab1461fe41622906a06349e54732f3df10de1abab4ddfa06ae9577","observation_id":"9ed208a0-5dc5-4684-88c7-68ebf84151c0","resolution":{"observed_at":"2026-08-15T20:36:34.459271Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.07602","last_updated":"2022-03-20T15:13:08Z","snapshot_observed_at":"2026-08-18T04:49:12.041312Z","submitted_at":"2021-10-14T17:58:47Z","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.07602","snapshot_observed_at":"2026-08-15T20:36:34.155738Z","title":"P-tuning v2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.12579","last_updated":"2025-05-18T23:45:50Z","snapshot_observed_at":"2026-08-18T00:26:24.225628Z","submitted_at":"2025-05-18T23:45:50Z","title":"Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T20:36:34.155738Z"},"links":{"cited_paper":"/paper/2110.07602","citing_paper":"/paper/2505.12579"},"observation_digest":"sha256:2de85b0a4f3e9821a028da9709acd97046e5e7557b30595d6a4dce3c16d7fbb4","observation_id":"4195f6fa-a13b-463c-ab3e-8f0f7f23e8c3","resolution":{"observed_at":"2026-08-15T20:36:34.155738Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1907.11692","last_updated":"2019-07-26T17:48:29Z","snapshot_observed_at":"2026-08-16T14:33:50.657682Z","submitted_at":"2019-07-26T17:48:29Z","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.11692","snapshot_observed_at":"2026-08-15T20:36:34.160701Z","title":"Roberta: A robustly optimized bert pretraining approach.arXiv preprint arXiv:1907.11692, 2019","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2505.12579","last_updated":"2025-05-18T23:45:50Z","snapshot_observed_at":"2026-08-18T00:26:24.225628Z","submitted_at":"2025-05-18T23:45:50Z","title":"Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T20:36:34.160701Z"},"links":{"cited_paper":"/paper/1907.11692","citing_paper":"/paper/2505.12579"},"observation_digest":"sha256:b133c35004ad1457f3a84e7842a1388336cf7337f104e7a5d858f34bd0e6d803","observation_id":"407ea49a-db54-48be-96f0-d23cacf6eeeb","resolution":{"observed_at":"2026-08-15T20:36:34.160701Z","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":"2026-08-15T20:36:34.443254Z","title":"John Wiley & Sons, Inc., 1990","venue":null,"work_id":"21304b95-debc-48dd-933b-5290f16d70d1","year":1990},"citing_paper":{"arxiv_id":"2505.12579","last_updated":"2025-05-18T23:45:50Z","snapshot_observed_at":"2026-08-18T00:26:24.225628Z","submitted_at":"2025-05-18T23:45:50Z","title":"Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T20:36:34.164739Z"},"links":{"citing_paper":"/paper/2505.12579"},"observation_digest":"sha256:52c9ebfe35c6aa38c07ffe6a3ea9b2b7e81c9ce2ebc30a7df0d6e04a063b84e1","observation_id":"d5f7c353-e5d3-41a1-b9fd-fd33d8e659e5","resolution":{"observed_at":"2026-08-15T20:36:34.447156Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.14117","last_updated":"2025-04-19T00:33:16Z","snapshot_observed_at":"2026-08-20T16:10:58.025400Z","submitted_at":"2025-04-19T00:33:16Z","title":"PEFT A2Z: Parameter-Efficient Fine-Tuning Survey for Large Language and Vision Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.14117","snapshot_observed_at":"2026-08-15T20:36:34.168422Z","title":"Peft a2z: Parameter-efficient fine-tuning survey for large language and vision models.arXiv preprint arXiv:2504.14117, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.12579","last_updated":"2025-05-18T23:45:50Z","snapshot_observed_at":"2026-08-18T00:26:24.225628Z","submitted_at":"2025-05-18T23:45:50Z","title":"Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T20:36:34.168422Z"},"links":{"cited_paper":"/paper/2504.14117","citing_paper":"/paper/2505.12579"},"observation_digest":"sha256:51725a408310648fa43d7362b85a00e785f74e5043cc1d5d62f194212a2471dd","observation_id":"8c7a03cf-2649-47ee-ba7c-d1c89ec8c348","resolution":{"observed_at":"2026-08-15T20:36:34.168422Z","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":"2026-08-15T20:36:34.431208Z","title":"Language models are unsupervised multitask learners.OpenAI blog, 1(8):9, 2019","venue":null,"work_id":"08826e31-c6dd-4977-a1a0-121d9040307b","year":2019},"citing_paper":{"arxiv_id":"2505.12579","last_updated":"2025-05-18T23:45:50Z","snapshot_observed_at":"2026-08-18T00:26:24.225628Z","submitted_at":"2025-05-18T23:45:50Z","title":"Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T20:36:34.172707Z"},"links":{"citing_paper":"/paper/2505.12579"},"observation_digest":"sha256:17375ff95c3ebfbd4fba43c8cfbe7708f944c2892811b5aafcafcc75929622b0","observation_id":"3fe6340b-7969-4a46-b077-b33a985963c7","resolution":{"observed_at":"2026-08-15T20:36:34.435608Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T20:36:34.176778Z","title":"Exploring the limits of transfer learning with a unified text-to-text transformer.Journal of machine learning research, 21(140):1–67, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.12579","last_updated":"2025-05-18T23:45:50Z","snapshot_observed_at":"2026-08-18T00:26:24.225628Z","submitted_at":"2025-05-18T23:45:50Z","title":"Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T20:36:34.176778Z"},"links":{"citing_paper":"/paper/2505.12579"},"observation_digest":"sha256:fd12bb52cc2c7a176927f14da35679e6dd480eb43d0426a30472dca542e5813b","observation_id":"8fcf76bf-808a-4eef-aa3f-b37543a40485","resolution":{"observed_at":"2026-08-15T20:36:34.176778Z","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":"2026-08-15T20:36:34.411204Z","title":"Glue: A multi-task benchmark and analysis platform for natural language understanding","venue":null,"work_id":"2f8bd48c-5724-4e54-97db-748760381cd4","year":null},"citing_paper":{"arxiv_id":"2505.12579","last_updated":"2025-05-18T23:45:50Z","snapshot_observed_at":"2026-08-18T00:26:24.225628Z","submitted_at":"2025-05-18T23:45:50Z","title":"Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T20:36:34.180459Z"},"links":{"citing_paper":"/paper/2505.12579"},"observation_digest":"sha256:190f179ded2e490853d67dfc2c5297165ea21b3078009d9e6144cd53896e5a63","observation_id":"91ff8b46-8e29-4844-a450-d8f28d5cd555","resolution":{"observed_at":"2026-08-15T20:36:34.415412Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.19878","last_updated":"2025-04-24T07:20:31Z","snapshot_observed_at":"2026-08-16T13:06:16.410317Z","submitted_at":"2024-10-24T13:58:59Z","title":"Parameter-Efficient Fine-Tuning in Large Models: A Survey of Methodologies","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.19878","snapshot_observed_at":"2026-08-15T20:36:34.184530Z","title":"Parameter-efficient fine-tuning in large models: A survey of methodologies.arXiv preprint arXiv:2410.19878, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.12579","last_updated":"2025-05-18T23:45:50Z","snapshot_observed_at":"2026-08-18T00:26:24.225628Z","submitted_at":"2025-05-18T23:45:50Z","title":"Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T20:36:34.184530Z"},"links":{"cited_paper":"/paper/2410.19878","citing_paper":"/paper/2505.12579"},"observation_digest":"sha256:e029f4a707fdb7a06cdbd8b7a5c35b1e3d3e9c193f4c70bbddcb0bb19100ef5f","observation_id":"9af0e975-aa81-4ab8-a6fc-ec2db237a5c5","resolution":{"observed_at":"2026-08-15T20:36:34.184530Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.05000","last_updated":"2024-07-16T07:32:23Z","snapshot_observed_at":"2026-08-19T00:46:49.288994Z","submitted_at":"2024-07-06T08:37:21Z","title":"LoRA-GA: Low-Rank Adaptation with Gradient Approximation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.05000","snapshot_observed_at":"2026-08-15T20:36:34.188514Z","title":"Lora-ga: Low-rank adaptation with gradient approxima- tion.arXiv preprint arXiv:2407.05000, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.12579","last_updated":"2025-05-18T23:45:50Z","snapshot_observed_at":"2026-08-18T00:26:24.225628Z","submitted_at":"2025-05-18T23:45:50Z","title":"Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T20:36:34.188514Z"},"links":{"cited_paper":"/paper/2407.05000","citing_paper":"/paper/2505.12579"},"observation_digest":"sha256:be69b5ec3b8d746d25419ea2f494b143d981c027b3f1b7acd59bf51dc40a33dc","observation_id":"c4b83fbf-ac69-48b6-9a50-d12312979520","resolution":{"observed_at":"2026-08-15T20:36:34.188514Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.18242","last_updated":"2025-03-22T09:29:15Z","snapshot_observed_at":"2026-08-17T22:14:24.262905Z","submitted_at":"2024-07-25T17:57:12Z","title":"LoRA-Pro: Are Low-Rank Adapters Properly Optimized?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.18242","snapshot_observed_at":"2026-08-15T20:36:34.192860Z","title":"Lora-pro: Are low-rank adapters properly optimized?arXiv preprint arXiv:2407.18242, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.12579","last_updated":"2025-05-18T23:45:50Z","snapshot_observed_at":"2026-08-18T00:26:24.225628Z","submitted_at":"2025-05-18T23:45:50Z","title":"Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T20:36:34.192860Z"},"links":{"cited_paper":"/paper/2407.18242","citing_paper":"/paper/2505.12579"},"observation_digest":"sha256:dd37c8d00546fc69b6e2094906b3ee83bd1d944e281a690bf0d644e027b1cf98","observation_id":"d87e9c0a-b9de-4664-8b6f-46ce4d0da853","resolution":{"observed_at":"2026-08-15T20:36:34.192860Z","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":"2026-08-15T20:36:34.197975Z","title":"Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked language-models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.12579","last_updated":"2025-05-18T23:45:50Z","snapshot_observed_at":"2026-08-18T00:26:24.225628Z","submitted_at":"2025-05-18T23:45:50Z","title":"Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T20:36:34.197975Z"},"links":{"citing_paper":"/paper/2505.12579"},"observation_digest":"sha256:016706a97ff19ab9314dfc0332b8953b7c467c9862ee1df8a5a86dfc59fccf11","observation_id":"5b43b26c-287c-4797-b48c-4fb606546192","resolution":{"observed_at":"2026-08-15T20:36:34.197975Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03303","last_updated":"2026-05-09T05:30:15Z","snapshot_observed_at":"2026-08-13T08:01:16.750424Z","submitted_at":"2023-08-07T05:12:27Z","title":"LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03303","snapshot_observed_at":"2026-08-15T20:36:34.201947Z","title":"Lora-fa: Memory-efficient low-rank adaptation for large language models fine-tuning.arXiv preprint arXiv:2308.03303, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.12579","last_updated":"2025-05-18T23:45:50Z","snapshot_observed_at":"2026-08-18T00:26:24.225628Z","submitted_at":"2025-05-18T23:45:50Z","title":"Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T20:36:34.201947Z"},"links":{"cited_paper":"/paper/2308.03303","citing_paper":"/paper/2505.12579"},"observation_digest":"sha256:6fd0bba10cfedf5333b19f0faed1ddba51ca16d39f45552d3810231acac567ae","observation_id":"c4b0f433-b863-4f32-8c68-58cb5947cf13","resolution":{"observed_at":"2026-08-15T20:36:34.201947Z","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":"2026-08-15T20:36:34.390521Z","title":"Tuning layernorm in attention: Towards efficient multi-modal llm finetuning","venue":null,"work_id":"f5d87b2d-3ddd-4db5-afe7-0434dc00cda5","year":null},"citing_paper":{"arxiv_id":"2505.12579","last_updated":"2025-05-18T23:45:50Z","snapshot_observed_at":"2026-08-18T00:26:24.225628Z","submitted_at":"2025-05-18T23:45:50Z","title":"Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T20:36:34.206016Z"},"links":{"citing_paper":"/paper/2505.12579"},"observation_digest":"sha256:47583d4d4012cba7f50512138f3a77845a4c5209c22ddb7e1d39c5d3624b92af","observation_id":"a6c6fd8d-04a5-4688-b7ea-57896c2f2de3","resolution":{"observed_at":"2026-08-15T20:36:34.395076Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1709.00103","last_updated":"2017-11-09T23:06:14Z","snapshot_observed_at":"2026-08-16T12:20:26.377960Z","submitted_at":"2017-08-31T23:12:15Z","title":"Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1709.00103","snapshot_observed_at":"2026-08-15T20:36:34.210188Z","title":"Seq2sql: Generating structured queries from natural language using reinforcement learning.CoRR, abs/1709.00103, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.12579","last_updated":"2025-05-18T23:45:50Z","snapshot_observed_at":"2026-08-18T00:26:24.225628Z","submitted_at":"2025-05-18T23:45:50Z","title":"Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T20:36:34.210188Z"},"links":{"cited_paper":"/paper/1709.00103","citing_paper":"/paper/2505.12579"},"observation_digest":"sha256:356e10d1e6e67adddf737ffb5aa48f76c482730dc0bf15a5e375e0235a9c14b8","observation_id":"d30ad096-ba92-4151-92b7-f53511436fac","resolution":{"observed_at":"2026-08-15T20:36:34.210188Z","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":"2026-08-15T20:36:34.376934Z","title":"Automatic, dynamic, and nearly optimal learning rate specification via local quadratic approximation.Neural Networks, 141:11–29, 2021","venue":null,"work_id":"80c5a347-bee8-481a-8dcc-c78a4d00d473","year":2021},"citing_paper":{"arxiv_id":"2505.12579","last_updated":"2025-05-18T23:45:50Z","snapshot_observed_at":"2026-08-18T00:26:24.225628Z","submitted_at":"2025-05-18T23:45:50Z","title":"Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T20:36:34.214216Z"},"links":{"citing_paper":"/paper/2505.12579"},"observation_digest":"sha256:f4dcd220ccf34d1acc1c933a806a5d4782fb723a7dcbff1b905e2059298ff834","observation_id":"72f9e60e-3fd2-41f7-9356-169a4dca29bb","resolution":{"observed_at":"2026-08-15T20:36:34.382342Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.12579","last_updated":"2025-05-18T23:45:50Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-18T00:26:24.225628Z","submitted_at":"2025-05-18T23:45:50Z","title":"Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection"},"reference_resolution":{"displayed":26,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":17,"verified_exact":0,"verified_fuzzy":9},"total_outbound_references":26},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 1 inbound Pith citation observation for arXiv:2505.12579."}