{"as_of":"2026-08-09T19:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0ea0cc26bba9fe6a8c9e8631d0033be7a7654680f3de82cf6b5805410d078a3b","coverage":[{"denominator":75,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":75,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:15:55.842329Z","state":"measured"},{"denominator":77,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":77,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-21T05:59:59.183023Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-21T06:03:59.420139Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"cited_work":{"arxiv_id":"2505.22355","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.22355","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Look within or look beyond? a theoretical comparison between parameter- efficient and full fine-tuning","venue":null,"work_id":"d26ce9c5-e728-435f-8977-fe05f9e38b36","year":2025},"citing_paper":{"arxiv_id":"2605.21147","last_updated":"2026-05-20T13:19:28Z","snapshot_observed_at":"2026-07-06T23:31:37.061253Z","submitted_at":"2026-05-20T13:19:28Z","title":"SMoA: Spectrum Modulation Adapter for Parameter-Efficient Fine-Tuning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-21T05:59:59.183023Z"},"links":{"cited_paper":"/paper/2505.22355","citing_paper":"/paper/2605.21147"},"observation_digest":"sha256:ca55a89fcff76a2a047444c425abad2413a96f80a17371ff7e49deccbe7b80c7","observation_id":"1f192a19-ffbd-4c23-b1f0-3c54320dfc57","resolution":{"observed_at":"2026-05-21T06:03:59.421593Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"cited_work":{"arxiv_id":"2505.22355","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.22355","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Look within or look beyond? a theoretical comparison between parameter- efficient and full fine-tuning","venue":null,"work_id":"d26ce9c5-e728-435f-8977-fe05f9e38b36","year":2025},"citing_paper":{"arxiv_id":"2605.21177","last_updated":"2026-05-20T13:44:44Z","snapshot_observed_at":"2026-07-06T23:31:41.930458Z","submitted_at":"2026-05-20T13:44:44Z","title":"ChunkFT: Byte-Streamed Optimization for Memory-Efficient Full Fine-Tuning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-21T05:46:08.709560Z"},"links":{"cited_paper":"/paper/2505.22355","citing_paper":"/paper/2605.21177"},"observation_digest":"sha256:93a02812557e110da018915ba85c01bdb6b20fe375ab7452079c77caa8399938","observation_id":"fc37002a-ba2f-4591-a0a7-15231d2b08c6","resolution":{"observed_at":"2026-05-21T05:49:41.053697Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2505.22355/citation-record","integrity":"/paper/2505.22355/integrity","json":"/paper/2505.22355/citation-record.json","paper":"/paper/2505.22355"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:16:03.717552Z","title":"Composable sparse fine-tuning for cross-lingual transfer","venue":null,"work_id":"1ec9e5a5-473b-483a-813e-12c6d4396b3b","year":2022},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:36.521221Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:6bf2586b88417e2bc5c576198ce54c0278d5ec10a40e7cc8d49c4d608a6fc54e","observation_id":"12f79f23-09ae-4692-aa1b-6486511d8153","resolution":{"observed_at":"2026-08-07T13:16:03.836514Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:16:03.501162Z","title":"Fine-Tuning LLMs: LoRA or Full-Parameter? An in-depth Analysis with Llama-2","venue":null,"work_id":"f83fefde-31c3-49ce-bb15-87fc8bacb85f","year":2023},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:36.582348Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:e04c2c3144ee921e31343ab927493c08a75fa5c4cd286a8d66672017b5f59c9e","observation_id":"dcb45d7c-daf6-460e-93e4-4de3b160d0fa","resolution":{"observed_at":"2026-08-07T13:16:03.609223Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:16:03.235090Z","title":"Machine learning theory","venue":null,"work_id":"fc6d3dd6-9869-43bf-abdb-19d0c5e699b2","year":2007},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:36.759818Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:7ef5bf8adca0dcf8e5ec67da76919bb50437e2c91341a36095e25321ddb03fca","observation_id":"c5289ade-3c36-4247-820a-1ef255278aa5","resolution":{"observed_at":"2026-08-07T13:16:03.345191Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:16:02.957535Z","title":"Attention fusion: a light yet efficient late fusion mechanism for task adaptation in nlu","venue":null,"work_id":"5e2d03d2-fe17-472a-8914-0a034795e0eb","year":2022},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:36.874038Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:60522fdc17ccb58653dbe272d592530789492848453feb8499771307f975967e","observation_id":"d4987e2d-c24d-4d54-995e-2c4227742f20","resolution":{"observed_at":"2026-08-07T13:16:03.097240Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:15:37.049804Z","title":"SemEval- 2019 task 3: EmoContext contextual emotion detection in text","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:37.049804Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:0f3427c63b09d23d599dbae1c117f6cc703b271d95ad247431ed3577b0505ec7","observation_id":"687c27bb-9ecd-447f-bbda-e96fc3c40e7e","resolution":{"observed_at":"2026-08-07T13:15:37.049804Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.01821","last_updated":"2023-01-04T21:00:18Z","snapshot_observed_at":"2026-07-06T14:37:32.503892Z","submitted_at":"2023-01-04T21:00:18Z","title":"Parameter-Efficient Fine-Tuning Design Spaces","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.01821","snapshot_observed_at":"2026-08-07T13:15:37.186380Z","title":"Parameter-efficient fine-tuning design spaces","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:37.186380Z"},"links":{"cited_paper":"/paper/2301.01821","citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:97376538e5f46464047d03b28c0d77f64f79f946fc56a263a0a447e44f61a8b3","observation_id":"90353056-37e9-477a-9947-833d833a3134","resolution":{"observed_at":"2026-08-07T13:15:37.186380Z","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":"2026-08-07T13:15:37.363511Z","title":"Gonzalez, Ion Stoica, and Eric P","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:37.363511Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:eb12123e414a2863af60d0c293525efa8097bca2ea99bd164a44a34fe5dea343","observation_id":"cbe02d9e-607d-4414-b9b6-9e8b69548659","resolution":{"observed_at":"2026-08-07T13:15:37.363511Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.14168","last_updated":"2021-11-18T00:23:45Z","snapshot_observed_at":"2026-08-07T01:45:38.840969Z","submitted_at":"2021-10-27T04:49:45Z","title":"Training Verifiers to Solve Math Word Problems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.14168","snapshot_observed_at":"2026-08-07T13:15:37.522359Z","title":"Training verifiers to solve math word problems","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:37.522359Z"},"links":{"cited_paper":"/paper/2110.14168","citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:c2a7641c2de720104a1f20c92de5e1defb6790f1c5ac8e62b6073f2b007b1d14","observation_id":"34a45761-fbcd-4bfa-8015-0a75e6451adc","resolution":{"observed_at":"2026-08-07T13:15:37.522359Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.02355","last_updated":"2021-09-06T10:48:40Z","snapshot_observed_at":"2026-07-06T11:44:36.471158Z","submitted_at":"2021-09-06T10:48:40Z","title":"A Farewell to the Bias-Variance Tradeoff? An Overview of the Theory of Overparameterized Machine Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.02355","snapshot_observed_at":"2026-08-07T13:15:37.660314Z","title":"A farewell to the bias-variance tradeoff? an overview of the theory of overparameterized machine learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:37.660314Z"},"links":{"cited_paper":"/paper/2109.02355","citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:e2fb5114f6f8544b26feadbf37c71cb9b9e8843351a17d464acef5f1c99d02f5","observation_id":"1377627b-25c8-402b-a37b-5835adf133fa","resolution":{"observed_at":"2026-08-07T13:15:37.660314Z","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":"2026-08-07T13:16:02.648248Z","title":"Identifying and attacking the saddle point problem in high-dimensional non- convex optimization","venue":null,"work_id":"ffcc3430-be18-4f24-8a4b-16a716b24b9e","year":2014},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:37.762392Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:78d18bfd4f3589570ef8e856c2e200d0b9b167a2967b1d16734215f5a2a77438","observation_id":"419ee7b2-7da3-4f03-9b56-e536371315c7","resolution":{"observed_at":"2026-08-07T13:16:02.761982Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:16:02.466046Z","title":"Parameter- efficient fine-tuning of large-scale pre-trained language models","venue":null,"work_id":"9d931c85-a102-4c4f-b31b-a76b1c219f98","year":2023},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:37.881514Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:bd672060bfddbe8bc420ad5434862b8407e898ff7587da33b27633803f9d571a","observation_id":"26a3b6a5-a3d4-4ad5-aad4-2dea01183bb1","resolution":{"observed_at":"2026-08-07T13:16:02.567927Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.10650","last_updated":"2022-12-20T20:56:52Z","snapshot_observed_at":"2026-08-09T04:51:56.558555Z","submitted_at":"2022-12-20T20:56:52Z","title":"KronA: Parameter Efficient Tuning with Kronecker Adapter","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.10650","snapshot_observed_at":"2026-08-07T13:15:38.030936Z","title":"Krona: Parameter efficient tuning with kronecker adapter","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:38.030936Z"},"links":{"cited_paper":"/paper/2212.10650","citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:51863a71e692c1a51f53a64d98c3538190bc3edbbd622536609dcc09a35b2af6","observation_id":"2eac4ad3-6e2f-45f4-8d24-bd325366bb7e","resolution":{"observed_at":"2026-08-07T13:15:38.030936Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.06072","last_updated":"2022-06-13T12:03:32Z","snapshot_observed_at":"2026-08-07T04:49:45.715668Z","submitted_at":"2022-06-13T12:03:32Z","title":"Rank Diminishing in Deep Neural Networks","version":1},"cited_work":{"arxiv_id":"2206.06072","doi":null,"metadata_source":"pith","pith_arxiv_id":"2206.06072","snapshot_observed_at":"2026-08-07T13:15:56.435188Z","title":"Rank Diminishing in Deep Neural Networks","venue":"cs.LG","work_id":"c2682d27-f91e-4e16-91b7-3d5754aa8089","year":2022},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:38.199860Z"},"links":{"cited_paper":"/paper/2206.06072","citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:e91f24157dbf881a6e58b6660dd0c7d3dc2d9a9cd619fb99e9ee2ce0d895cf1a","observation_id":"2b2d3dba-fd6c-4996-a2d2-25bacaa1d1ac","resolution":{"observed_at":"2026-08-07T13:15:56.506053Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.01412","last_updated":"2021-04-29T16:44:25Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-10-03T19:02:10Z","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.01412","snapshot_observed_at":"2026-08-07T13:15:38.318455Z","title":"Sharpness-aware min- imization for efficiently improving generalization","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:38.318455Z"},"links":{"cited_paper":"/paper/2010.01412","citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:15fe8efca6acb6f43ec3d0c7733c3f75badaa1437d57de2c55eab047753ae2ae","observation_id":"b98447e0-0554-4cc8-80ae-58f44909fd43","resolution":{"observed_at":"2026-08-07T13:15:38.318455Z","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":"2026-08-07T13:16:02.190792Z","title":"Robustness gym: Unifying the NLP evaluation landscape","venue":null,"work_id":"9cf9bc7a-182d-4cb2-90d5-4c0d6c0d740f","year":2021},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:38.441936Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:7708beedb8c44b7a9d0c39467af6778cff76636871e4ceb860ffdb43b85a6c9b","observation_id":"87e43c74-1627-436e-9071-1bfbe63c44aa","resolution":{"observed_at":"2026-08-07T13:16:02.295718Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:16:01.903388Z","title":"A survey of adversarial defenses and robustness in nlp","venue":null,"work_id":"d259fb1f-397b-4369-9401-bc2f605d9623","year":2023},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:38.574186Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:669d3c1cb9ff2af929e10d77fe3908df248c71fe4b68d2357e88659bf6b5d8af","observation_id":"6aab1f42-997c-408b-a688-50fde9c37782","resolution":{"observed_at":"2026-08-07T13:16:02.019454Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"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":"2026-08-07T13:15:38.680064Z","title":"Parameter-efficient fine-tuning for large models: A comprehensive survey","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:38.680064Z"},"links":{"cited_paper":"/paper/2403.14608","citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:c7f40dd7d26281eec5417f5caae7c52d221f598edea91d6e076926bd8b57e52e","observation_id":"33125f48-a545-46ff-b590-3471570c0df3","resolution":{"observed_at":"2026-08-07T13:15:38.680064Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.16775","last_updated":"2024-11-25T07:06:09Z","snapshot_observed_at":"2026-08-07T07:32:41.663598Z","submitted_at":"2024-11-25T07:06:09Z","title":"Parameter Efficient Instruction Tuning: An Empirical Study","version":1},"cited_work":{"arxiv_id":"2411.16775","doi":null,"metadata_source":"pith","pith_arxiv_id":"2411.16775","snapshot_observed_at":"2026-08-07T13:15:56.243618Z","title":"Parameter Efficient Instruction Tuning: An Empirical Study","venue":"cs.CL","work_id":"78ceb928-6ad5-4a23-88b1-7ebaf169476a","year":2024},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:38.811243Z"},"links":{"cited_paper":"/paper/2411.16775","citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:dfd8198ba4e62961d693e0c16c9bc1958a57f2e84bad7bbdbe814cae40f3218f","observation_id":"1452da4b-d04b-4518-be58-6dcca4a6595d","resolution":{"observed_at":"2026-08-07T13:15:56.316577Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:15:38.927860Z","title":"Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:38.927860Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:d3acd69f3d45af2a70a8366f313e05296291b24a2ca97658be9f3d5d522b140d","observation_id":"18d56fac-2f96-464b-9b00-0cd59fa76ad6","resolution":{"observed_at":"2026-08-07T13:15:38.927860Z","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":"2026-08-07T13:16:01.717657Z","title":"Llm-adapters: An adapter family for parameter-efficient fine- tuning of large language models","venue":null,"work_id":"10d43660-6e1c-4cfb-8c7e-0a2baeeb20dd","year":2023},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:39.181520Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:04cb5b87ce94f2f52ace95bb3bf3240e39a0f3366bb1b2678c25f609bd1060c4","observation_id":"5033d86d-2885-44d6-b57f-1e07d368427b","resolution":{"observed_at":"2026-08-07T13:16:01.805125Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:16:01.547729Z","title":"Hira: Parameter-efficient hadamard high-rank adaptation for large language models","venue":null,"work_id":"54005912-a87c-4774-b785-3e87ad075f6e","year":2025},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:39.291715Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:82ad033bf306c3bec4d611d2843d9a03ab5c3bbbe5511f0295967e0479b590f3","observation_id":"0452cebd-4809-4724-8a9f-5af721ab6b57","resolution":{"observed_at":"2026-08-07T13:16:01.621151Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:16:01.224483Z","title":"Adversarial examples for evaluating reading comprehension systems","venue":null,"work_id":"7b031c17-d388-467a-a0e3-6ee0b4dda8da","year":2017},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:39.405947Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:d5cf5ee7863da82477579bc85ef14a76d10e4c1c151ebe6b9b56eb0be4017c5b","observation_id":"8bbbc91b-d652-4aa9-9404-0388fd60c4d2","resolution":{"observed_at":"2026-08-07T13:16:01.366464Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1707.07328","last_updated":"2017-07-23T18:26:29Z","snapshot_observed_at":"2026-07-06T05:52:19.613514Z","submitted_at":"2017-07-23T18:26:29Z","title":"Adversarial Examples for Evaluating Reading Comprehension Systems","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1707.07328","snapshot_observed_at":"2026-08-07T13:15:39.516491Z","title":"Adversarial examples for evaluating reading comprehension systems","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:39.516491Z"},"links":{"cited_paper":"/paper/1707.07328","citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:171f7ca3442a97a7bf006803c35eb760e495d54ea9f667cd8fc0226008d2ec5b","observation_id":"58551801-1c41-410b-abb7-38034034acbc","resolution":{"observed_at":"2026-08-07T13:15:39.516491Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06825","last_updated":"2023-10-10T17:54:58Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-10-10T17:54:58Z","title":"Mistral 7B","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06825","snapshot_observed_at":"2026-08-07T13:15:39.689990Z","title":"Mistral 7b","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:39.689990Z"},"links":{"cited_paper":"/paper/2310.06825","citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:386b9615f5c232417e8563fa5626e7ef464868c40769930d98058f756ce50d7c","observation_id":"bd2c7bce-fac4-40ca-9130-b50717598f5a","resolution":{"observed_at":"2026-08-07T13:15:39.689990Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.01886","last_updated":"2024-02-03T15:22:33Z","snapshot_observed_at":"2026-07-06T16:26:58.234941Z","submitted_at":"2023-10-03T08:39:33Z","title":"BYOM: Building Your Own Multi-Task Model For Free","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.01886","snapshot_observed_at":"2026-08-07T13:15:39.754741Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:39.754741Z"},"links":{"cited_paper":"/paper/2310.01886","citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:7b466e7e1cab090e76e15ed3f50463183c572460a91ed0b699ee81cf24843a39","observation_id":"595688af-1c8a-43e4-81d0-994c2d73856b","resolution":{"observed_at":"2026-08-07T13:15:39.754741Z","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":"2026-08-07T13:16:01.026885Z","title":"Viggo: A video game corpus for data-to-text generation in open-domain conversation","venue":null,"work_id":"522ca0ee-fee2-43d9-a569-322932104b75","year":2019},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:39.838440Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:4b92c67da1c7b4203fd22a335e8c873bb3475bee769cc9ecbd21a27dbf6da7d0","observation_id":"3ca2f388-d13c-4179-899e-2266dbaaa8cc","resolution":{"observed_at":"2026-08-07T13:16:01.097881Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2001.08361","last_updated":"2020-01-23T03:59:20Z","snapshot_observed_at":"2026-07-06T08:52:12.656082Z","submitted_at":"2020-01-23T03:59:20Z","title":"Scaling Laws for Neural Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.08361","snapshot_observed_at":"2026-08-07T13:15:39.921205Z","title":"Scaling laws for neural language models","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:39.921205Z"},"links":{"cited_paper":"/paper/2001.08361","citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:fbfb3cdf5945b1b220b3024ff2908bab5b85ebc4e88acf60caf534715dd21b61","observation_id":"b67ff8d5-0e9b-45e4-93f7-bb5ee0fb3dab","resolution":{"observed_at":"2026-08-07T13:15:39.921205Z","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":"2026-08-07T13:15:39.995899Z","title":"Compacter: Efficient low-rank hypercomplex adapter layers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:39.995899Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:f767a0c3e27da3a39f9c6942e8e5bf2046996db386c31cc17af6218e16c05de9","observation_id":"4bb41e2c-d6ea-4f2c-be09-e0bd1a049f51","resolution":{"observed_at":"2026-08-07T13:15:39.995899Z","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":"2026-08-07T13:16:00.807648Z","title":"Bias plus variance decomposition for zero-one loss functions","venue":null,"work_id":"ca77667c-c1db-4148-910c-efdaeb0edaa4","year":1996},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:40.059767Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:f2d3a02e08cf68703b82e2c24725bb35ee680d1bed772231b397434f55ffb690","observation_id":"208642fc-4995-4ec3-802f-bb0efe11ef5f","resolution":{"observed_at":"2026-08-07T13:16:00.907734Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:16:00.636968Z","title":"Fine-Tuning Llama-2: A Comprehensive Case Study for Tailoring Models to Unique Applications","venue":null,"work_id":"71f50f5f-2080-4a7f-8acd-f71a5e981ac5","year":2023},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:40.139808Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:1f086c191722d0f15f9b2cd280bb7862d8c651e943d8b428c03e803b2cba8927","observation_id":"c09185b5-02c3-4826-915e-35b2c989352d","resolution":{"observed_at":"2026-08-07T13:16:00.714779Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:16:00.419438Z","title":"The power of scale for parameter-efficient prompt tuning","venue":null,"work_id":"f72769b8-191e-4462-9add-391e7fdad01b","year":2021},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:40.256605Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:d9bd8528ce87b2ac08740b632a4d5e2929ccb5d6bee57aa4aff10330fa138ec4","observation_id":"f5b87aa2-e10b-4844-848f-938c461c6ca1","resolution":{"observed_at":"2026-08-07T13:16:00.531571Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:16:00.253757Z","title":"BART: denoising sequence-to-sequence pre- training for natural language generation, translation, and comprehension","venue":null,"work_id":"bb8cdf58-99a7-4bfa-b38b-a7e4db044e73","year":2020},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:40.317550Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:1296073a0fae0a76c12f6e0788b4f8bcd23a72ebca8a362f599eaf1cdcda1c13","observation_id":"ba3a2de4-834a-4ec9-a469-348fd83c155b","resolution":{"observed_at":"2026-08-07T13:16:00.327525Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:16:00.015757Z","title":"Measuring the intrinsic dimension of objective landscapes","venue":null,"work_id":"38713729-6aca-4562-a959-3fcb2f9b29fa","year":2018},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:40.383650Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:5b5ee507eca2ec7ef8992eb2b0109ba3add6fab87a7e8ef33aa0e54e488dcc68","observation_id":"1a364875-df6b-4d88-9fd8-7b135d3afba6","resolution":{"observed_at":"2026-08-07T13:16:00.146513Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:15:40.444743Z","title":"Prefix-tuning: Optimizing continuous prompts for generation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:40.444743Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:084669e4d5ff88b5180e7a4bf7a4a35901f3cae89342a2e181dbef5ef020cc06","observation_id":"14fdf519-0097-4acc-9c5a-36d69afa2748","resolution":{"observed_at":"2026-08-07T13:15:40.444743Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-04T11:46:49.970828Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-07T13:15:40.547680Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:40.547680Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:d1d83e4781b8aec2c23965682d8ebaeedd5dc25cf5d3092dfb0a50c62d367d32","observation_id":"851674e6-c71a-4aa2-9dee-5f4cb0250ae5","resolution":{"observed_at":"2026-08-07T13:15:40.547680Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.13303","last_updated":"2024-04-03T08:23:06Z","snapshot_observed_at":"2026-08-09T16:22:22.618593Z","submitted_at":"2024-01-24T08:57:39Z","title":"MaLA-500: Massive Language Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.13303","snapshot_observed_at":"2026-08-07T13:15:40.661396Z","title":"Mala-500: Massive language adaptation of large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:40.661396Z"},"links":{"cited_paper":"/paper/2401.13303","citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:75066182fdd7d3eac6f10a44ad11fe8e3e787e9d465f6e953c708213eca57a03","observation_id":"984b72ce-b176-4fba-85fd-b26c46e6685d","resolution":{"observed_at":"2026-08-07T13:15:40.661396Z","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":"2026-08-07T13:15:59.791966Z","title":"Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning","venue":null,"work_id":"4a3286f5-d075-4671-ba74-a9911e34f347","year":2022},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:40.744269Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:f9ce8266b064f32ce63796b82a2d056d7291d32d42572792707ce5a5c3b05446","observation_id":"724c77be-d3f7-4802-bc6d-ab53e4ebf3fe","resolution":{"observed_at":"2026-08-07T13:15:59.895873Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:15:40.805362Z","title":"Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning","venue":null,"work_id":null,"year":1950},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:40.805362Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:a6cc9c74c06cd334a0f083ad859cbd0ccabf059101df74c84f5ed853b5cf7736","observation_id":"0c264f59-2a2a-4ad5-9528-041921dc133b","resolution":{"observed_at":"2026-08-07T13:15:40.805362Z","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":"2026-08-07T13:15:59.541159Z","title":"A robust adversarial training approach to machine reading comprehension","venue":null,"work_id":"06d9f404-11f2-427c-880c-1dd08e612e6a","year":2020},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:40.885986Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:b761c285664b3340d24436133a2eeafc4f68569c324b7698035105e4a832bda7","observation_id":"15f10fbe-82e8-4a88-beb6-67e401725a5f","resolution":{"observed_at":"2026-08-07T13:15:59.658680Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1907.11692","last_updated":"2019-07-26T17:48:29Z","snapshot_observed_at":"2026-07-31T22:31:37.910868Z","submitted_at":"2019-07-26T17:48:29Z","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.11692","snapshot_observed_at":"2026-08-07T13:15:40.970414Z","title":"Roberta: A robustly optimized BERT pretraining approach","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:40.970414Z"},"links":{"cited_paper":"/paper/1907.11692","citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:da6cfc49fcbf1c9024b0fa5a36914108253af136135753e05a866120c3741444","observation_id":"54772026-c1e0-4ffa-82de-c58cc9fd5efd","resolution":{"observed_at":"2026-08-07T13:15:40.970414Z","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":"2026-08-07T13:15:59.320969Z","title":"Multilingual denoising pre-training for neural machine translation","venue":null,"work_id":"4c45fdf1-cb9b-4572-8574-2668b62245c8","year":2020},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:41.034754Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:0b0ec677f4eb33dbb1e63532629cd069cf6478e25e8f8ed4877fecf574e397a9","observation_id":"42a32492-fb45-484a-9e38-02d7c81fe6a9","resolution":{"observed_at":"2026-08-07T13:15:59.414841Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.15207","last_updated":"2024-06-17T10:35:06Z","snapshot_observed_at":"2026-07-06T17:21:10.236126Z","submitted_at":"2024-01-26T21:14:32Z","title":"HiFT: A Hierarchical Full Parameter Fine-Tuning Strategy","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.15207","snapshot_observed_at":"2026-08-07T13:15:41.039555Z","title":"Hift: A hierarchical full parameter fine-tuning strategy","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:41.039555Z"},"links":{"cited_paper":"/paper/2401.15207","citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:847e946b05878f94f985c5ee6bfaf5eedca886f6a04cfa55e8fa53e45dc28ffc","observation_id":"2e3b0e7d-0f44-43e3-a0a7-358d6297b950","resolution":{"observed_at":"2026-08-07T13:15:41.039555Z","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":"2026-08-07T13:15:59.125447Z","title":"Hidden factors and hidden topics: understanding rating dimensions with review text","venue":null,"work_id":"3186858a-718f-423d-ad16-f76537ccbfb0","year":2013},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:41.044050Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:3be7151e0b3915fee71205db89fe9eef578ff88e869a4eab6b0ae0ca5eccb5a4","observation_id":"fa20ead6-55c7-4201-a814-661fafc423df","resolution":{"observed_at":"2026-08-07T13:15:59.229472Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:15:58.929034Z","title":null,"venue":null,"work_id":"cd90ab3b-cb46-4436-bf6e-8a9cffcfea58","year":1960},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:53.878264Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:da2b7bbee41bca0c4d9cdac37a2d78e21a3451f348d902055ac27b5ad231e3ae","observation_id":"2298b2e2-7bb6-4c8c-a958-45f97552efe8","resolution":{"observed_at":"2026-08-07T13:15:59.005445Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:15:58.742699Z","title":"Morris, Eli Lifland, Jin Yong Yoo, Jake Grigsby, Di Jin, and Yanjun Qi","venue":null,"work_id":"0e9c5ec5-1f87-4a92-bc12-bfe6d4c82f14","year":2020},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:53.902121Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:d01ab11fab2632f01c07a6c033a7d932f8b8b66d8766b5d8bd4f3241ff639b26","observation_id":"8991882c-3e58-49ce-8dec-15c8029035dd","resolution":{"observed_at":"2026-08-07T13:15:58.829639Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:15:58.601165Z","title":"A modern take on the bias-variance tradeoff in neural networks","venue":null,"work_id":"19605846-3bcf-47b7-98c0-6cd96f146b89","year":2018},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:53.921183Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:b495b98576d09ac3560605f2be73a049d824189d4f9aad0324f4a16bd5c6518a","observation_id":"0fc136bd-353e-44b3-8d8d-fb711d037128","resolution":{"observed_at":"2026-08-07T13:15:58.647517Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:15:58.479367Z","title":"Learn more, but bother less: parameter efficient continual learning","venue":null,"work_id":"803a4ee0-6b18-407c-93d0-3ea967d81cdd","year":2024},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:53.962429Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:54c4209bcdc8dc48adc4a676034df2bec09a312ad7d334898cb221166b48e739","observation_id":"781a4c6f-717c-46b8-911d-06dda19d32e2","resolution":{"observed_at":"2026-08-07T13:15:58.528083Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:15:58.328243Z","title":"Know what you don’t know: Unanswerable ques- tions for squad","venue":null,"work_id":"0effe257-d825-4041-867e-ce5b127f98a9","year":2018},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:53.984276Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:4f6e66e0063b1943134be884380aa2910f92e72b85e934aa66e88a02a3accbb8","observation_id":"0af02282-ef80-4015-a23b-f1685ef01d7a","resolution":{"observed_at":"2026-08-07T13:15:58.402648Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:15:58.204070Z","title":"Finetuning LLMs with LoRA and QLoRA: Insights from Hundreds of Experiments","venue":null,"work_id":"7397f190-a79e-4a8a-9cf4-0ac46df53309","year":2023},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:54.023521Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:2e394334a6b2ed7f4e5e90d8c8e4b4251f229f4732b4f7a293e2c581a2f742e6","observation_id":"6d648650-517d-434a-845a-001ba5d7d64a","resolution":{"observed_at":"2026-08-07T13:15:58.263088Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:15:54.064996Z","title":"The measure of the critical values of differentiable maps","venue":null,"work_id":null,"year":1942},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:54.064996Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:eb3e4e6bc6aa51cd29f059764c23ae3a3021a8d585aded0e3807ff93cfe69744","observation_id":"09fecb0d-2c84-4cb9-841c-53b7264b3c73","resolution":{"observed_at":"2026-08-07T13:15:54.064996Z","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":"2026-08-07T13:15:54.097363Z","title":"Recursive deep models for semantic compositionality over a sentiment treebank","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:54.097363Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:1de48999b5a9ce9aad72bc6cdc3fa7fd71a4948e736b51ef82b26c33da641873","observation_id":"cddc0f6a-6d9e-48ce-b38b-120bba7c3c92","resolution":{"observed_at":"2026-08-07T13:15:54.097363Z","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":"2026-08-07T13:15:54.137803Z","title":"Stanford alpaca: An instruction-following llama model, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:54.137803Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:97a17447e3fca520e1cb41bfd87e9a53ff572c659354cb561eff61485c53a6e4","observation_id":"38854a62-521c-4abe-b29a-2673f5044541","resolution":{"observed_at":"2026-08-07T13:15:54.137803Z","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":"2026-08-07T13:15:54.211557Z","title":"Llama 2: Open foundation and fine-tuned chat models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:54.211557Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:9728924478b00ab922a2439e8913b7b552c9475a5950dc700ff3a0ee8a468372","observation_id":"4f5d9545-870b-4f7e-a2ac-e391ac171ca7","resolution":{"observed_at":"2026-08-07T13:15:54.211557Z","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":"2026-08-07T13:15:54.284807Z","title":"Attention is all you need","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:54.284807Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:9a97172feb15f3b5cb7329fbe0b792acad9786e3e50d6a32eddbce3beaec4ce4","observation_id":"71a6feda-aeac-49f2-8493-bd21401a207c","resolution":{"observed_at":"2026-08-07T13:15:54.284807Z","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":"2026-08-07T13:15:54.350966Z","title":"Building a question answering test collection","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:54.350966Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:8ec97dd031d4e9e140eaeb61f79997be682f42ed334bf9b668a2d78ca38f2d6d","observation_id":"3ed71f43-c9bd-43ed-8116-f3878f7e44f8","resolution":{"observed_at":"2026-08-07T13:15:54.350966Z","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":"2026-08-07T13:15:58.028175Z","title":"Efficient fine-tuning of bert models on the edge","venue":null,"work_id":"7ca2c111-351b-40ac-96e4-35db336c60e5","year":2022},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:54.421944Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:d09348edfc32840b0f88e14717fbb61a534a8baef4cc3bbea3541ef288c73332","observation_id":"d07643eb-e23f-43a1-92f3-b7ee68bb1db9","resolution":{"observed_at":"2026-08-07T13:15:58.080872Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:15:57.918214Z","title":"Glue: A multi-task benchmark and analysis platform for natural language understanding","venue":null,"work_id":"1bf7d7af-4eec-44bc-8bac-4f4a5a9ea26c","year":2018},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:54.539883Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:9ecfa45c13dc07af2e7b5582b407d6cb3e5798c7505f56cfe51149f9c4458194","observation_id":"f797033a-c2e2-4c82-b445-870a8f2213c8","resolution":{"observed_at":"2026-08-07T13:15:57.964986Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:15:57.789977Z","title":"Adversarial GLUE: A multi-task benchmark for robustness evaluation of language models","venue":null,"work_id":"664708cd-e064-48b1-b5c2-bddf1309cab1","year":2021},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:54.602084Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:75a8fb3cef1eec0132fc2e4b0270ebbf473557c6ac84d743f9b7a807cdb71000","observation_id":"f507dc7a-600f-45f1-afb5-383a323f12c9","resolution":{"observed_at":"2026-08-07T13:15:57.854289Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.12095","last_updated":"2023-08-29T05:34:25Z","snapshot_observed_at":"2026-08-05T13:57:45.408890Z","submitted_at":"2023-02-22T11:01:20Z","title":"On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.12095","snapshot_observed_at":"2026-08-07T13:15:54.670865Z","title":"On the robustness of chatgpt: An adversarial and out-of-distribution perspective","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:54.670865Z"},"links":{"cited_paper":"/paper/2302.12095","citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:6bb4a66d3c6be49a91a088114bcc1a0392abf6861a750510cf957011cfe88e57","observation_id":"0623adb6-d5df-4bbc-8bcf-2796c5b81227","resolution":{"observed_at":"2026-08-07T13:15:54.670865Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.06024","last_updated":"2024-09-14T21:47:21Z","snapshot_observed_at":"2026-07-06T15:25:28.320467Z","submitted_at":"2023-05-10T10:19:31Z","title":"A Survey on the Robustness of Computer Vision Models against Common Corruptions","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.06024","snapshot_observed_at":"2026-08-07T13:15:54.766783Z","title":"The robustness of computer vision models against common corruptions: a survey","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:54.766783Z"},"links":{"cited_paper":"/paper/2305.06024","citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:ea545f4dc6991d1b21a406aeff33c46585bd4bce0f818781da27e7a8e8e1e86c","observation_id":"bd5caff5-17a8-47cf-b8cc-6faa2779ee90","resolution":{"observed_at":"2026-08-07T13:15:54.766783Z","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":"2026-08-07T13:15:57.640902Z","title":"Textflint: Unified multilingual robustness evaluation toolkit for natural language processing","venue":null,"work_id":"2dbf4554-bf37-4acf-aa0d-df1b0a321d0d","year":2021},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:54.882757Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:16852d11e42fd498d76c4948d1bbd621d2676730ba6d9cccf31a6ebb721dbcf6","observation_id":"03d6909f-789f-4c19-ae47-e1aa948e8708","resolution":{"observed_at":"2026-08-07T13:15:57.718317Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:15:57.504579Z","title":"A broad-coverage challenge corpus for sentence understanding through inference","venue":null,"work_id":"fd8175b2-522c-4a57-8bb2-61b2acad0576","year":2018},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:54.929259Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:2d6f4dafcc8aa7a9bb483d1c634b29425e2049246be21af9eebc6e99052f6b6e","observation_id":"36d36e32-1957-4131-893d-ca55d2ba6f71","resolution":{"observed_at":"2026-08-07T13:15:57.546769Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1809.08887","last_updated":"2019-02-02T23:53:18Z","snapshot_observed_at":"2026-07-06T07:03:52.901427Z","submitted_at":"2018-09-24T13:03:13Z","title":"Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.08887","snapshot_observed_at":"2026-08-07T13:15:54.995510Z","title":"Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-sql task","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:54.995510Z"},"links":{"cited_paper":"/paper/1809.08887","citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:2fe498b86586f8389adbd5702c473c6530af667a387ce8521a226d1569681040","observation_id":"2a3bcc9a-4993-49df-b715-032782d0c94a","resolution":{"observed_at":"2026-08-07T13:15:54.995510Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.04618","last_updated":"2023-10-26T06:59:50Z","snapshot_observed_at":"2026-07-06T15:39:53.141172Z","submitted_at":"2023-06-07T17:47:03Z","title":"Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.04618","snapshot_observed_at":"2026-08-07T13:15:55.040614Z","title":"Revisiting out-of-distribution robustness in NLP: benchmark, analysis, and llms evaluations","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:55.040614Z"},"links":{"cited_paper":"/paper/2306.04618","citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:06b7f26078723ef4cabc8e477bd02b330f0df6a3a5e7d693cecfcb8ff2caeec9","observation_id":"77b91b32-6a72-45d9-a7bb-820cd4b08436","resolution":{"observed_at":"2026-08-07T13:15:55.040614Z","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":"2026-08-07T13:15:57.388105Z","title":"Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked language-models","venue":null,"work_id":"d9e97a5e-01f8-4e27-9e17-0206eec3b27c","year":2022},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:55.142722Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:9663af05c2b9a4dce721809b2a487b881c3f2edd81607a8553ad058badbbb476","observation_id":"388a7cf4-dd0b-4d55-881a-84f3d9a8f983","resolution":{"observed_at":"2026-08-07T13:15:57.439796Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.02414","last_updated":"2023-10-25T05:22:43Z","snapshot_observed_at":"2026-08-02T04:26:53.194797Z","submitted_at":"2022-10-05T17:34:44Z","title":"GLM-130B: An Open Bilingual Pre-trained Model","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.02414","snapshot_observed_at":"2026-08-07T13:15:55.244227Z","title":"Glm-130b: An open bilingual pre-trained model","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:55.244227Z"},"links":{"cited_paper":"/paper/2210.02414","citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:97a6329435edb7e2d7a7f2deb3edab3092bc4c7dc6a5f4ff183bb4f504c47c54","observation_id":"6bfe6ea7-c4c8-403f-9c3a-43905a0b7358","resolution":{"observed_at":"2026-08-07T13:15:55.244227Z","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":"2026-08-07T13:15:57.217456Z","title":"Openattack: An open-source textual adversarial attack toolkit","venue":null,"work_id":"a04a43c4-e746-40b9-b5ba-2ca84847e8d1","year":2021},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:55.295070Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:56f7d98075230661dda69298833eb687e81aae61aa572165f18eb6293d9f4ac9","observation_id":"aee6f738-f1b5-4a74-aee6-9bf9f458524d","resolution":{"observed_at":"2026-08-07T13:15:57.324635Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:15:56.925831Z","title":"Adaptive budget allocation for parameter-efficient fine-tuning","venue":null,"work_id":"834f5aba-13a2-481a-b793-0bb82f1c2cf7","year":2023},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:55.360370Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:da2a7a5c7d49bc81ea377063ecf64f2a25cd6262afd5adfb0bbd7876fb290b1d","observation_id":"31379478-576f-4554-9bc8-056bbae3760f","resolution":{"observed_at":"2026-08-07T13:15:57.095799Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.01068","last_updated":"2022-06-21T17:04:40Z","snapshot_observed_at":"2026-08-06T03:13:37.403059Z","submitted_at":"2022-05-02T17:49:50Z","title":"OPT: Open Pre-trained Transformer Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.01068","snapshot_observed_at":"2026-08-07T13:15:55.462049Z","title":"Diab, Xian Li, Xi Victoria Lin, Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, and Luke Zettlemoyer","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:55.462049Z"},"links":{"cited_paper":"/paper/2205.01068","citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:9c33d2d646a7890cd1969137cf3bfb09175d9c3e0d0ed904634a5211ca2aa33e","observation_id":"1a149608-d37f-42d6-bac8-9f8d702474c8","resolution":{"observed_at":"2026-08-07T13:15:55.462049Z","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":"2026-08-07T13:15:55.536142Z","title":"Character-level convolutional networks for text classification","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:55.536142Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:fa16f8a8a20d56ffbe0fbb4fbd87b078fda3b6f33e43fc98f02005f23b6b8c8e","observation_id":"6e772163-ad6c-4050-bad6-2d498d276e61","resolution":{"observed_at":"2026-08-07T13:15:55.536142Z","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":"2026-08-07T13:15:56.681961Z","title":"Towards adaptive prefix tuning for parameter-efficient language model fine-tuning","venue":null,"work_id":"b7ea5f8d-085f-44a5-a15a-d5944962ba10","year":2023},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:55.605128Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:cfa4db69ed5ceb0e1a4beea82c92dad1f72b806d435d5ec21e6e0a101766e8ec","observation_id":"2d648484-6cee-4fd4-a42e-a8c25732a4a9","resolution":{"observed_at":"2026-08-07T13:15:56.771479Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:15:55.677885Z","title":"Judging llm-as-a-judge with mt-bench and chatbot arena","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:55.677885Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:24fc6bec963aadfe8319c7e45f78d7974cbe2a87599a61b81ed1add600916e04","observation_id":"6d651174-1ff7-40e9-af12-90f93b9bb3e6","resolution":{"observed_at":"2026-08-07T13:15:55.677885Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1709.00103","last_updated":"2017-11-09T23:06:14Z","snapshot_observed_at":"2026-08-03T05:45:09.122112Z","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":"2026-08-07T13:15:55.747677Z","title":"Seq2sql: Generating structured queries from natural language using reinforcement learning","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:55.747677Z"},"links":{"cited_paper":"/paper/1709.00103","citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:64a9d739319d81ac76a267cb04bb138229d847f98cc9d63fdac166f9e57b90cd","observation_id":"f4fd0f2d-302f-4567-8054-18a397a81b32","resolution":{"observed_at":"2026-08-07T13:15:55.747677Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.04528","last_updated":"2024-07-16T07:29:49Z","snapshot_observed_at":"2026-08-07T20:45:44.253504Z","submitted_at":"2023-06-07T15:37:00Z","title":"PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.04528","snapshot_observed_at":"2026-08-07T13:15:55.842329Z","title":"q_proj\",","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:55.842329Z"},"links":{"cited_paper":"/paper/2306.04528","citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:e692e6d9905cd0e9097f1c5495446042071d18e71c9617eee2d266f16dd9497a","observation_id":"1f3d2782-3fef-4ef9-acbe-fb7db3bb5404","resolution":{"observed_at":"2026-08-07T13:15:55.842329Z","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":"2026-08-07T13:15:39.056700Z","title":"URL https://openreview.net/forum?id=nZeVKeeFYf9","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:39.056700Z"},"links":{"citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:340ea2cdd1967401db1b6bcfd482c108185c479dbd51f1babd6119ff6652c327","observation_id":"6d3914cc-c6b7-47ae-a059-7d79700c3a30","resolution":{"observed_at":"2026-08-07T13:15:39.056700Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T09:37:33.386478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning"},"reference_resolution":{"displayed":75,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":38,"verified_exact":1,"verified_fuzzy":35},"total_outbound_references":75},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 75 of 75 outbound references and 2 inbound Pith citation observations for arXiv:2505.22355."}