{"as_of":"2026-08-13T07:13:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5459f10aa079282daddbc139cc4ce0afb897d5f10906947a337f8c6fb2cd92c9","coverage":[{"denominator":105,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T05:31:01.030883Z","state":"measured"},{"denominator":102,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":102,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+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":"2026-07-11T22:55:43.595779Z","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":"2026-05-20T10:28:12.100716Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"cited_work":{"arxiv_id":"2412.00383","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.00383","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"8f93a173-d4b0-4f21-a6c3-142db98ac6bd","year":2024},"citing_paper":{"arxiv_id":"2605.19042","last_updated":"2026-05-18T19:05:40Z","snapshot_observed_at":"2026-07-06T23:29:47.081347Z","submitted_at":"2026-05-18T19:05:40Z","title":"Interference-Aware Multi-Task Unlearning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-20T10:25:57.025905Z"},"links":{"cited_paper":"/paper/2412.00383","citing_paper":"/paper/2605.19042"},"observation_digest":"sha256:24dc679b62d171a13fb843df50808e9b9665f6e64b40457fd914fd11936aacac","observation_id":"59f2578b-da08-4e60-a347-37587fa0c1c5","resolution":{"observed_at":"2026-05-20T10:28:12.102243Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.00383","snapshot_observed_at":"2026-07-11T22:55:43.595779Z","title":"doi: 10.18653/v1/N19-1423","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.03932","last_updated":"2026-07-04T15:52:16Z","snapshot_observed_at":"2026-08-10T00:16:50.746302Z","submitted_at":"2026-07-04T15:52:16Z","title":"MPSelectTune: Prompt-type Selection for Fine-tuning improves Concept Unlearning in LLMs","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-11T22:55:43.595779Z"},"links":{"cited_paper":"/paper/2412.00383","citing_paper":"/paper/2607.03932"},"observation_digest":"sha256:372e49f019272c9547c828e5816e41ffd95b1712f048fed5c964de07bf4e8a33","observation_id":"2bbc6d04-fa87-4013-9b88-f359a8fa2831","resolution":{"observed_at":"2026-07-11T22:55:43.595779Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2412.00383/citation-record","integrity":"/paper/2412.00383/integrity","json":"/paper/2412.00383/citation-record.json","paper":"/paper/2412.00383"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1602.03943","last_updated":"2017-11-30T18:38:02Z","snapshot_observed_at":"2026-08-11T14:52:13.950357Z","submitted_at":"2016-02-12T01:38:05Z","title":"Second-Order Stochastic Optimization for Machine Learning in Linear Time","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1602.03943","snapshot_observed_at":"2026-08-12T05:31:00.515942Z","title":"Second order stochastic optimization in linear time","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.515942Z"},"links":{"cited_paper":"/paper/1602.03943","citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:00ba9c9d38204524da1cf021a6d833838b940552bc7ebe25cbaac80c30c93f31","observation_id":"2ad3360d-e3f7-44c0-8ad6-40b8466045e5","resolution":{"observed_at":"2026-08-12T05:31:00.515942Z","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":"2026-08-12T05:31:00.523511Z","title":"Glassman","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.523511Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:890b9d03935b3957b187c1a8f7221564b77a089901c347264e300533d755e1e4","observation_id":"45e46501-a67f-476c-8e7e-ad1d51d28b80","resolution":{"observed_at":"2026-08-12T05:31:00.523511Z","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":"2026-08-12T05:31:00.529606Z","title":"Tallrec: An effective and efficient tuning framework to align large language model with recommendation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.529606Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:efb29db8bb3ad62b65667297d5ea2c2e528679805af9a7816a29684906b93d7a","observation_id":"9d0a5263-d4fa-431e-9e78-02c6a59b60b5","resolution":{"observed_at":"2026-08-12T05:31:00.529606Z","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":"2026-08-12T05:31:00.535506Z","title":"Bartlett and Shahar Mendelson","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.535506Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:02fc580091621ca742774344d3bafef7d8cda2425d144ed6332b05698332798c","observation_id":"ab53bb16-446e-4ad3-9a97-07d1dc532067","resolution":{"observed_at":"2026-08-12T05:31:00.535506Z","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":"2026-08-12T05:31:00.540714Z","title":"Influence functions in deep learning are fragile","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.540714Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:8f8518526a2da818288a7c9ce2795d8a316a9922034aca290d23b65cb3f9cced","observation_id":"a0677543-befc-4372-b57b-41750bd72ffd","resolution":{"observed_at":"2026-08-12T05:31:00.540714Z","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":"2026-08-12T05:31:00.548256Z","title":"A fast iterative shrinkage-thresholding algorithm for linear inverse problems","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.548256Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:a20e61b375cdf3aeb7a7ef94e4e5679d00461429714bfa5585a01c6ce92d17cc","observation_id":"945758f6-357c-4bf5-993b-dd4ebb307a45","resolution":{"observed_at":"2026-08-12T05:31:00.548256Z","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":"2026-08-12T05:31:00.554420Z","title":"Nonlinear programming","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.554420Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:153a568f00954815f449cda9e3399c843990d47ac2357f661202670b63c1399c","observation_id":"33902f26-4994-4701-8ba8-a1cacb2e5d00","resolution":{"observed_at":"2026-08-12T05:31:00.554420Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.02062","last_updated":"2024-04-02T16:01:18Z","snapshot_observed_at":"2026-08-13T00:39:10.222116Z","submitted_at":"2024-04-02T16:01:18Z","title":"Digital Forgetting in Large Language Models: A Survey of Unlearning Methods","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.02062","snapshot_observed_at":"2026-08-12T05:31:00.559557Z","title":"Digital forgetting in large language models: A survey of unlearning methods","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.559557Z"},"links":{"cited_paper":"/paper/2404.02062","citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:21de3ed33b20a5cc9fd3ef27e22fc50d71eebb31aa71f2cbfb5a285b49f060be","observation_id":"cdba72d5-d301-4526-b4a5-e474eb42899b","resolution":{"observed_at":"2026-08-12T05:31:00.559557Z","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":"2026-08-12T05:31:00.564974Z","title":"Choquette - Choo, Hengrui Jia, Adelin Travers, Baiwu Zhang, David Lie, and Nicolas Papernot","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.564974Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:d7027509f50b35bc7f55885ef9c0e60f00773e84edebadd01c89280d10dc639e","observation_id":"2e50319d-d09d-407e-bfe7-48055e80cebd","resolution":{"observed_at":"2026-08-12T05:31:00.564974Z","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":"2026-08-12T05:31:00.570717Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.570717Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:5c584823b949b1d47569c3b819fc33f5303613824294a3d7c5da93cbaaab5ec6","observation_id":"92272415-2c71-4b39-ac45-bb8944bdb9de","resolution":{"observed_at":"2026-08-12T05:31:00.570717Z","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":"2026-08-12T05:31:00.576489Z","title":null,"venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.576489Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:c446cb6fc87ab6c2843dab405ee3cfed687fa61827eccc451c0a68d7a9b169ae","observation_id":"b45a1d76-b44d-41d3-9b14-cbd046aea339","resolution":{"observed_at":"2026-08-12T05:31:00.576489Z","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":"2026-08-12T05:31:00.581737Z","title":"Prompting change: exploring prompt engineering in large language model ai and its potential to transform education","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.581737Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:e2b8a9252eb79a43043949b1def0331bd7d9a3a2d70c181c20163ebbc133ba7c","observation_id":"2ee5cf91-3f2a-4ea7-9a84-4c5f776b6679","resolution":{"observed_at":"2026-08-12T05:31:00.581737Z","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":"2026-08-12T05:31:00.586641Z","title":"Proceedings of the 2nd International Workshop on Information Heterogeneity and Fusion in Recommender Systems, HetRec '11, Chicago, Illinois, USA, October 27, 2011, 2011","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.586641Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:b6df7017d5a20738c2685793c11ad4eaf1c403a5bcdc83d64f3f690524d566cb","observation_id":"473097d0-7c4e-4e36-98f6-f7e40d4e0439","resolution":{"observed_at":"2026-08-12T05:31:00.586641Z","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":"2026-08-12T05:31:00.591464Z","title":"Learning to unlearn: Instance-wise unlearning for pre-trained classifiers","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.591464Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:57f33b3e502ee69dadbe49ee163514bcf04933995bacfdf39a4d6b375b131115","observation_id":"5180e43d-82b6-4a79-9bf5-46fdd3d6869a","resolution":{"observed_at":"2026-08-12T05:31:00.591464Z","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":"2026-08-12T05:31:00.596262Z","title":"Recommendation unlearning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.596262Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:4195e9efa216d2c19f044cc633411d7b7461b4bdfdb9548be9ebf8cf08ace70a","observation_id":"c3fafa25-8237-4dd8-900b-bddc1faa5863","resolution":{"observed_at":"2026-08-12T05:31:00.596262Z","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":"2026-08-12T05:31:00.601063Z","title":"Unlearn what you want to forget: Efficient unlearning for llms","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.601063Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:fc47b0bd49f71391f578e52ab3747941f9021a9a94943c7074d80ee6813b7cba","observation_id":"2e9faee9-0cb3-49f4-8f6a-cdc9a12e7af8","resolution":{"observed_at":"2026-08-12T05:31:00.601063Z","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":"2026-08-12T05:31:00.605788Z","title":"On softmax direct preference optimization for recommendation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.605788Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:6dbed7dfdbdc67abc2b108ae7028518896621e661e4bd066996c2c46b777429c","observation_id":"293423e4-795f-4ab7-b33b-3bf81cdaf23e","resolution":{"observed_at":"2026-08-12T05:31:00.605788Z","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":"2026-08-12T05:31:00.610866Z","title":"Exploring the potential of large language models (llms)in learning on graphs","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.610866Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:6df20db0b283a7a6a95b25e702d69dd94add999a4118fd5f60e57267dbfd724b","observation_id":"42596e1e-7f21-44cf-a72e-9b004e08699d","resolution":{"observed_at":"2026-08-12T05:31:00.610866Z","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":"2026-08-12T05:31:00.615474Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.615474Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:634d08e7f8b05a9647b000a33f6439cbbb800acac9ef84df453cab98fe9e8813","observation_id":"242cebc4-71b6-44f2-9af2-4cd3d474b9d8","resolution":{"observed_at":"2026-08-12T05:31:00.615474Z","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":"2026-08-12T05:31:00.620244Z","title":"Personalized pedagogy through a llm-based recommender system","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.620244Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:74de786f2b7ac0f6ec6f5bebdf2311ec8ff3624bedde29c4337a92355ca168c3","observation_id":"54a6b158-4594-408e-b2ff-a04530288236","resolution":{"observed_at":"2026-08-12T05:31:00.620244Z","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":"2026-08-12T05:31:00.625036Z","title":"Qlora: Efficient finetuning of quantized llms","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.625036Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:566855556654d4040b0fad7f78564a6a9fd91327479748db17ef9bd22c2701c7","observation_id":"c9371465-255f-4dd1-a6bf-c36026de8355","resolution":{"observed_at":"2026-08-12T05:31:00.625036Z","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":"2026-08-12T05:31:00.629624Z","title":"BERT: pre-training of deep bidirectional transformers for language understanding","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.629624Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:b9a45c514c2cf48a345cb86b4f98714997f55aab112b996fa4b5aaa1c6ec3c9a","observation_id":"4adeb7df-206f-4117-a5ab-043308026aef","resolution":{"observed_at":"2026-08-12T05:31:00.629624Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.01669","last_updated":"2025-08-14T12:15:41Z","snapshot_observed_at":"2026-08-12T22:42:54.513023Z","submitted_at":"2025-02-01T16:23:13Z","title":"Delayed Feedback Modeling with Influence Functions","version":2},"cited_work":{"arxiv_id":"2502.01669","doi":null,"metadata_source":"pith","pith_arxiv_id":"2502.01669","snapshot_observed_at":"2026-08-12T05:31:01.677969Z","title":"Delayed Feedback Modeling with Influence Functions","venue":"cs.LG","work_id":"c75018f5-9ed6-4d63-bc7e-bc82b2134bf7","year":2025},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.634357Z"},"links":{"cited_paper":"/paper/2502.01669","citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:74ec3f41fa38e42f61fdec66974755fef447c3fc027e6bb37be6209a7abb59e3","observation_id":"1f89fb10-6204-4b74-b4d9-d3f0173a4fbd","resolution":{"observed_at":"2026-08-12T05:31:01.682761Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.06305","last_updated":"2020-02-15T02:40:10Z","snapshot_observed_at":"2026-08-12T00:45:25.809655Z","submitted_at":"2020-02-15T02:40:10Z","title":"Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.06305","snapshot_observed_at":"2026-08-12T05:31:00.639379Z","title":"Fine-tuning pretrained language models: Weight initializations, data orders, and early stopping","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.639379Z"},"links":{"cited_paper":"/paper/2002.06305","citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:0762cec64514ec3bd22282f60f272faf7a8c937a9b0fe1fb4461d191a46a4da9","observation_id":"831c41ef-e60e-40e5-828a-c8440d25e3b0","resolution":{"observed_at":"2026-08-12T05:31:00.639379Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.02238","last_updated":"2023-10-04T05:20:19Z","snapshot_observed_at":"2026-08-13T05:58:13.172138Z","submitted_at":"2023-10-03T17:48:14Z","title":"Who's Harry Potter? Approximate Unlearning in LLMs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.02238","snapshot_observed_at":"2026-08-12T05:31:00.645733Z","title":"Who's harry potter? approximate unlearning in llms","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.645733Z"},"links":{"cited_paper":"/paper/2310.02238","citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:0f127aefa0f37728214c89f6fd82391653a55eb1f0da264573bd94e627840c7e","observation_id":"bc54fad1-8982-49fb-b227-6644077294d4","resolution":{"observed_at":"2026-08-12T05:31:00.645733Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.02355","last_updated":"2025-04-22T16:15:47Z","snapshot_observed_at":"2026-08-12T22:31:47.584935Z","submitted_at":"2024-10-03T10:06:27Z","title":"AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.02355","snapshot_observed_at":"2026-08-12T05:31:00.651754Z","title":"Alphaedit: Null-space constrained knowledge editing for language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.651754Z"},"links":{"cited_paper":"/paper/2410.02355","citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:482b63285d85ff9973d6811beb933cdc76d058de6cd409300987819697e294c4","observation_id":"1e785353-e268-4426-be9d-e6878418b5c5","resolution":{"observed_at":"2026-08-12T05:31:00.651754Z","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":"2026-08-12T05:31:00.657095Z","title":"Moltc: Towards molecular relational modeling in language models","venue":null,"work_id":null,"year":1943},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.657095Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:98a5d35e767064cd13ea872dc5d2beb641a72258a500ed6658dd7b5262a8771d","observation_id":"0c112a92-49f5-42b9-bd86-188f54744172","resolution":{"observed_at":"2026-08-12T05:31:00.657095Z","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":"2026-08-12T05:31:00.662126Z","title":"Practical methods of optimization","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.662126Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:05a52dfdeff3f936a49020e14cd6524f25b9d7d08525674fab23b66d619cfae9","observation_id":"aa151ae4-7635-4da6-81b3-dcd994fde19f","resolution":{"observed_at":"2026-08-12T05:31:00.662126Z","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":"2026-08-12T05:31:00.667041Z","title":"Maxwell Harper and Joseph A","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.667041Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:3e0aad3dfb24139d992463658105c072031be7abd5f79add17723bb9491760ad","observation_id":"446c476f-a2c8-4e8b-ada4-1f222df13c54","resolution":{"observed_at":"2026-08-12T05:31:00.667041Z","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":"2026-08-12T05:31:00.672049Z","title":"Methods of conjugate gradients for solving linear systems, volume 49","venue":null,"work_id":null,"year":1952},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.672049Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:a25dda3184ed7b2fc2ea3a66331ebd2be1236a57e59cd2682606cb9e93cd6f2a","observation_id":"f5e1efb4-80fe-4413-bf75-53d9ddadb514","resolution":{"observed_at":"2026-08-12T05:31:00.672049Z","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":"2026-08-12T05:31:00.677003Z","title":"Parameter-efficient transfer learning for NLP","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.677003Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:01aacc2b530525128d085fdab96da7cf9c72b96200d41708f5c5abe452979363","observation_id":"1205adb6-52e5-4547-bff4-93cf8dd2a7ee","resolution":{"observed_at":"2026-08-12T05:31:00.677003Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.11181","last_updated":"2024-01-20T09:43:36Z","snapshot_observed_at":"2026-08-13T04:38:42.393190Z","submitted_at":"2024-01-20T09:43:36Z","title":"Inference without Interference: Disaggregate LLM Inference for Mixed Downstream Workloads","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.11181","snapshot_observed_at":"2026-08-12T05:31:00.681928Z","title":"Inference without interference: Disaggregate LLM inference for mixed downstream workloads","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.681928Z"},"links":{"cited_paper":"/paper/2401.11181","citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:b4cd3d0a7d6e93caac20a69e650ead3ba9471e7562543de58a014e3a60197d75","observation_id":"e9bfd67b-8615-4c24-abde-68b4eab96343","resolution":{"observed_at":"2026-08-12T05:31:00.681928Z","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":"2026-08-12T05:31:00.687388Z","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":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.687388Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:c3353d48f6571c4f2961e4132d9a97ff179583400bc903ff54ad6f5a06d9698f","observation_id":"3a6b0902-d822-4cc5-b28c-066d43f58be4","resolution":{"observed_at":"2026-08-12T05:31:00.687388Z","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":"2026-08-12T05:31:02.551514Z","title":"Enhancing sequential recommendation via llm-based semantic embedding learning","venue":null,"work_id":"6842cbb1-0463-40c9-8116-6c232816d2a5","year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.692616Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:ce557cf773c02a61d79e595b8208a93b3e9f0a12fe14a8b10d41d47bb276466b","observation_id":"83de7dbf-f994-41cb-8888-079da1f1496a","resolution":{"observed_at":"2026-08-12T05:31:02.556981Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.10327","last_updated":"2024-04-16T07:11:48Z","snapshot_observed_at":"2026-08-13T00:29:21.917432Z","submitted_at":"2024-04-16T07:11:48Z","title":"Exact and Efficient Unlearning for Large Language Model-based Recommendation","version":1},"cited_work":{"arxiv_id":"2404.10327","doi":null,"metadata_source":"pith","pith_arxiv_id":"2404.10327","snapshot_observed_at":"2026-08-12T05:31:01.583350Z","title":"Exact and Efficient Unlearning for Large Language Model-based Recommendation","venue":"cs.IR","work_id":"aa891731-b302-4ebd-995a-a3e07f3cbfa7","year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.697754Z"},"links":{"cited_paper":"/paper/2404.10327","citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:b7a10794b27d40afb01e3fa507e91907736e37c302a7cec09dd9ab6b37df3730","observation_id":"ce099af9-b965-485d-a3f7-8dd2c093b548","resolution":{"observed_at":"2026-08-12T05:31:01.590534Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:31:02.533777Z","title":"Knowledge unlearning for mitigating privacy risks in language models","venue":null,"work_id":"359fc431-6822-494e-a708-c950057b22e7","year":2023},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.703600Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:3f56612fcd97d2a05f29cb27d481d54e223d9f8d784eba019169e771cb2bd1e5","observation_id":"d6bdd975-a3cc-40ff-84f6-bdd8408af7f4","resolution":{"observed_at":"2026-08-12T05:31:02.538958Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.01325","last_updated":"2024-07-11T06:11:46Z","snapshot_observed_at":"2026-08-13T04:49:58.312834Z","submitted_at":"2024-01-02T18:30:51Z","title":"LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.01325","snapshot_observed_at":"2026-08-12T05:31:00.708689Z","title":"LLM maybe longlm: Self-extend LLM context window without tuning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.708689Z"},"links":{"cited_paper":"/paper/2401.01325","citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:7b4fdce21c1ed32937bc76818768d6169d431cc0f384387fb18e7bd05f7fdaea","observation_id":"a143afd2-946b-4c05-9ea9-5e5a2bc6d72a","resolution":{"observed_at":"2026-08-12T05:31:00.708689Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.07420","last_updated":"2023-12-12T16:44:47Z","snapshot_observed_at":"2026-08-13T05:04:01.700806Z","submitted_at":"2023-12-12T16:44:47Z","title":"FairSISA: Ensemble Post-Processing to Improve Fairness of Unlearning in LLMs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.07420","snapshot_observed_at":"2026-08-12T05:31:00.715607Z","title":"Fairsisa: Ensemble post-processing to improve fairness of unlearning in llms","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.715607Z"},"links":{"cited_paper":"/paper/2312.07420","citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:b4f5de12f86139146f291dd6bdcb3148c9518061bfe5ec152455646c679b3159","observation_id":"82f70db3-acfc-411a-8189-409761f69c56","resolution":{"observed_at":"2026-08-12T05:31:00.715607Z","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":"2026-08-12T05:31:02.517128Z","title":"Kassem, Omar Mahmoud, and Sherif Saad","venue":null,"work_id":"46ec9a27-9d83-4a18-bf68-e594e275910a","year":2023},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.721709Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:309f6496036e56c81965004c89c0d582d20ded0780fbd19e92d5ffbb66bb9941","observation_id":"4b86e939-df7b-4024-8dd6-95bbd17f7c51","resolution":{"observed_at":"2026-08-12T05:31:02.522998Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:31:02.501602Z","title":"Understanding black-box predictions via influence functions","venue":null,"work_id":"ae9244d6-6534-47f9-a4e0-f2d6ec2df73c","year":2017},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.726847Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:9588a62afa248824219d0a5dd43f03a6eddca368db8f7c49d119c550bc882f88","observation_id":"0beccad3-4e4f-4eb6-b462-342a83efdec2","resolution":{"observed_at":"2026-08-12T05:31:02.506625Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:31:02.486554Z","title":"Customizing language models with instance-wise lora for sequential recommendation","venue":null,"work_id":"a80442bf-31ac-4ed0-b000-8e0151f55c29","year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.732114Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:14a594dd975a430993fd76af1557ccd39d222da6f1d4612872218165f06e2f69","observation_id":"753e5bde-f1ea-4dd2-8f68-b8494d319564","resolution":{"observed_at":"2026-08-12T05:31:02.491578Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:31:02.470439Z","title":"Privacy adhering machine un-learning in NLP","venue":null,"work_id":"bc839eec-01bb-4bac-bde0-5453245e0655","year":2023},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.737325Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:b41812962776c3ec4cd2053447475355f5d2e82a292f8165a7429e8660029089","observation_id":"41e9366f-5119-4e0f-b690-361d38b2270d","resolution":{"observed_at":"2026-08-12T05:31:02.475476Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:31:02.454072Z","title":"Towards unbounded machine unlearning","venue":null,"work_id":"183e0282-48dc-4364-a84d-474972e9a680","year":2023},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.742873Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:7a080243e9c46a2f5d855ac3fcf916a680bc05d051e53b68f098a2427feb5d6e","observation_id":"dbb6d7c4-675f-49f1-af18-a231e7feae22","resolution":{"observed_at":"2026-08-12T05:31:02.459020Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:31:02.436171Z","title":"Let machines unlearn - machine unlearning and the right to be forgotten","venue":null,"work_id":"859ecc2c-a973-4982-ad11-b8ba77710135","year":2017},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.747852Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:1e017ad817f4160c876e48677907ab7eac8fabcb225ba9a47cf5282469cd532c","observation_id":"75df2c7c-9631-46a7-990c-6516f831f4b7","resolution":{"observed_at":"2026-08-12T05:31:02.442980Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:31:02.417053Z","title":"Collavo: Crayon large language and vision model","venue":null,"work_id":"8c02ce91-4614-4a75-aed7-353df631c01a","year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.753052Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:7a0bef412766975912548f428d69dde9c86ecf47b5827f7bc9d50fab6d9080bf","observation_id":"35667758-b425-42c2-9cfb-89d04108b809","resolution":{"observed_at":"2026-08-12T05:31:02.423009Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.07500","last_updated":"2024-03-12T10:38:03Z","snapshot_observed_at":"2026-08-13T00:56:52.293182Z","submitted_at":"2024-03-12T10:38:03Z","title":"Block-wise LoRA: Revisiting Fine-grained LoRA for Effective Personalization and Stylization in Text-to-Image Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.07500","snapshot_observed_at":"2026-08-12T05:31:00.757959Z","title":"Block-wise lora: Revisiting fine-grained lora for effective personalization and stylization in text-to-image generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.757959Z"},"links":{"cited_paper":"/paper/2403.07500","citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:f6317ff4a2e5b9c755ac71d7fe31e42f7a06a35599e4b315046cc0fcea24b1d4","observation_id":"14b33c2a-b4f9-462d-b4a7-3f8ee1e45eaf","resolution":{"observed_at":"2026-08-12T05:31:00.757959Z","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":"2026-08-12T05:31:00.763224Z","title":"Diffstyler: Diffusion-based localized image style transfer","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.763224Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:151f1865e57d0fd210237ab6cdc2fbe08ba1d75e7817ebc6d691fc0a8aada4cd","observation_id":"38b68d65-f967-4c49-ad2e-0dc6fee03132","resolution":{"observed_at":"2026-08-12T05:31:00.763224Z","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":"2026-08-12T05:31:02.400521Z","title":"Prefix-tuning: Optimizing continuous prompts for generation","venue":null,"work_id":"9053c1c0-e46d-4d2c-a463-4763accfb9bf","year":2021},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.768265Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:6a074b24fa30e6b5af9b23df8a1cc68bafc98eefce039c51d987b46a4f883abf","observation_id":"9e68a5e0-866d-49df-9a52-bb5b8c7ca746","resolution":{"observed_at":"2026-08-12T05:31:02.406158Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.01208","last_updated":"2023-10-02T13:53:03Z","snapshot_observed_at":"2026-08-13T05:59:19.080749Z","submitted_at":"2023-10-02T13:53:03Z","title":"Label Supervised LLaMA Finetuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.01208","snapshot_observed_at":"2026-08-12T05:31:00.773811Z","title":"Label supervised llama finetuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.773811Z"},"links":{"cited_paper":"/paper/2310.01208","citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:1684fafd0c63799ea44ae50666f37900eedd7b1c88d16931fdd1001e45ac897a","observation_id":"3f32a3b3-85c5-4306-a522-d55de371567c","resolution":{"observed_at":"2026-08-12T05:31:00.773811Z","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":"2026-08-12T05:31:02.383840Z","title":"Llara: Large language-recommendation assistant","venue":null,"work_id":"de167760-f7e3-4f47-958f-68064a3ec4da","year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.779597Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:b8c237e3075665f8af22e3015b5e52534e97a6a4deb73426afd2107ae36a25e3","observation_id":"a6a30c62-b419-4faa-ae66-701203dcad0d","resolution":{"observed_at":"2026-08-12T05:31:02.388888Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.03744","last_updated":"2024-05-15T19:22:44Z","snapshot_observed_at":"2026-08-13T06:40:28.574929Z","submitted_at":"2023-10-05T17:59:56Z","title":"Improved Baselines with Visual Instruction Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.03744","snapshot_observed_at":"2026-08-12T05:31:00.784314Z","title":"Improved baselines with visual instruction tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.784314Z"},"links":{"cited_paper":"/paper/2310.03744","citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:07433637f9433d6bae28f909650899cd83973e75470f48a1917b039827f7bd6f","observation_id":"641aac0b-8321-450f-82b7-997b2aaefe98","resolution":{"observed_at":"2026-08-12T05:31:00.784314Z","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":"2026-08-12T05:31:02.366629Z","title":"Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing","venue":null,"work_id":"85d100c7-d389-41e7-b443-b8e0b2def0ab","year":2023},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.789936Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:42bdcb5aeb5433d9545e13024001970efe1a333954d1eca60573b2e721d863c4","observation_id":"123d1bc3-b5f0-4f74-acac-8b1cd252389a","resolution":{"observed_at":"2026-08-12T05:31:02.372218Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.08787","last_updated":"2024-12-06T21:39:49Z","snapshot_observed_at":"2026-08-13T04:19:31.264775Z","submitted_at":"2024-02-13T20:51:58Z","title":"Rethinking Machine Unlearning for Large Language Models","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.08787","snapshot_observed_at":"2026-08-12T05:31:00.794735Z","title":"Varshney, Mohit Bansal, Sanmi Koyejo, and Yang Liu","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.794735Z"},"links":{"cited_paper":"/paper/2402.08787","citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:e462993b2ac818adbd0fac7110ff5ed0d02d54dd4876086ea11839c943515a5a","observation_id":"754b813c-a367-4d43-ab82-cee2e48374bd","resolution":{"observed_at":"2026-08-12T05:31:00.794735Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.07602","last_updated":"2022-03-20T15:13:08Z","snapshot_observed_at":"2026-08-10T14:24:20.137867Z","submitted_at":"2021-10-14T17:58:47Z","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.07602","snapshot_observed_at":"2026-08-12T05:31:00.799633Z","title":"P-tuning v2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.799633Z"},"links":{"cited_paper":"/paper/2110.07602","citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:76429501c6a1b33d494b459037373fd21a786bd4652af4489f52f90e367ddf4c","observation_id":"26df6d92-1de6-4b82-85ae-5d5980b361d3","resolution":{"observed_at":"2026-08-12T05:31:00.799633Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.02038","last_updated":"2024-01-06T03:32:08Z","snapshot_observed_at":"2026-08-13T04:49:16.653610Z","submitted_at":"2024-01-04T02:43:57Z","title":"Understanding LLMs: A Comprehensive Overview from Training to Inference","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.02038","snapshot_observed_at":"2026-08-12T05:31:00.804844Z","title":"Understanding llms: A comprehensive overview from training to inference","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.804844Z"},"links":{"cited_paper":"/paper/2401.02038","citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:932bd029763e9efddb760af8e9b6b1709154e3f1667e631632513ce4ed338d15","observation_id":"be4f4177-0a2b-42bf-81c9-12d957c28fb2","resolution":{"observed_at":"2026-08-12T05:31:00.804844Z","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":"2026-08-12T05:31:02.349816Z","title":"Towards safer large language models through machine unlearning","venue":null,"work_id":"ff24326d-c0fb-4871-b2fd-9908e4342e3b","year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.809813Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:eec286e90bfa6ca5059acdfa1f86c21738d66a07a8287dc1589c127b782c9036","observation_id":"2c1f7739-53e8-4ed5-a2ce-e1541bbf037b","resolution":{"observed_at":"2026-08-12T05:31:02.355041Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.05880","last_updated":"2024-07-03T17:52:00Z","snapshot_observed_at":"2026-08-13T00:34:39.088526Z","submitted_at":"2024-04-08T21:26:22Z","title":"Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledge","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.05880","snapshot_observed_at":"2026-08-12T05:31:00.814639Z","title":"Eraser: Jailbreaking defense in large language models via unlearning harmful knowledge","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.814639Z"},"links":{"cited_paper":"/paper/2404.05880","citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:464db1295ebf4cbeb60d2214b4e8e70b778bb53f4a53be53e1c11094ec6aa50a","observation_id":"565d8b2b-5470-4350-bde8-88d836e3473f","resolution":{"observed_at":"2026-08-12T05:31:00.814639Z","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":"2026-08-12T05:31:02.333230Z","title":"QUARK: controllable text generation with reinforced unlearning","venue":null,"work_id":"b261223a-aa46-4401-b6fd-c1f8a82667be","year":2022},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.820221Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:cc17d8f2547aaca28a942df48760a522d339b62e75234c1724f5cded33210e02","observation_id":"fff7ff87-bee1-4437-b3fe-eccd2ee60e55","resolution":{"observed_at":"2026-08-12T05:31:02.338876Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:31:02.314640Z","title":"Linear and nonlinear programming, volume 2","venue":null,"work_id":"85ceab26-ada2-4951-91b6-fefca67ea687","year":1984},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.824997Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:275e030cc3c1fd0ec7604e09cb82ba839d07820040415016e3ae787d4a3a7291","observation_id":"3a3b585b-6b8c-4953-85f4-eeca28ba1083","resolution":{"observed_at":"2026-08-12T05:31:02.320839Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:31:02.294699Z","title":"Llm-rec: Personalized recommendation via prompting large language models","venue":null,"work_id":"fe6a1a6e-952c-488d-93ca-b43fe75af795","year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.829767Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:1d82f715367a01b5e82e11e83d2ab6c28a127a2e66bd8901aa2ecdcfb889269f","observation_id":"2af41ddf-03aa-4b97-90dd-1afc55d75ebd","resolution":{"observed_at":"2026-08-12T05:31:02.300431Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.17115","last_updated":"2025-02-03T15:18:05Z","snapshot_observed_at":"2026-08-12T23:15:49.666862Z","submitted_at":"2024-07-24T09:24:49Z","title":"Reinforced Prompt Personalization for Recommendation with Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.17115","snapshot_observed_at":"2026-08-12T05:31:00.834756Z","title":"Reinforced prompt personalization for recommendation with large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.834756Z"},"links":{"cited_paper":"/paper/2407.17115","citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:a052a808af185c45937fb92bc438e33e4bd1b421734455c85342c28c9b1af2cd","observation_id":"e3ce1277-e503-4e68-ba34-7b2c4d1bbe76","resolution":{"observed_at":"2026-08-12T05:31:00.834756Z","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":"2026-08-12T05:31:02.276407Z","title":"Getting to know your neighbors (KYN)","venue":null,"work_id":"3d477149-a68e-4ce5-a842-b925ea9ea7e2","year":2020},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.840010Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:47154265bf81b3be61aec5b980c26bd65874a79b0cdb71b19061981cd8394edd","observation_id":"7fd1ec6a-8277-42dd-8215-e19734b01b2b","resolution":{"observed_at":"2026-08-12T05:31:02.282727Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:31:02.258972Z","title":"Feature unlearning for pre-trained gans and vaes","venue":null,"work_id":"5e9c5bdc-2fca-4719-b0c1-c873d3d3b2ed","year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.844632Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:1f203a0075bd3146c57bf814f24e1863839680cc929183af42a40de6d28edc32","observation_id":"cc9f8369-965f-45b1-a65f-3a45910eea95","resolution":{"observed_at":"2026-08-12T05:31:02.264634Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:31:02.241625Z","title":"Hellendoorn, Bogdan Vasilescu, and Brad A","venue":null,"work_id":"0b534983-cdd9-4f86-b61d-4dcfeb44c699","year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.849495Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:a528a201faaec70f2abdfb27c2dcbd0f7456c233dec9fbf5d1962d5083c038a1","observation_id":"b70f1138-bf58-4d61-b275-9cb707803da8","resolution":{"observed_at":"2026-08-12T05:31:02.246736Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:31:02.225228Z","title":"Nesterov","venue":null,"work_id":"2c0d3654-b6d3-453d-b7d5-f07629056c6e","year":2013},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.854086Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:36bbd51f1770d306583982b29c925c8ea134b86f4b49db8c59afbc9cf724cc84","observation_id":"66c30060-502c-422b-9ad4-d23e5270527a","resolution":{"observed_at":"2026-08-12T05:31:02.230471Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:31:00.859404Z","title":"Numerical optimization","venue":null,"work_id":null,"year":1999},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.859404Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:92a2d3fdf02ccd356c8b18c1876576f8e1569b3bece27971565f3312e946a716","observation_id":"20a78351-236d-4d89-b181-18aefe03e9c0","resolution":{"observed_at":"2026-08-12T05:31:00.859404Z","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":"2026-08-12T05:31:00.863974Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.863974Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:77cd70d607d0e7b1b21496542239d2e88d5d6e32946066feea2c3ad9347ae92c","observation_id":"3490aa15-d015-4f0e-8982-f19407fcd9bd","resolution":{"observed_at":"2026-08-12T05:31:00.863974Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.07579","last_updated":"2024-06-06T06:31:08Z","snapshot_observed_at":"2026-08-13T05:52:04.876928Z","submitted_at":"2023-10-11T15:19:31Z","title":"In-Context Unlearning: Language Models as Few Shot Unlearners","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.07579","snapshot_observed_at":"2026-08-12T05:31:00.868846Z","title":"In-context unlearning: Language models as few shot unlearners","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.868846Z"},"links":{"cited_paper":"/paper/2310.07579","citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:f4ee14ed93ef36687c8cc14275d84c688c12538da7dc80212f7f5427402c7ef8","observation_id":"2baea320-ed96-4927-a538-74fe8b0d3092","resolution":{"observed_at":"2026-08-12T05:31:00.868846Z","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":"2026-08-12T05:31:02.185378Z","title":"Pazzani and Daniel Billsus","venue":null,"work_id":"78741b04-f1db-40aa-b2cd-6d2d88b8f30a","year":2007},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":69,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.874552Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:421603c1f526f7721b80cab175a8d354e27520bd67da76cdc3752cb00a9d9d6f","observation_id":"6592d793-4fdb-436a-b9ae-7d013fd34abc","resolution":{"observed_at":"2026-08-12T05:31:02.191288Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:31:02.167595Z","title":"Pearlmutter","venue":null,"work_id":"0eab2dae-c9cd-4d68-b6a8-6a338726ae6c","year":1994},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.880047Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:4c0c3b7d116e2fea1fe3b11bd0bd2dabf443e3eba737fe43c27011e2dfbe6bf6","observation_id":"e3f3d1cf-4f0c-4384-a9b6-994348e7879b","resolution":{"observed_at":"2026-08-12T05:31:02.173524Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.15779","last_updated":"2024-03-23T09:26:15Z","snapshot_observed_at":"2026-08-13T04:51:04.690656Z","submitted_at":"2024-03-23T09:26:15Z","title":"The Frontier of Data Erasure: Machine Unlearning for Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.15779","snapshot_observed_at":"2026-08-12T05:31:00.885017Z","title":"The frontier of data erasure: Machine unlearning for large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.885017Z"},"links":{"cited_paper":"/paper/2403.15779","citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:15cf085d6c0423099d69fd1f0f2f58e6ce51b9b922ed971330e021f0fa75a87b","observation_id":"a24ead87-95bb-4e8b-bfb5-eb5afcd067d2","resolution":{"observed_at":"2026-08-12T05:31:00.885017Z","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":"2026-08-12T05:31:00.890064Z","title":"Language models are unsupervised multitask learners","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.890064Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:0584b265c3620672973a31e3e2c914364a21e2441e31f7a684b739c3bb688784","observation_id":"af6d0a38-dbe0-4632-af65-d466c7a91c20","resolution":{"observed_at":"2026-08-12T05:31:00.890064Z","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":"2026-08-12T05:31:02.140565Z","title":null,"venue":null,"work_id":"c8fcc6ce-2dab-46b1-9e3a-3fd8df64384f","year":2022},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":73,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.894587Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:83ffc4903c15cc501ba90a54bfec279689239af37441b8ff34a2795c22e1b8fb","observation_id":"9d14afac-ae4b-459c-b99b-c1e3f1728e85","resolution":{"observed_at":"2026-08-12T05:31:02.146634Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:31:02.122260Z","title":"Remember what you want to forget: Algorithms for machine unlearning","venue":null,"work_id":"e13f89e7-3c88-4a6a-9aa6-1eb3c48aa5e9","year":2021},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.899745Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:0e5ef8e6df8063ca0932b81c6f5bcc8597a8a626b1a803261bcaf44de3253a23","observation_id":"5298a1b2-01ce-413d-a0f7-0be4efcea6b8","resolution":{"observed_at":"2026-08-12T05:31:02.128676Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:31:00.904589Z","title":"Understanding Machine Learning - From Theory to Algorithms","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":75,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.904589Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:73f6b0c3f17d80d0845353123c3ac0f6ae7665c4d7033ecfbe0cff02ec9ef451","observation_id":"985c31e5-1819-49d5-8f43-0c18da3b5e42","resolution":{"observed_at":"2026-08-12T05:31:00.904589Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.14809","last_updated":"2025-07-04T16:22:10Z","snapshot_observed_at":"2026-08-13T00:24:03.989744Z","submitted_at":"2024-04-23T07:39:24Z","title":"A Survey of Large Language Models on Generative Graph Analytics: Query, Learning, and Applications","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.14809","snapshot_observed_at":"2026-08-12T05:31:00.909148Z","title":"A survey of large language models on generative graph analytics: Query, learning, and applications","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":76,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.909148Z"},"links":{"cited_paper":"/paper/2404.14809","citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:7af4f733ef1aafa6cc8d75064c2176cdfef5e17c5105c8bf054f9f972262b258","observation_id":"fe12166b-2bd2-478b-9dfe-d6184086360a","resolution":{"observed_at":"2026-08-12T05:31:00.909148Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.05441","last_updated":"2025-04-21T03:45:36Z","snapshot_observed_at":"2026-08-12T23:27:16.977484Z","submitted_at":"2024-07-07T17:05:24Z","title":"Language Representations Can be What Recommenders Need: Findings and Potentials","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.05441","snapshot_observed_at":"2026-08-12T05:31:00.914907Z","title":"Language models encode collaborative signals in recommendation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":77,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.914907Z"},"links":{"cited_paper":"/paper/2407.05441","citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:174a93f0e82687376f27eca0d0f6e8b7300cf4414b09ec5ac73579cac60ce1ef","observation_id":"77f43dc2-1d4d-433c-b312-39fab015ace9","resolution":{"observed_at":"2026-08-12T05:31:00.914907Z","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":"2026-08-12T05:31:00.920452Z","title":"An introduction to the conjugate gradient method without the agonizing pain","venue":null,"work_id":null,"year":1994},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":78,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.920452Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:c0e53e4050a88c3130ba3e4e44f72215576a7160b1c37734036d7fccf248de58","observation_id":"8f7b13f1-b77d-40d7-8823-e54a4e6abdc5","resolution":{"observed_at":"2026-08-12T05:31:00.920452Z","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":"2026-08-12T05:31:02.073977Z","title":"Graphgpt: Graph instruction tuning for large language models","venue":null,"work_id":"b5458da8-48e5-4916-9d05-1555d3de9e1b","year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":79,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.924987Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:19462f5658319a2d99ea19141642481dd50817fea34bfcee0405a6246552478d","observation_id":"024d3d18-87ae-4e48-8e0b-9bc96d6814ea","resolution":{"observed_at":"2026-08-12T05:31:02.079625Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-12T05:31:00.929933Z","title":"Llama: Open and efficient foundation language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":80,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.929933Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:920018fe7ec6c5b4842681d494a7b2474ab3f6547945197473109d6bb267fb93","observation_id":"9a648bc1-d3c1-4816-a4a7-25b3f608b693","resolution":{"observed_at":"2026-08-12T05:31:00.929933Z","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":"2026-08-12T05:31:00.935823Z","title":"Llama 2: Open foundation and fine-tuned chat models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":81,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.935823Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:8b18e48064328f244ef4a5ff71481baa785d5d8ca15c65c73fe2d021d7fa1796","observation_id":"1a73a2eb-3c53-4856-886d-7e050efcad8b","resolution":{"observed_at":"2026-08-12T05:31:00.935823Z","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":"2026-08-12T05:31:02.055434Z","title":"Statistical learning theory","venue":null,"work_id":"4e39560d-6a11-4c27-af18-9c98ec39399a","year":1998},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":82,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.941112Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:1e4d8d57863cecc1a6285cdeee7c2bbb195c269331735907d0062e8b7b4d8091","observation_id":"7937c7ed-34bb-42e6-876b-e9de1ff61095","resolution":{"observed_at":"2026-08-12T05:31:02.061584Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.03536","last_updated":"2024-06-30T04:00:06Z","snapshot_observed_at":"2026-08-13T04:02:27.334399Z","submitted_at":"2024-03-06T08:31:35Z","title":"Towards Efficient and Effective Unlearning of Large Language Models for Recommendation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.03536","snapshot_observed_at":"2026-08-12T05:31:00.945729Z","title":"Towards efficient and effective unlearning of large language models for recommendation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":83,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.945729Z"},"links":{"cited_paper":"/paper/2403.03536","citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:73ca40228fd0cd9a4d4263d1131cf9de1a5f5e031e5966e863a15b1bcbb7be97","observation_id":"8699662c-7eb8-45e0-a8f0-6b472f5958e6","resolution":{"observed_at":"2026-08-12T05:31:00.945729Z","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":"2026-08-12T05:31:00.950656Z","title":"Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":84,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.950656Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:056187c3b62f09c40d04d904feb9f613c6f10ea5d941ac26b0dd0de9ee095f9c","observation_id":"a16e6e49-7ff0-46a1-b299-3f883bc2b9e2","resolution":{"observed_at":"2026-08-12T05:31:00.950656Z","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":"2026-08-12T05:31:02.020812Z","title":"Graph convolution machine for context-aware recommender system","venue":null,"work_id":"c55896d0-4190-4381-a310-73ddce91c8c5","year":2022},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":85,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.955379Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:7343a26c188b939c4612a16d4175e13eefba9bf9b96375f96411d36fa9015c30","observation_id":"94f07666-bac9-4142-90f8-23201fb48fdb","resolution":{"observed_at":"2026-08-12T05:31:02.027373Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:31:02.000255Z","title":"GIF: A general graph unlearning strategy via influence function","venue":null,"work_id":"a89c9a80-9fb4-4e92-8bf0-88066aa7d7de","year":2023},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":86,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.960120Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:3c1adc49de6c09e49964c912ddf4b35c3ed10ace366df07813e3889d037a30fa","observation_id":"64701d24-7b7d-4823-9e31-5989681c066f","resolution":{"observed_at":"2026-08-12T05:31:02.007376Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:31:01.984027Z","title":"On the effectiveness of sampled softmax loss for item recommendation","venue":null,"work_id":"7206b21b-43de-479e-bf26-676087f8c533","year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":87,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.965016Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:80a62b4b7f52d49a54db4b9243b3ee37c45e4cde0dc48499b725452488a4141b","observation_id":"cb9b9798-e988-4c8f-b6e3-48fdb217e4d5","resolution":{"observed_at":"2026-08-12T05:31:01.988854Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:31:01.967933Z","title":"\\( \\) -dpo: Direct preference optimization with dynamic \\( \\)","venue":null,"work_id":"89cf73d8-f803-4c4e-910a-549147120d65","year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":88,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.970025Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:2c475126a258489974b73d5054b9fd42821e921cc544a1350f73dd356abd3974","observation_id":"462a71dc-c8c3-4865-bef3-70f47339fcf6","resolution":{"observed_at":"2026-08-12T05:31:01.973391Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:31:01.950744Z","title":"Evaluating and analyzing relationship hallucinations in large vision-language models","venue":null,"work_id":"461fc159-cc5f-4351-a86d-65027e31ee6c","year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":89,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.975452Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:bc6f30ccc635d2c3edcb60e0493c2ed0fc05a63117fd4a2884c74191fe1ece77","observation_id":"f240397b-aa13-4d13-bf65-065b0bd29ac3","resolution":{"observed_at":"2026-08-12T05:31:01.956580Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:31:01.933992Z","title":"Rethinking reinforcement learning for recommendation: A prompt perspective","venue":null,"work_id":"9c09aeda-5c6e-4e1f-bad5-ff13a0cb3c07","year":2022},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":90,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.980657Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:aa36ad84b74b787c76e7d5a6f0ddb331d55dd7e323702e196d5b3810aa53c5b5","observation_id":"206ef86b-9e74-40b4-87c2-b1afcac4e381","resolution":{"observed_at":"2026-08-12T05:31:01.939336Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.01032","last_updated":"2024-06-03T06:33:51Z","snapshot_observed_at":"2026-08-12T23:51:53.469463Z","submitted_at":"2024-06-03T06:33:51Z","title":"LLM and GNN are Complementary: Distilling LLM for Multimodal Graph Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.01032","snapshot_observed_at":"2026-08-12T05:31:00.985266Z","title":"LLM and GNN are complementary: Distilling LLM for multimodal graph learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":91,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.985266Z"},"links":{"cited_paper":"/paper/2406.01032","citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:599ab2b84e369cade8c0e43bac2062967a291e5b39c7a167e673f1dfe9cc9725","observation_id":"ca850fac-95e4-4d72-87f1-0a05833f1ce9","resolution":{"observed_at":"2026-08-12T05:31:00.985266Z","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":"2026-08-12T05:31:01.915098Z","title":"Hendler, Marzyeh Ghassemi, Anind K","venue":null,"work_id":"75c42e15-b71d-401d-b6d7-b3100069b858","year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":92,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.990040Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:e73a26e0ea844cb5dc16c9d5366ad2afdcb9e207d0bb03038006a76ccb9b3c0d","observation_id":"925a1598-ee18-4e47-9e4f-f505f632f187","resolution":{"observed_at":"2026-08-12T05:31:01.921567Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:31:00.995189Z","title":"Rehg, and Aidong Zhang","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":93,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:00.995189Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:95cd8ee15f0a9bdfc29c464224294876df16ee2c23b9ec5a9f791d4c49ba724b","observation_id":"82093e8b-6ec7-4572-93de-3c2ea04619e3","resolution":{"observed_at":"2026-08-12T05:31:00.995189Z","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":"2026-08-12T05:31:01.896722Z","title":"Unlearning bias in language models by partitioning gradients","venue":null,"work_id":"7fa261c3-897c-4189-b8b8-7ee9f06f4bdd","year":2023},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":94,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:01.000300Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:343dfc95645024ca2a2428762a2db335ef2ece5228f12db44965b1c763c4b480","observation_id":"1a4eee4f-61d2-4a73-a76e-002696f9e8f3","resolution":{"observed_at":"2026-08-12T05:31:01.903000Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:31:01.880252Z","title":"Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked language-models","venue":null,"work_id":"80f5a75d-6534-4978-bbf6-18875438a77f","year":2022},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":95,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:01.005072Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:90f0339f9b59c9a1f4e64ef76d8cbda12734b5f47e8bcbfb8e259dc6bdd6b3b2","observation_id":"8f239d14-e356-4663-8baf-53e4c5939bd1","resolution":{"observed_at":"2026-08-12T05:31:01.885631Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:31:01.862565Z","title":"When scaling meets LLM finetuning: The effect of data, model and finetuning method","venue":null,"work_id":"ee7849d4-4b9e-4d74-9c25-c4e333ba6305","year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":96,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:01.010116Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:e960a6b014c0fa4505460ac786546c987265981c04afe22d5bac8f14c6696382","observation_id":"306d8573-ba04-4ddf-ad07-94774b444aa8","resolution":{"observed_at":"2026-08-12T05:31:01.868292Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:31:01.844939Z","title":"Adaptive budget allocation for parameter-efficient fine-tuning","venue":null,"work_id":"771b510c-0bae-4687-81f7-61af8c45d149","year":2023},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":97,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:01.014789Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:65d13c2464b579653263131b3340d86eec78292cf15d21198a8032083f0c99cf","observation_id":"ceac35d2-4486-4748-b529-dcbab68f3ede","resolution":{"observed_at":"2026-08-12T05:31:01.850177Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:31:01.828377Z","title":"Personalized lora for human-centered text understanding","venue":null,"work_id":"01f6feca-4528-4bea-9a30-4a5b3849e367","year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":98,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:01.020629Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:f7147a7c3f4c1dbf409465234c32edd6efca1704e77fd2e6e8bb078f7d88fb3a","observation_id":"e010cdec-a85e-42d2-9b65-6a771edf5d56","resolution":{"observed_at":"2026-08-12T05:31:01.833340Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:31:01.811021Z","title":"Adam can converge without any modification on update rules","venue":null,"work_id":"2308bee0-1906-46a3-97e6-dd65ff25fbbd","year":2022},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":99,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:01.025741Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:e6499b43e890aa6cb42b8c81c50348f7a5a483de54fb99cb50e306e3671e813b","observation_id":"ce5d0597-6ed1-455f-8b4c-90b0aa5a22e2","resolution":{"observed_at":"2026-08-12T05:31:01.816504Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:31:01.792829Z","title":"Let me do it for you: Towards LLM empowered recommendation via tool learning","venue":null,"work_id":"5615d7e8-9be2-4c66-8796-47fd7097d9c2","year":2024},"citing_paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs","version":2},"reference_index":100,"source":"arxiv_source","source_observed_at":"2026-08-12T05:31:01.030883Z"},"links":{"citing_paper":"/paper/2412.00383"},"observation_digest":"sha256:44f74a93751eabbfb2abfa30bd529e869b6cad277e1ed282024d68c23ddb4709","observation_id":"662adcaa-5dbb-4aa4-86f8-d3e255870982","resolution":{"observed_at":"2026-08-12T05:31:01.798057Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.00383","last_updated":"2025-04-18T06:58:12Z","latest_version":2,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-12T22:25:48.667315Z","submitted_at":"2024-11-30T07:21:02Z","title":"Unified Parameter-Efficient Unlearning for LLMs"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":59,"verified_exact":2,"verified_fuzzy":39},"total_outbound_references":105},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 100 of 105 outbound references and 2 inbound Pith citation observations for arXiv:2412.00383."}