{"as_of":"2026-08-14T02:45:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0e2901d19825deebf45b783b8c48a7235c64f67426814dba57546388fe262cf5","coverage":[{"denominator":31,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":31,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T23:27:37.796703Z","state":"measured"},{"denominator":31,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":31,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2412.20412/citation-record","integrity":"/paper/2412.20412/integrity","json":"/paper/2412.20412/citation-record.json","paper":"/paper/2412.20412"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2212.08073","last_updated":"2022-12-15T06:19:23Z","snapshot_observed_at":"2026-08-02T04:53:58.766070Z","submitted_at":"2022-12-15T06:19:23Z","title":"Constitutional AI: Harmlessness from AI Feedback","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.08073","snapshot_observed_at":"2026-08-10T23:27:37.640279Z","title":"Constitutional ai: Harmlessness from ai feedback,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.20412","last_updated":"2025-01-04T13:27:04Z","snapshot_observed_at":"2026-08-11T14:46:48.771691Z","submitted_at":"2024-12-29T09:35:56Z","title":"Multi-Objective Large Language Model Unlearning","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T23:27:37.640279Z"},"links":{"cited_paper":"/paper/2212.08073","citing_paper":"/paper/2412.20412"},"observation_digest":"sha256:b895e25046253c7737f24ddbc2dac76fc54021b3bbd73c53bfbced642c842316","observation_id":"33a9d9b1-5a6b-4f47-a40b-b6bfb7d47ebb","resolution":{"observed_at":"2026-08-10T23:27:37.640279Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.09363","last_updated":"2024-06-04T21:07:11Z","snapshot_observed_at":"2026-08-13T04:18:54.194241Z","submitted_at":"2024-02-14T18:09:53Z","title":"Copyright Traps for Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.09363","snapshot_observed_at":"2026-08-10T23:27:37.646725Z","title":"Copyright traps for large language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.20412","last_updated":"2025-01-04T13:27:04Z","snapshot_observed_at":"2026-08-11T14:46:48.771691Z","submitted_at":"2024-12-29T09:35:56Z","title":"Multi-Objective Large Language Model Unlearning","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T23:27:37.646725Z"},"links":{"cited_paper":"/paper/2402.09363","citing_paper":"/paper/2412.20412"},"observation_digest":"sha256:63df2b89d897300bce909413d4125343f2603d12fb286ddf94da9bc07c2b56b3","observation_id":"f1ffd72f-fce4-4248-a380-063a20d7dd5e","resolution":{"observed_at":"2026-08-10T23:27:37.646725Z","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":"2026-08-10T23:27:38.351864Z","title":"Towards mitigating llm hallucination via self reflection,","venue":null,"work_id":"f1647e72-92f7-40f6-9d7b-d8a6f5306621","year":2023},"citing_paper":{"arxiv_id":"2412.20412","last_updated":"2025-01-04T13:27:04Z","snapshot_observed_at":"2026-08-11T14:46:48.771691Z","submitted_at":"2024-12-29T09:35:56Z","title":"Multi-Objective Large Language Model Unlearning","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T23:27:37.652372Z"},"links":{"citing_paper":"/paper/2412.20412"},"observation_digest":"sha256:f31cb43d09bb81238d57a394a039b5209a8b4777794b96d924e8732228f72fd2","observation_id":"3e49c09b-c82f-4413-a0b9-b7be2953538f","resolution":{"observed_at":"2026-08-10T23:27:38.356897Z","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":"2026-08-10T23:27:38.337152Z","title":"Privacy and data protection in chatgpt and other ai chatbots: strategies for securing user information,","venue":null,"work_id":"f09b1dc6-9001-47cd-9f57-9e9e90bbac50","year":2023},"citing_paper":{"arxiv_id":"2412.20412","last_updated":"2025-01-04T13:27:04Z","snapshot_observed_at":"2026-08-11T14:46:48.771691Z","submitted_at":"2024-12-29T09:35:56Z","title":"Multi-Objective Large Language Model Unlearning","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T23:27:37.658416Z"},"links":{"citing_paper":"/paper/2412.20412"},"observation_digest":"sha256:b1854680034fe1725e367a038be03548bc2a97c9e52e3ff6a8b3afdbe98dfc58","observation_id":"7d990619-5a40-459e-8767-3256fb66e877","resolution":{"observed_at":"2026-08-10T23:27:38.341873Z","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":"2026-08-10T23:27:38.322363Z","title":"Firewallm: A portable data protection and recovery framework for llm services,","venue":null,"work_id":"dfd3d435-dadd-4e9e-9a88-a708e2108133","year":2023},"citing_paper":{"arxiv_id":"2412.20412","last_updated":"2025-01-04T13:27:04Z","snapshot_observed_at":"2026-08-11T14:46:48.771691Z","submitted_at":"2024-12-29T09:35:56Z","title":"Multi-Objective Large Language Model Unlearning","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T23:27:37.663387Z"},"links":{"citing_paper":"/paper/2412.20412"},"observation_digest":"sha256:2b7e2bae9b2f72067d90c6d81b460b32726c7ac577ccfa79ece3019a0b7868e0","observation_id":"7bbdb462-4e5b-450f-95c6-2c7ec7584ac8","resolution":{"observed_at":"2026-08-10T23:27:38.327308Z","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":"2310.10683","last_updated":"2024-02-16T19:47:36Z","snapshot_observed_at":"2026-08-13T05:49:30.329434Z","submitted_at":"2023-10-14T00:32:55Z","title":"Large Language Model Unlearning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.10683","snapshot_observed_at":"2026-08-10T23:27:37.668920Z","title":"Large language model unlearning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.20412","last_updated":"2025-01-04T13:27:04Z","snapshot_observed_at":"2026-08-11T14:46:48.771691Z","submitted_at":"2024-12-29T09:35:56Z","title":"Multi-Objective Large Language Model Unlearning","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T23:27:37.668920Z"},"links":{"cited_paper":"/paper/2310.10683","citing_paper":"/paper/2412.20412"},"observation_digest":"sha256:8aae02fe121a8bb3d0c3661cd600ab90b068fd699ed0ebeabf4ce3f2f56d9cc7","observation_id":"fbdfaf40-281d-471f-9a68-54eebda3aaa2","resolution":{"observed_at":"2026-08-10T23:27:37.668920Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-10T23:27:37.675085Z","title":"Rethinking machine unlearning for large language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.20412","last_updated":"2025-01-04T13:27:04Z","snapshot_observed_at":"2026-08-11T14:46:48.771691Z","submitted_at":"2024-12-29T09:35:56Z","title":"Multi-Objective Large Language Model Unlearning","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T23:27:37.675085Z"},"links":{"cited_paper":"/paper/2402.08787","citing_paper":"/paper/2412.20412"},"observation_digest":"sha256:9eec832bf486fbdd2422d0a749e20492e89d66139bfc6351d2ee9a17dcc57f7a","observation_id":"d148ccbc-3443-467b-ae44-7209132950ff","resolution":{"observed_at":"2026-08-10T23:27:37.675085Z","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":"2026-08-10T23:27:38.306951Z","title":"Efuf: Efficient fine-grained unlearning framework for mitigating hallucinations in multimodal large language models,","venue":null,"work_id":"0d25e9d0-149b-431d-87a1-d8387f067569","year":2024},"citing_paper":{"arxiv_id":"2412.20412","last_updated":"2025-01-04T13:27:04Z","snapshot_observed_at":"2026-08-11T14:46:48.771691Z","submitted_at":"2024-12-29T09:35:56Z","title":"Multi-Objective Large Language Model Unlearning","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T23:27:37.680663Z"},"links":{"citing_paper":"/paper/2412.20412"},"observation_digest":"sha256:3e21142220d7ef6cfd41f8f58852b24727d9b399b02c7f6f6bfe6812cc09dcea","observation_id":"46abda67-5e2d-471c-b194-3a98f6ac28cf","resolution":{"observed_at":"2026-08-10T23:27:38.312274Z","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":"2406.10952","last_updated":"2025-02-11T01:46:13Z","snapshot_observed_at":"2026-08-12T23:41:44.737311Z","submitted_at":"2024-06-16T14:12:37Z","title":"Avoiding Copyright Infringement via Large Language Model Unlearning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.10952","snapshot_observed_at":"2026-08-10T23:27:37.686292Z","title":"Avoiding copyright infringement via machine unlearning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.20412","last_updated":"2025-01-04T13:27:04Z","snapshot_observed_at":"2026-08-11T14:46:48.771691Z","submitted_at":"2024-12-29T09:35:56Z","title":"Multi-Objective Large Language Model Unlearning","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T23:27:37.686292Z"},"links":{"cited_paper":"/paper/2406.10952","citing_paper":"/paper/2412.20412"},"observation_digest":"sha256:ff46673fca59ab9c37cb641f6a6c1608e2827993ee5c59ef13ab3fe1447d51c4","observation_id":"ca05832e-3197-4170-8ffb-9cdac1e532ae","resolution":{"observed_at":"2026-08-10T23:27:37.686292Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.20150","last_updated":"2023-10-31T03:35:59Z","snapshot_observed_at":"2026-08-13T05:36:58.902617Z","submitted_at":"2023-10-31T03:35:59Z","title":"Unlearn What You Want to Forget: Efficient Unlearning for LLMs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.20150","snapshot_observed_at":"2026-08-10T23:27:37.691587Z","title":"Unlearn what you want to forget: Efficient unlearning for llms,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.20412","last_updated":"2025-01-04T13:27:04Z","snapshot_observed_at":"2026-08-11T14:46:48.771691Z","submitted_at":"2024-12-29T09:35:56Z","title":"Multi-Objective Large Language Model Unlearning","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T23:27:37.691587Z"},"links":{"cited_paper":"/paper/2310.20150","citing_paper":"/paper/2412.20412"},"observation_digest":"sha256:5d0e14714df4953c5f1a5db0b576281f97d60b9737f4c89fb5fe49065e7e74c4","observation_id":"70caa778-1a13-459f-aa3d-ef593e15192f","resolution":{"observed_at":"2026-08-10T23:27:37.691587Z","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":"2026-08-10T23:27:37.697461Z","title":"In-context unlearning: Lan- guage models as few shot unlearners,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.20412","last_updated":"2025-01-04T13:27:04Z","snapshot_observed_at":"2026-08-11T14:46:48.771691Z","submitted_at":"2024-12-29T09:35:56Z","title":"Multi-Objective Large Language Model Unlearning","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T23:27:37.697461Z"},"links":{"cited_paper":"/paper/2310.07579","citing_paper":"/paper/2412.20412"},"observation_digest":"sha256:e70b03ccc4303cc8082008f66721b3786f6d3bc01d64ed630814cf4d08f520c2","observation_id":"6c604a7d-d661-4455-897b-13ff31d233a5","resolution":{"observed_at":"2026-08-10T23:27:37.697461Z","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":"2026-08-10T23:27:37.702752Z","title":"Formalizing and bench- marking prompt injection attacks and defenses,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.20412","last_updated":"2025-01-04T13:27:04Z","snapshot_observed_at":"2026-08-11T14:46:48.771691Z","submitted_at":"2024-12-29T09:35:56Z","title":"Multi-Objective Large Language Model Unlearning","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T23:27:37.702752Z"},"links":{"citing_paper":"/paper/2412.20412"},"observation_digest":"sha256:9d8fbb9ddba5b553d8bfb823040178aa80cd7d3f3d13e5e5b725ba6470681793","observation_id":"7b462e9e-fec7-4ab0-b0ec-9522e0ae1d77","resolution":{"observed_at":"2026-08-10T23:27:37.702752Z","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":"2026-08-10T23:27:37.707677Z","title":"Who’s harry potter? approximate unlearning in llms,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.20412","last_updated":"2025-01-04T13:27:04Z","snapshot_observed_at":"2026-08-11T14:46:48.771691Z","submitted_at":"2024-12-29T09:35:56Z","title":"Multi-Objective Large Language Model Unlearning","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T23:27:37.707677Z"},"links":{"cited_paper":"/paper/2310.02238","citing_paper":"/paper/2412.20412"},"observation_digest":"sha256:c51ba4af23595ecebde9348fab2dcb86cac520117883132ad23f44213ed940d7","observation_id":"c8357770-320c-4aa5-b8b7-a79f64ef382b","resolution":{"observed_at":"2026-08-10T23:27:37.707677Z","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":"2026-08-10T23:27:38.292354Z","title":"Training language models to fol- low instructions with human feedback,","venue":null,"work_id":"099d2563-7456-430e-b7bd-209e8ec86820","year":2022},"citing_paper":{"arxiv_id":"2412.20412","last_updated":"2025-01-04T13:27:04Z","snapshot_observed_at":"2026-08-11T14:46:48.771691Z","submitted_at":"2024-12-29T09:35:56Z","title":"Multi-Objective Large Language Model Unlearning","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T23:27:37.712562Z"},"links":{"citing_paper":"/paper/2412.20412"},"observation_digest":"sha256:407aab145e192543b5f642a95ba73520ac115dd02d5355d3847aeea9c9229021","observation_id":"36e53f8e-b412-4ad6-94b0-e8ff173949b5","resolution":{"observed_at":"2026-08-10T23:27:38.297207Z","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":"2309.00267","last_updated":"2024-09-03T14:01:54Z","snapshot_observed_at":"2026-07-06T16:13:07.384791Z","submitted_at":"2023-09-01T05:53:33Z","title":"RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.00267","snapshot_observed_at":"2026-08-10T23:27:37.717148Z","title":"Rlaif: Scaling reinforce- ment learning from human feedback with ai feedback,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.20412","last_updated":"2025-01-04T13:27:04Z","snapshot_observed_at":"2026-08-11T14:46:48.771691Z","submitted_at":"2024-12-29T09:35:56Z","title":"Multi-Objective Large Language Model Unlearning","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T23:27:37.717148Z"},"links":{"cited_paper":"/paper/2309.00267","citing_paper":"/paper/2412.20412"},"observation_digest":"sha256:b4eb242594df1f45d1f22d8cd86869da5b3173786f02bdaf414f71e8177aec35","observation_id":"f6f314ed-ac70-4431-b3ef-87af8c9691a3","resolution":{"observed_at":"2026-08-10T23:27:37.717148Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.14339","last_updated":"2024-03-21T12:11:26Z","snapshot_observed_at":"2026-08-13T00:48:44.841703Z","submitted_at":"2024-03-21T12:11:26Z","title":"$\\nabla \\tau$: Gradient-based and Task-Agnostic machine Unlearning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.14339","snapshot_observed_at":"2026-08-10T23:27:37.722482Z","title":"∇τ: Gradient-based and task-agnostic machine unlearning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.20412","last_updated":"2025-01-04T13:27:04Z","snapshot_observed_at":"2026-08-11T14:46:48.771691Z","submitted_at":"2024-12-29T09:35:56Z","title":"Multi-Objective Large Language Model Unlearning","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T23:27:37.722482Z"},"links":{"cited_paper":"/paper/2403.14339","citing_paper":"/paper/2412.20412"},"observation_digest":"sha256:5952f117b4cdb4c8b2bac964e2c324b48e3eae06efd159e4908e072c239ae62c","observation_id":"ddc37edb-ff56-47aa-9f60-3289bcef070d","resolution":{"observed_at":"2026-08-10T23:27:37.722482Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.09391","last_updated":"2024-06-13T17:59:06Z","snapshot_observed_at":"2026-08-14T02:25:00.395812Z","submitted_at":"2024-06-13T17:59:06Z","title":"A More Practical Approach to Machine Unlearning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.09391","snapshot_observed_at":"2026-08-10T23:27:37.727771Z","title":"A more practical approach to machine unlearning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.20412","last_updated":"2025-01-04T13:27:04Z","snapshot_observed_at":"2026-08-11T14:46:48.771691Z","submitted_at":"2024-12-29T09:35:56Z","title":"Multi-Objective Large Language Model Unlearning","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T23:27:37.727771Z"},"links":{"cited_paper":"/paper/2406.09391","citing_paper":"/paper/2412.20412"},"observation_digest":"sha256:d85579bf7ebf259ba8014e51ebbe378705f79a855c39d426e29032a19288e918","observation_id":"fb0c41cd-55c5-46a1-91a9-d91cd821d78a","resolution":{"observed_at":"2026-08-10T23:27:37.727771Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2207.05521","last_updated":"2023-10-20T19:57:54Z","snapshot_observed_at":"2026-08-14T02:07:33.249781Z","submitted_at":"2022-07-12T13:24:23Z","title":"Federated Unlearning: How to Efficiently Erase a Client in FL?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.05521","snapshot_observed_at":"2026-08-10T23:27:37.732824Z","title":"Federated unlearning: How to efficiently erase a client in fl?","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.20412","last_updated":"2025-01-04T13:27:04Z","snapshot_observed_at":"2026-08-11T14:46:48.771691Z","submitted_at":"2024-12-29T09:35:56Z","title":"Multi-Objective Large Language Model Unlearning","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T23:27:37.732824Z"},"links":{"cited_paper":"/paper/2207.05521","citing_paper":"/paper/2412.20412"},"observation_digest":"sha256:3455b9909e2685e3336345a3e8be2e4cbe697d32671ee5f9de77e325dae99723","observation_id":"1a8416db-f3a2-481e-ad0b-db1053766c1c","resolution":{"observed_at":"2026-08-10T23:27:37.732824Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.09880","last_updated":"2023-10-30T10:14:02Z","snapshot_observed_at":"2026-08-13T12:41:00.773129Z","submitted_at":"2023-02-20T10:15:36Z","title":"Towards Unbounded Machine Unlearning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.09880","snapshot_observed_at":"2026-08-10T23:27:37.737596Z","title":"Towards unbounded machine unlearning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.20412","last_updated":"2025-01-04T13:27:04Z","snapshot_observed_at":"2026-08-11T14:46:48.771691Z","submitted_at":"2024-12-29T09:35:56Z","title":"Multi-Objective Large Language Model Unlearning","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T23:27:37.737596Z"},"links":{"cited_paper":"/paper/2302.09880","citing_paper":"/paper/2412.20412"},"observation_digest":"sha256:06d91afa8cc7ec0a807b431883270483ad0b02b478878145087b44db2933a0ea","observation_id":"9a73e739-16e3-41b2-b0fe-ea773c4c1740","resolution":{"observed_at":"2026-08-10T23:27:37.737596Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.15513","last_updated":"2025-06-14T16:04:31Z","snapshot_observed_at":"2026-08-12T23:38:02.782103Z","submitted_at":"2024-06-20T18:37:36Z","title":"PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.15513","snapshot_observed_at":"2026-08-10T23:27:37.742460Z","title":"Pku-saferlhf: A safety alignment preference dataset for llama family models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.20412","last_updated":"2025-01-04T13:27:04Z","snapshot_observed_at":"2026-08-11T14:46:48.771691Z","submitted_at":"2024-12-29T09:35:56Z","title":"Multi-Objective Large Language Model Unlearning","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T23:27:37.742460Z"},"links":{"cited_paper":"/paper/2406.15513","citing_paper":"/paper/2412.20412"},"observation_digest":"sha256:24471b074aa267a2f42e013a8afda0bf02b207c1a6c9eebbe80aa36e1809f39b","observation_id":"1c2e0654-df77-4799-972b-b57bcfff8d00","resolution":{"observed_at":"2026-08-10T23:27:37.742460Z","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":"2026-08-10T23:27:38.276076Z","title":"Steepest descent methods for multicriteria optimization,","venue":null,"work_id":"ad1d2ab3-114c-4c12-b696-ba29a03ccdec","year":2000},"citing_paper":{"arxiv_id":"2412.20412","last_updated":"2025-01-04T13:27:04Z","snapshot_observed_at":"2026-08-11T14:46:48.771691Z","submitted_at":"2024-12-29T09:35:56Z","title":"Multi-Objective Large Language Model Unlearning","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T23:27:37.748206Z"},"links":{"citing_paper":"/paper/2412.20412"},"observation_digest":"sha256:59ca7fc77c7131430b6949f73d2427774d951945dd5b941f1c572335372b26f0","observation_id":"c883c3c5-128a-4c4e-9036-4e0332e8e985","resolution":{"observed_at":"2026-08-10T23:27:38.281649Z","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":"2026-08-10T23:27:38.258008Z","title":"Fedmdfg: Federated learning with multi-gradient descent and fair guidance,","venue":null,"work_id":"f3640ba1-c63b-4082-bba0-754b8955798d","year":2023},"citing_paper":{"arxiv_id":"2412.20412","last_updated":"2025-01-04T13:27:04Z","snapshot_observed_at":"2026-08-11T14:46:48.771691Z","submitted_at":"2024-12-29T09:35:56Z","title":"Multi-Objective Large Language Model Unlearning","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T23:27:37.753565Z"},"links":{"citing_paper":"/paper/2412.20412"},"observation_digest":"sha256:542ddf54248d25ce8bad9afcf2a3886250e15e39b54bb96d7a34f3fa4952cd99","observation_id":"9b226c97-0bae-4bba-b36c-1da3f7ef7169","resolution":{"observed_at":"2026-08-10T23:27:38.263696Z","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":"2026-08-10T23:27:38.242889Z","title":"Fedlf: Layer-wise fair federated learn- ing,","venue":null,"work_id":"24261954-e231-42e8-ae19-a7ecb76933ac","year":2024},"citing_paper":{"arxiv_id":"2412.20412","last_updated":"2025-01-04T13:27:04Z","snapshot_observed_at":"2026-08-11T14:46:48.771691Z","submitted_at":"2024-12-29T09:35:56Z","title":"Multi-Objective Large Language Model Unlearning","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T23:27:37.758433Z"},"links":{"citing_paper":"/paper/2412.20412"},"observation_digest":"sha256:ee0044fab5ca8f1806344f0b110e688d2cdf06506ece8546bb649fdb6eee6e0b","observation_id":"36791047-362a-4c63-8d8c-b66ff462d1ed","resolution":{"observed_at":"2026-08-10T23:27:38.247717Z","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":"2026-08-10T23:27:38.227174Z","title":"Polyhedral geometry and linear optimization,","venue":null,"work_id":"cbb54892-36fe-4774-8c07-a7f9cbeb7ade","year":2010},"citing_paper":{"arxiv_id":"2412.20412","last_updated":"2025-01-04T13:27:04Z","snapshot_observed_at":"2026-08-11T14:46:48.771691Z","submitted_at":"2024-12-29T09:35:56Z","title":"Multi-Objective Large Language Model Unlearning","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T23:27:37.763015Z"},"links":{"citing_paper":"/paper/2412.20412"},"observation_digest":"sha256:b12779055b725757a60658e1a7f13725ea215ce9f4800a18d948d2940b385497","observation_id":"c9a2e506-8b5f-43e5-bff3-ef368a6884b7","resolution":{"observed_at":"2026-08-10T23:27:38.232387Z","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":"2026-08-10T23:27:38.211897Z","title":null,"venue":null,"work_id":"8055b879-8c15-413b-b029-d105913d6112","year":2013},"citing_paper":{"arxiv_id":"2412.20412","last_updated":"2025-01-04T13:27:04Z","snapshot_observed_at":"2026-08-11T14:46:48.771691Z","submitted_at":"2024-12-29T09:35:56Z","title":"Multi-Objective Large Language Model Unlearning","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T23:27:37.767468Z"},"links":{"citing_paper":"/paper/2412.20412"},"observation_digest":"sha256:e3013d1b1d8833f88fbfc94bd99149192f8e60026cef1a7bcee16e19ffa406d8","observation_id":"113df591-b060-40c1-917d-d9be0d1ae031","resolution":{"observed_at":"2026-08-10T23:27:38.216572Z","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":"2026-08-10T23:27:38.195277Z","title":"Beavertails: Towards improved safety alignment of llm via a human-preference dataset,","venue":null,"work_id":"21e70c61-95e2-4cc4-9b80-218fe49993df","year":2024},"citing_paper":{"arxiv_id":"2412.20412","last_updated":"2025-01-04T13:27:04Z","snapshot_observed_at":"2026-08-11T14:46:48.771691Z","submitted_at":"2024-12-29T09:35:56Z","title":"Multi-Objective Large Language Model Unlearning","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T23:27:37.772204Z"},"links":{"citing_paper":"/paper/2412.20412"},"observation_digest":"sha256:19499db9864dc9409340d22623b1ebc19088603e3265edb10019e63dfcb7df53","observation_id":"4ec4aac2-040e-4e57-a0e9-4caf45030007","resolution":{"observed_at":"2026-08-10T23:27:38.200956Z","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":"2026-08-10T23:27:37.777114Z","title":"Orthogonal gradient descent for continual learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.20412","last_updated":"2025-01-04T13:27:04Z","snapshot_observed_at":"2026-08-11T14:46:48.771691Z","submitted_at":"2024-12-29T09:35:56Z","title":"Multi-Objective Large Language Model Unlearning","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T23:27:37.777114Z"},"links":{"citing_paper":"/paper/2412.20412"},"observation_digest":"sha256:f15142a78871fefb49bc424131ba1a1b93bc812e1727c774c3976ad50b36d1f9","observation_id":"34bda88f-024d-42dc-b023-092709e02464","resolution":{"observed_at":"2026-08-10T23:27:37.777114Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.12320","last_updated":"2023-05-21T02:37:26Z","snapshot_observed_at":"2026-08-13T12:52:05.463587Z","submitted_at":"2023-05-21T02:37:26Z","title":"Random Relabeling for Efficient Machine Unlearning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.12320","snapshot_observed_at":"2026-08-10T23:27:37.781623Z","title":"Random relabeling for efficient machine unlearning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.20412","last_updated":"2025-01-04T13:27:04Z","snapshot_observed_at":"2026-08-11T14:46:48.771691Z","submitted_at":"2024-12-29T09:35:56Z","title":"Multi-Objective Large Language Model Unlearning","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T23:27:37.781623Z"},"links":{"cited_paper":"/paper/2305.12320","citing_paper":"/paper/2412.20412"},"observation_digest":"sha256:32884716695939bd8e8d7559d90f8b531670fd8394e7faa79af3e67f00946888","observation_id":"af876fb0-4f54-4f0c-9f70-11b1f367ab7e","resolution":{"observed_at":"2026-08-10T23:27:37.781623Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-10T23:27:37.787518Z","title":"Llama: Open and efficient foundation language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.20412","last_updated":"2025-01-04T13:27:04Z","snapshot_observed_at":"2026-08-11T14:46:48.771691Z","submitted_at":"2024-12-29T09:35:56Z","title":"Multi-Objective Large Language Model Unlearning","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T23:27:37.787518Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2412.20412"},"observation_digest":"sha256:0efb230a88ea5a40bbb3acb0cfcc7469cbe2cf8e5e023fee4428ea55a810ba38","observation_id":"ffd8d084-fa4b-4ef6-bf59-c99269c30626","resolution":{"observed_at":"2026-08-10T23:27:37.787518Z","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":"2026-08-10T23:27:37.792281Z","title":"Detoxify,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.20412","last_updated":"2025-01-04T13:27:04Z","snapshot_observed_at":"2026-08-11T14:46:48.771691Z","submitted_at":"2024-12-29T09:35:56Z","title":"Multi-Objective Large Language Model Unlearning","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T23:27:37.792281Z"},"links":{"citing_paper":"/paper/2412.20412"},"observation_digest":"sha256:51e8b904243ee2392033076f65dad5566f18522eb37d0caf82c380b29670bde6","observation_id":"915260fe-13f6-49e3-b797-6a5068a1f6aa","resolution":{"observed_at":"2026-08-10T23:27:37.792281Z","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":"2026-08-10T23:27:38.157400Z","title":"A contrastive framework for neural text generation,","venue":null,"work_id":"d7824e98-81b1-494e-ad0b-f2ddec689be6","year":2022},"citing_paper":{"arxiv_id":"2412.20412","last_updated":"2025-01-04T13:27:04Z","snapshot_observed_at":"2026-08-11T14:46:48.771691Z","submitted_at":"2024-12-29T09:35:56Z","title":"Multi-Objective Large Language Model Unlearning","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T23:27:37.796703Z"},"links":{"citing_paper":"/paper/2412.20412"},"observation_digest":"sha256:1f54a785d9440e0316b7ba3b25fe2eadb47a8a1a1cd26c2b0c9543a1b11f8571","observation_id":"75afe604-d904-4175-8226-ea80a9e5e898","resolution":{"observed_at":"2026-08-10T23:27:38.164833Z","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":"2412.20412","last_updated":"2025-01-04T13:27:04Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-11T14:46:48.771691Z","submitted_at":"2024-12-29T09:35:56Z","title":"Multi-Objective Large Language Model Unlearning"},"reference_resolution":{"displayed":31,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":20,"verified_exact":0,"verified_fuzzy":11},"total_outbound_references":31},"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 14 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 0 inbound Pith citation observations for arXiv:2412.20412."}