{"as_of":"2026-08-09T03:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6d8b5e24a71abe6a7a9b922cc8351a97e8a4ee99411a842765579a19797f023d","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":8,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":8,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":8,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":8,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T15:32:50.198585Z","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":"2026-07-01T22:36:16.638261Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2405.03097","last_updated":"2024-05-06T01:21:50Z","snapshot_observed_at":"2026-08-08T21:46:45.885489Z","submitted_at":"2024-05-06T01:21:50Z","title":"To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.03097","snapshot_observed_at":"2026-08-07T15:32:50.198585Z","title":"arXiv preprint arXiv:2405.03097","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.14832","last_updated":"2025-05-27T08:11:40Z","snapshot_observed_at":"2026-08-07T15:26:40.910848Z","submitted_at":"2025-05-20T18:53:32Z","title":"SEPS: A Separability Measure for Robust Unlearning in LLMs","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-07T15:32:50.198585Z"},"links":{"cited_paper":"/paper/2405.03097","citing_paper":"/paper/2505.14832"},"observation_digest":"sha256:43791d4563aafaa6e9edd452090a830484f0fa049623691efa82357c7a704ff4","observation_id":"5a96a088-4e9f-48c0-99f6-f6aa636fc572","resolution":{"observed_at":"2026-08-07T15:32:50.198585Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.03097","last_updated":"2024-05-06T01:21:50Z","snapshot_observed_at":"2026-08-08T21:46:45.885489Z","submitted_at":"2024-05-06T01:21:50Z","title":"To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.03097","snapshot_observed_at":"2026-08-07T15:26:20.858559Z","title":"Barbulescu and P","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.15209","last_updated":"2025-05-31T04:26:58Z","snapshot_observed_at":"2026-08-08T00:47:46.009254Z","submitted_at":"2025-05-21T07:37:35Z","title":"DUSK: Do Not Unlearn Shared Knowledge","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:20.858559Z"},"links":{"cited_paper":"/paper/2405.03097","citing_paper":"/paper/2505.15209"},"observation_digest":"sha256:ffcaa52811833ebd3cf5895a5679817981c03a3628d8cbd455e463e3b734e74d","observation_id":"b1fb138a-1989-43de-9610-280c14f83e1c","resolution":{"observed_at":"2026-08-07T15:26:20.858559Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.03097","last_updated":"2024-05-06T01:21:50Z","snapshot_observed_at":"2026-08-08T21:46:45.885489Z","submitted_at":"2024-05-06T01:21:50Z","title":"To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.03097","snapshot_observed_at":"2026-08-07T14:29:48.640081Z","title":"and Triantafillou, P","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18786","last_updated":"2025-05-24T16:55:57Z","snapshot_observed_at":"2026-08-07T14:23:20.871121Z","submitted_at":"2025-05-24T16:55:57Z","title":"Leveraging Per-Instance Privacy for Machine Unlearning","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-07T14:29:48.640081Z"},"links":{"cited_paper":"/paper/2405.03097","citing_paper":"/paper/2505.18786"},"observation_digest":"sha256:da46e7985845a0736149b3190e3e9c849f471170ce4041b2792644593b3b67a3","observation_id":"a9536f05-ffa6-4c42-b79f-2ab5ff392a3c","resolution":{"observed_at":"2026-08-07T14:29:48.640081Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.03097","last_updated":"2024-05-06T01:21:50Z","snapshot_observed_at":"2026-08-08T21:46:45.885489Z","submitted_at":"2024-05-06T01:21:50Z","title":"To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models","version":1},"cited_work":{"arxiv_id":"2405.03097","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.03097","snapshot_observed_at":"2026-07-01T22:36:16.638261Z","title":"To each (textual sequence) its own: Im- proving memorized-data unlearning in large language models","venue":null,"work_id":"1acbad69-7ef6-44dc-b2ad-73048583eefc","year":2024},"citing_paper":{"arxiv_id":"2506.20941","last_updated":"2026-04-27T18:06:07Z","snapshot_observed_at":"2026-08-02T21:32:45.612265Z","submitted_at":"2025-06-26T02:16:16Z","title":"Revisiting the Past: Data Unlearning with Model State History","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-19T08:12:19.391973Z"},"links":{"cited_paper":"/paper/2405.03097","citing_paper":"/paper/2506.20941"},"observation_digest":"sha256:2474a31090881381f00a079c0c5c9df94ea27fe4db2d18b2bdcc0730c290de5b","observation_id":"2a3e9d3b-8608-4572-84a0-3fa052071026","resolution":{"observed_at":"2026-05-19T08:13:01.661830Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.03097","last_updated":"2024-05-06T01:21:50Z","snapshot_observed_at":"2026-08-08T21:46:45.885489Z","submitted_at":"2024-05-06T01:21:50Z","title":"To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.03097","snapshot_observed_at":"2026-08-06T11:42:04.273571Z","title":"Barbulescu and P","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.22499","last_updated":"2025-07-30T09:12:25Z","snapshot_observed_at":"2026-08-07T22:01:09.686657Z","submitted_at":"2025-07-30T09:12:25Z","title":"LoReUn: Data Itself Implicitly Provides Cues to Improve Machine Unlearning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T11:42:04.273571Z"},"links":{"cited_paper":"/paper/2405.03097","citing_paper":"/paper/2507.22499"},"observation_digest":"sha256:6ee55638ab06b9a30c6b7ae38f2a47d9496bd8a7fe6db0a613323e08c1f8f183","observation_id":"c8b7f019-1f94-4bd4-8427-1eea7130aae6","resolution":{"observed_at":"2026-08-06T11:42:04.273571Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.03097","last_updated":"2024-05-06T01:21:50Z","snapshot_observed_at":"2026-08-08T21:46:45.885489Z","submitted_at":"2024-05-06T01:21:50Z","title":"To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models","version":1},"cited_work":{"arxiv_id":"2405.03097","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.03097","snapshot_observed_at":"2026-07-01T22:36:16.638261Z","title":"To each (textual sequence) its own: Im- proving memorized-data unlearning in large language models","venue":null,"work_id":"1acbad69-7ef6-44dc-b2ad-73048583eefc","year":2024},"citing_paper":{"arxiv_id":"2604.07962","last_updated":"2026-04-09T08:24:52Z","snapshot_observed_at":"2026-07-06T22:57:09.435331Z","submitted_at":"2026-04-09T08:24:52Z","title":"Is your algorithm unlearning or untraining?","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-10T18:06:08.962042Z"},"links":{"cited_paper":"/paper/2405.03097","citing_paper":"/paper/2604.07962"},"observation_digest":"sha256:407dab9a93618bf16f76175af65baf15fef0090feeede7c59f8a9fb31a41b586","observation_id":"7d2df039-75f8-48f8-9020-21413d16fed7","resolution":{"observed_at":"2026-05-11T05:30:59.187102Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.03097","last_updated":"2024-05-06T01:21:50Z","snapshot_observed_at":"2026-08-08T21:46:45.885489Z","submitted_at":"2024-05-06T01:21:50Z","title":"To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models","version":1},"cited_work":{"arxiv_id":"2405.03097","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.03097","snapshot_observed_at":"2026-07-01T22:36:16.638261Z","title":"To each (textual sequence) its own: Im- proving memorized-data unlearning in large language models","venue":null,"work_id":"1acbad69-7ef6-44dc-b2ad-73048583eefc","year":2024},"citing_paper":{"arxiv_id":"2604.13777","last_updated":"2026-04-15T12:07:14Z","snapshot_observed_at":"2026-07-06T23:01:41.643335Z","submitted_at":"2026-04-15T12:07:14Z","title":"From Anchors to Supervision: Memory-Graph Guided Corpus-Free Unlearning for Large Language Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-10T14:15:16.795281Z"},"links":{"cited_paper":"/paper/2405.03097","citing_paper":"/paper/2604.13777"},"observation_digest":"sha256:2ecd01bad73f51d354f624a82bfb522b7f2ac223838764fd5e4719ecc3bd0b0a","observation_id":"978d1c27-de26-46c6-891d-b4a60997c2a2","resolution":{"observed_at":"2026-05-10T14:15:28.915662Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.03097","last_updated":"2024-05-06T01:21:50Z","snapshot_observed_at":"2026-08-08T21:46:45.885489Z","submitted_at":"2024-05-06T01:21:50Z","title":"To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models","version":1},"cited_work":{"arxiv_id":"2405.03097","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.03097","snapshot_observed_at":"2026-07-01T22:36:16.638261Z","title":"To each (textual sequence) its own: Im- proving memorized-data unlearning in large language models","venue":null,"work_id":"1acbad69-7ef6-44dc-b2ad-73048583eefc","year":2024},"citing_paper":{"arxiv_id":"2606.02453","last_updated":"2026-06-01T16:25:10Z","snapshot_observed_at":"2026-08-02T22:48:07.065976Z","submitted_at":"2026-06-01T16:25:10Z","title":"Initialization is Half the Battle: Generating Diverse Images from a Guidance Potential Posterior","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-06-28T15:19:32.238094Z"},"links":{"cited_paper":"/paper/2405.03097","citing_paper":"/paper/2606.02453"},"observation_digest":"sha256:f3fc86c0c1d93f7fd7680e774b49bed92c992b434850483e49d3ebf1ed3763b6","observation_id":"4bc62c46-6612-4655-a7f2-d6e11f980404","resolution":{"observed_at":"2026-07-01T22:36:16.640373Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2405.03097/citation-record","integrity":"/paper/2405.03097/integrity","json":"/paper/2405.03097/citation-record.json","paper":"/paper/2405.03097"},"outbound":[],"paper":{"arxiv_id":"2405.03097","last_updated":"2024-05-06T01:21:50Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-08T21:46:45.885489Z","submitted_at":"2024-05-06T01:21:50Z","title":"To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 8 inbound Pith citation observations for arXiv:2405.03097."}