{"as_of":"2026-08-08T23:35:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b05f909693f70d507c305b26f11181ea39929a97f5b73367c60a75410bc305f4","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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":"2026-08-07T15:02:33.988579Z","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":"2026-05-23T20:58:26.222539Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2409.12914","last_updated":"2025-02-26T01:01:00Z","snapshot_observed_at":"2026-08-04T16:42:09.474306Z","submitted_at":"2024-09-19T17:10:34Z","title":"Evaluating Defences against Unsafe Feedback in RLHF","version":3},"cited_work":{"arxiv_id":"2409.12914","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2409.12914","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Defending against reverse preference attacks is difficult","venue":null,"work_id":"312b0ec6-9cb6-46be-a01c-d560a25dc6fd","year":2024},"citing_paper":{"arxiv_id":"2409.18169","last_updated":"2026-04-23T18:48:49Z","snapshot_observed_at":"2026-07-06T19:22:58.341345Z","submitted_at":"2024-09-26T17:55:22Z","title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","version":6},"reference_index":127,"source":"pdf_text","source_observed_at":"2026-05-23T20:58:16.237327Z"},"links":{"cited_paper":"/paper/2409.12914","citing_paper":"/paper/2409.18169"},"observation_digest":"sha256:f55fb984f6a62616cfa79ed8bf46eb94795d3ee0deea541a55155efb4e08957c","observation_id":"8e82f57e-685b-468d-bd22-cd7cc9d8a3d8","resolution":{"observed_at":"2026-05-23T20:58:26.224787Z","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":"2409.12914","last_updated":"2025-02-26T01:01:00Z","snapshot_observed_at":"2026-08-04T16:42:09.474306Z","submitted_at":"2024-09-19T17:10:34Z","title":"Evaluating Defences against Unsafe Feedback in RLHF","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.12914","snapshot_observed_at":"2026-08-07T15:02:33.988579Z","title":"Defending against reverse preference attacks is difficult","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.16559","last_updated":"2025-05-22T11:47:08Z","snapshot_observed_at":"2026-08-07T14:56:28.471596Z","submitted_at":"2025-05-22T11:47:08Z","title":"CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T15:02:33.988579Z"},"links":{"cited_paper":"/paper/2409.12914","citing_paper":"/paper/2505.16559"},"observation_digest":"sha256:55bee04c5662830354ed868c1475243649efc3868382415664202c114252358f","observation_id":"e78ab843-a81a-4a19-b7b2-a8e195c0841d","resolution":{"observed_at":"2026-08-07T15:02:33.988579Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2409.12914/citation-record","integrity":"/paper/2409.12914/integrity","json":"/paper/2409.12914/citation-record.json","paper":"/paper/2409.12914"},"outbound":[],"paper":{"arxiv_id":"2409.12914","last_updated":"2025-02-26T01:01:00Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-04T16:42:09.474306Z","submitted_at":"2024-09-19T17:10:34Z","title":"Evaluating Defences against Unsafe Feedback in RLHF"},"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 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2409.12914."}