{"as_of":"2026-08-09T19:19:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:dbce262769e08f1089c4cc30b04ad35ae7ffd172336b29d32d519f6e96c5a143","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":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T18:10:53.340865Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-06T16:44:52.425401Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2410.04166","last_updated":"2025-03-07T10:51:04Z","snapshot_observed_at":"2026-08-08T12:24:13.216966Z","submitted_at":"2024-10-05T14:04:03Z","title":"Learning from negative feedback, or positive feedback or both","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.04166","snapshot_observed_at":"2026-08-08T18:10:53.340865Z","title":"T., Hertweck, T., Joshi, R., Oh, J., Bloesch, M., Lampe, T., Heess, N., et al","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.05773","last_updated":"2025-07-24T22:59:42Z","snapshot_observed_at":"2026-08-09T13:54:38.102857Z","submitted_at":"2025-02-09T04:31:30Z","title":"PIPA: Preference Alignment as Prior-Informed Statistical Estimation","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-08T18:10:53.340865Z"},"links":{"cited_paper":"/paper/2410.04166","citing_paper":"/paper/2502.05773"},"observation_digest":"sha256:e0dab51db9a4913ed150c2718f51a299f4fa092bd76a1ebcc83c36bf4128efe9","observation_id":"a869fe09-2ea4-4a9f-a322-c1eff8008cb4","resolution":{"observed_at":"2026-08-08T18:10:53.340865Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.04166","last_updated":"2025-03-07T10:51:04Z","snapshot_observed_at":"2026-08-08T12:24:13.216966Z","submitted_at":"2024-10-05T14:04:03Z","title":"Learning from negative feedback, or positive feedback or both","version":3},"cited_work":{"arxiv_id":"2410.04166","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.04166","snapshot_observed_at":"2026-08-06T16:44:52.425401Z","title":"Learning from negative feedback, or positive feedback or both","venue":"cs.LG","work_id":"99760e95-1f53-4558-a988-f02730abd6f8","year":2024},"citing_paper":{"arxiv_id":"2507.12856","last_updated":"2025-09-06T23:54:03Z","snapshot_observed_at":"2026-08-09T00:47:01.931226Z","submitted_at":"2025-07-17T07:26:54Z","title":"Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-06T16:44:46.237472Z"},"links":{"cited_paper":"/paper/2410.04166","citing_paper":"/paper/2507.12856"},"observation_digest":"sha256:275441529b67df1346d7534a27215c6203916d666e261a0631dc717fe6efdc35","observation_id":"bfb073a7-0f9e-4f28-a85d-514a64fbb332","resolution":{"observed_at":"2026-08-06T16:44:52.510853Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2410.04166/citation-record","integrity":"/paper/2410.04166/integrity","json":"/paper/2410.04166/citation-record.json","paper":"/paper/2410.04166"},"outbound":[],"paper":{"arxiv_id":"2410.04166","last_updated":"2025-03-07T10:51:04Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-08T12:24:13.216966Z","submitted_at":"2024-10-05T14:04:03Z","title":"Learning from negative feedback, or positive feedback or both"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2410.04166."}