{"as_of":"2026-08-08T14:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2aaab010d02fc050667f95198216ca7460d4c59d999059116727da82e1f6ab5c","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T12:50:42.595875Z","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":"2026-05-22T01:10:51.594672Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2312.00267","last_updated":"2025-03-20T14:23:17Z","snapshot_observed_at":"2026-07-06T16:55:25.413169Z","submitted_at":"2023-12-01T00:54:02Z","title":"Sample Efficient Preference Alignment in LLMs via Active Exploration","version":3},"cited_work":{"arxiv_id":"2312.00267","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2312.00267","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Sample efficient reinforcement learning from human feedback via active exploration","venue":null,"work_id":"bfe77083-1611-4f69-b9c1-7901fef478c8","year":2023},"citing_paper":{"arxiv_id":"2505.19241","last_updated":"2026-05-14T18:01:35Z","snapshot_observed_at":"2026-08-02T15:42:14.270446Z","submitted_at":"2025-05-25T17:42:52Z","title":"ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-22T01:06:19.756032Z"},"links":{"cited_paper":"/paper/2312.00267","citing_paper":"/paper/2505.19241"},"observation_digest":"sha256:3b917c44a6a1e02001d717e7891d0c4cc01a300dc19adb87501a4f72b8223899","observation_id":"6118295d-f6ab-499d-a9e5-e3b96791dd0c","resolution":{"observed_at":"2026-05-22T01:10:51.597571Z","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":"2312.00267","last_updated":"2025-03-20T14:23:17Z","snapshot_observed_at":"2026-07-06T16:55:25.413169Z","submitted_at":"2023-12-01T00:54:02Z","title":"Sample Efficient Preference Alignment in LLMs via Active Exploration","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.00267","snapshot_observed_at":"2026-08-07T12:50:42.595875Z","title":"Sample efficient reinforcement learning from human feedback via active exploration","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.23673","last_updated":"2025-05-29T17:17:29Z","snapshot_observed_at":"2026-08-07T12:37:58.181685Z","submitted_at":"2025-05-29T17:17:29Z","title":"Bayesian Optimization from Human Feedback: Near-Optimal Regret Bounds","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-07T12:50:42.595875Z"},"links":{"cited_paper":"/paper/2312.00267","citing_paper":"/paper/2505.23673"},"observation_digest":"sha256:542b16b07a30d332fb37fc8e5621e33119351eb4c0c7213a739c29d714c66e80","observation_id":"3e05f0f4-440a-4c96-815a-b223275df31c","resolution":{"observed_at":"2026-08-07T12:50:42.595875Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.00267","last_updated":"2025-03-20T14:23:17Z","snapshot_observed_at":"2026-07-06T16:55:25.413169Z","submitted_at":"2023-12-01T00:54:02Z","title":"Sample Efficient Preference Alignment in LLMs via Active Exploration","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.00267","snapshot_observed_at":"2026-08-07T10:19:02.653953Z","title":"Sample efficient reinforcement learning from human feedback via active exploration,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.02870","last_updated":"2025-06-06T10:50:08Z","snapshot_observed_at":"2026-08-08T01:09:03.836574Z","submitted_at":"2025-06-06T10:50:08Z","title":"Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models","version":1},"reference_index":131,"source":"pdf_text","source_observed_at":"2026-08-07T10:19:02.653953Z"},"links":{"cited_paper":"/paper/2312.00267","citing_paper":"/paper/2507.02870"},"observation_digest":"sha256:fdc5eaa10fd2038b16817592f04df459661dedb1cfa6928209f800c1079a2509","observation_id":"c1401097-56a0-419f-a1eb-2a08d476e9ea","resolution":{"observed_at":"2026-08-07T10:19:02.653953Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.00267","last_updated":"2025-03-20T14:23:17Z","snapshot_observed_at":"2026-07-06T16:55:25.413169Z","submitted_at":"2023-12-01T00:54:02Z","title":"Sample Efficient Preference Alignment in LLMs via Active Exploration","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.00267","snapshot_observed_at":"2026-08-06T14:13:06.588039Z","title":"Sample efficient preference alignment in llms via active exploration","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.19672","last_updated":"2025-07-25T20:52:58Z","snapshot_observed_at":"2026-08-07T12:02:14.124506Z","submitted_at":"2025-07-25T20:52:58Z","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","version":1},"reference_index":179,"source":"arxiv_source","source_observed_at":"2026-08-06T14:13:06.588039Z"},"links":{"cited_paper":"/paper/2312.00267","citing_paper":"/paper/2507.19672"},"observation_digest":"sha256:1f516053e6d810aff3b6d09d6783b2e16896b1e74aed2ec62d0d7e3bee3c8755","observation_id":"d6c2d3a6-669a-4a6d-be60-13eaf37134cc","resolution":{"observed_at":"2026-08-06T14:13:06.588039Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2312.00267/citation-record","integrity":"/paper/2312.00267/integrity","json":"/paper/2312.00267/citation-record.json","paper":"/paper/2312.00267"},"outbound":[],"paper":{"arxiv_id":"2312.00267","last_updated":"2025-03-20T14:23:17Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T16:55:25.413169Z","submitted_at":"2023-12-01T00:54:02Z","title":"Sample Efficient Preference Alignment in LLMs via Active Exploration"},"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 4 inbound Pith citation observations for arXiv:2312.00267."}