{"as_of":"2026-08-12T07:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:edd4a159833bbfda7f3c35489381d575b0be07da770a19204baf97c38b9fe59b","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":"2026-08-12T06:34:41.77262+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":"2026-08-11T12:58:26.789698Z","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":"2026-05-16T13:20:57.553166Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2308.15812","last_updated":"2024-02-05T19:59:46Z","snapshot_observed_at":"2026-08-10T14:34:41.808560Z","submitted_at":"2023-08-30T07:35:32Z","title":"Peering Through Preferences: Unraveling Feedback Acquisition for Aligning Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.15812","snapshot_observed_at":"2026-08-11T12:58:26.789698Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.13666","last_updated":"2025-07-25T06:20:38Z","snapshot_observed_at":"2026-08-12T07:18:12.780142Z","submitted_at":"2024-12-18T09:48:53Z","title":"Evaluation of LLM Vulnerabilities to Being Misused for Personalized Disinformation Generation","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-11T12:58:26.789698Z"},"links":{"cited_paper":"/paper/2308.15812","citing_paper":"/paper/2412.13666"},"observation_digest":"sha256:88a1d79d07b02e7322b9b513fed2717c3f97912915daf36c80db75950e7944fa","observation_id":"519fdfbd-9abe-445f-9f24-f7c9f1631daa","resolution":{"observed_at":"2026-08-11T12:58:26.789698Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.15812","last_updated":"2024-02-05T19:59:46Z","snapshot_observed_at":"2026-08-10T14:34:41.808560Z","submitted_at":"2023-08-30T07:35:32Z","title":"Peering Through Preferences: Unraveling Feedback Acquisition for Aligning Large Language Models","version":3},"cited_work":{"arxiv_id":"2308.15812","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2308.15812","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Peering through preferences: Unraveling feedback acquisition for aligning large language models","venue":null,"work_id":"d70f554e-b499-4488-ba65-7352065e755d","year":2023},"citing_paper":{"arxiv_id":"2601.13262","last_updated":"2026-04-26T01:38:11Z","snapshot_observed_at":"2026-08-11T09:32:38.343501Z","submitted_at":"2026-01-19T17:51:00Z","title":"CURE-Med: Curriculum-Informed Reinforcement Learning for Multilingual Medical Reasoning","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-05-16T13:20:49.919833Z"},"links":{"cited_paper":"/paper/2308.15812","citing_paper":"/paper/2601.13262"},"observation_digest":"sha256:1c6eff54a754ca461ddeb52b89e74b8543d4221ad18deef9d4360430846ce9a5","observation_id":"b3ec4172-7154-4234-b38e-d633ca82fb37","resolution":{"observed_at":"2026-05-16T13:20:57.555633Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.15812","last_updated":"2024-02-05T19:59:46Z","snapshot_observed_at":"2026-08-10T14:34:41.808560Z","submitted_at":"2023-08-30T07:35:32Z","title":"Peering Through Preferences: Unraveling Feedback Acquisition for Aligning Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.15812","snapshot_observed_at":"2026-07-11T13:53:36.775836Z","title":"arXiv preprint arXiv:2308.15812 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.04763","last_updated":"2026-07-26T14:17:18Z","snapshot_observed_at":"2026-08-02T10:24:43.977557Z","submitted_at":"2026-07-06T07:56:53Z","title":"Multi-Turn On-Policy Distillation with Prefix Replay","version":1},"reference_index":223,"source":"arxiv_source","source_observed_at":"2026-07-11T13:53:36.775836Z"},"links":{"cited_paper":"/paper/2308.15812","citing_paper":"/paper/2607.04763"},"observation_digest":"sha256:94311872525a46706d79f88fbd4c581a2560b8feabdc3354e4d1e41928aee403","observation_id":"475e1631-7de9-4f09-b40e-97f6edada1cc","resolution":{"observed_at":"2026-07-11T13:53:36.775836Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.15812","last_updated":"2024-02-05T19:59:46Z","snapshot_observed_at":"2026-08-10T14:34:41.808560Z","submitted_at":"2023-08-30T07:35:32Z","title":"Peering Through Preferences: Unraveling Feedback Acquisition for Aligning Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.15812","snapshot_observed_at":"2026-08-02T08:40:57.895520Z","title":"arXiv preprint arXiv:2308.15812 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.04763","last_updated":"2026-07-26T14:17:18Z","snapshot_observed_at":"2026-08-02T10:24:43.977557Z","submitted_at":"2026-07-06T07:56:53Z","title":"Multi-Turn On-Policy Distillation with Prefix Replay","version":3},"reference_index":224,"source":"arxiv_source","source_observed_at":"2026-08-02T08:40:57.895520Z"},"links":{"cited_paper":"/paper/2308.15812","citing_paper":"/paper/2607.04763"},"observation_digest":"sha256:51038a22be061eb8aec04c8a9124df1b7fecc370e894f8fad6fd7c10ff3d3eb8","observation_id":"2640f13e-b16b-4cba-b5db-c2d3f7ea82e6","resolution":{"observed_at":"2026-08-02T08:40:57.895520Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2308.15812/citation-record","integrity":"/paper/2308.15812/integrity","json":"/paper/2308.15812/citation-record.json","paper":"/paper/2308.15812"},"outbound":[],"paper":{"arxiv_id":"2308.15812","last_updated":"2024-02-05T19:59:46Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T14:34:41.808560Z","submitted_at":"2023-08-30T07:35:32Z","title":"Peering Through Preferences: Unraveling Feedback Acquisition for Aligning 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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2308.15812."}