{"as_of":"2026-08-08T21:43:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:712f3709e613ff117a3c10dee66122811bfe3c6350911b53122b572a89344f2f","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":"2026-08-07T22:50:33.252571Z","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":"2026-05-13T20:13:13.622953Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2403.05006","last_updated":"2024-03-08T03:05:11Z","snapshot_observed_at":"2026-07-06T17:41:23.460300Z","submitted_at":"2024-03-08T03:05:11Z","title":"Provable Multi-Party Reinforcement Learning with Diverse Human Feedback","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.05006","snapshot_observed_at":"2026-08-07T22:50:33.252571Z","title":"Provable multi-party reinforcement learning with diverse human feedback","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.09053","last_updated":"2025-08-05T02:23:31Z","snapshot_observed_at":"2026-08-08T10:12:47.586452Z","submitted_at":"2025-02-13T08:08:27Z","title":"Game Theory Meets Large Language Models: A Systematic Survey with Taxonomy and New Frontiers","version":2},"reference_index":163,"source":"pdf_text","source_observed_at":"2026-08-07T22:50:33.252571Z"},"links":{"cited_paper":"/paper/2403.05006","citing_paper":"/paper/2502.09053"},"observation_digest":"sha256:c61b63a5e4fc8e5aa508ea42ba6c5b946f5e7e2d92b3f98c3732d8c0fcb81e1b","observation_id":"08bfe1a9-d6fb-4fab-90ad-64f0350a547c","resolution":{"observed_at":"2026-08-07T22:50:33.252571Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.05006","last_updated":"2024-03-08T03:05:11Z","snapshot_observed_at":"2026-07-06T17:41:23.460300Z","submitted_at":"2024-03-08T03:05:11Z","title":"Provable Multi-Party Reinforcement Learning with Diverse Human Feedback","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.05006","snapshot_observed_at":"2026-08-07T12:49:12.458231Z","title":"Provable multi-party reinforcement learning with diverse human feedback","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.23749","last_updated":"2025-05-29T17:59:20Z","snapshot_observed_at":"2026-08-07T12:36:14.760657Z","submitted_at":"2025-05-29T17:59:20Z","title":"Distortion of AI Alignment: Does Preference Optimization Optimize for Preferences?","version":1},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-07T12:49:12.458231Z"},"links":{"cited_paper":"/paper/2403.05006","citing_paper":"/paper/2505.23749"},"observation_digest":"sha256:b556a4447e993fc1c37c1274e95e18f12a9bb237fc8ee7e9e965e9f98493a1a3","observation_id":"86890663-deca-4538-9ae6-381b1a419079","resolution":{"observed_at":"2026-08-07T12:49:12.458231Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.05006","last_updated":"2024-03-08T03:05:11Z","snapshot_observed_at":"2026-07-06T17:41:23.460300Z","submitted_at":"2024-03-08T03:05:11Z","title":"Provable Multi-Party Reinforcement Learning with Diverse Human Feedback","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.05006","snapshot_observed_at":"2026-08-07T01:04:32.828481Z","title":"Provable multi-party reinforcement learning with diverse human feedback.arXiv preprint arXiv:2403.05006,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12350","last_updated":"2025-06-14T05:14:49Z","snapshot_observed_at":"2026-08-08T15:24:03.755091Z","submitted_at":"2025-06-14T05:14:49Z","title":"Theoretical Tensions in RLHF: Reconciling Empirical Success with Inconsistencies in Social Choice Theory","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T01:04:32.828481Z"},"links":{"cited_paper":"/paper/2403.05006","citing_paper":"/paper/2506.12350"},"observation_digest":"sha256:d02597d8259aa5b3ab38bf6d54ce556f299a71e65a93958a93501e1db28f3eed","observation_id":"3fcb66fe-0fc2-42c9-a6cf-fd8b5072d6a7","resolution":{"observed_at":"2026-08-07T01:04:32.828481Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.05006","last_updated":"2024-03-08T03:05:11Z","snapshot_observed_at":"2026-07-06T17:41:23.460300Z","submitted_at":"2024-03-08T03:05:11Z","title":"Provable Multi-Party Reinforcement Learning with Diverse Human Feedback","version":1},"cited_work":{"arxiv_id":"2403.05006","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.05006","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"J., Wu, Z","venue":null,"work_id":"effec646-2671-42a2-b182-36cb45cb1422","year":2024},"citing_paper":{"arxiv_id":"2604.02507","last_updated":"2026-04-02T21:04:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-02T21:04:17Z","title":"Reinforcement Learning from Human Feedback: A Statistical Perspective","version":1},"reference_index":93,"source":"arxiv_source","source_observed_at":"2026-05-13T20:10:43.578904Z"},"links":{"cited_paper":"/paper/2403.05006","citing_paper":"/paper/2604.02507"},"observation_digest":"sha256:23d8d69f2289486895fca94b195cc0f38f7d9b7d42f73463b189bdce621a97c5","observation_id":"e24cd083-7e1b-48b5-a078-67ba63e0862f","resolution":{"observed_at":"2026-05-13T20:13:13.626028Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2403.05006/citation-record","integrity":"/paper/2403.05006/integrity","json":"/paper/2403.05006/citation-record.json","paper":"/paper/2403.05006"},"outbound":[],"paper":{"arxiv_id":"2403.05006","last_updated":"2024-03-08T03:05:11Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T17:41:23.460300Z","submitted_at":"2024-03-08T03:05:11Z","title":"Provable Multi-Party Reinforcement Learning with Diverse Human Feedback"},"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:2403.05006."}