{"as_of":"2026-08-10T14:35:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c7f106a3cfe2a4fbf01fd26f781750bffdafe61abd5891dab3e433682f1d0e27","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T16:38:06.631594Z","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":"2026-05-23T03:57:29.547083Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.16834","last_updated":"2024-12-24T02:17:41Z","snapshot_observed_at":"2026-07-06T20:11:37.761713Z","submitted_at":"2024-12-22T02:43:07Z","title":"Online Learning from Strategic Human Feedback in LLM Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.16834","snapshot_observed_at":"2026-08-09T16:38:06.631594Z","title":"and Duan, L","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.01127","last_updated":"2025-02-07T08:10:54Z","snapshot_observed_at":"2026-08-09T16:26:39.640941Z","submitted_at":"2025-02-03T07:45:41Z","title":"The Battling Influencers Game: Nash Equilibria Structure of a Potential Game and Implications to Value Alignment","version":3},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-09T16:38:06.631594Z"},"links":{"cited_paper":"/paper/2412.16834","citing_paper":"/paper/2502.01127"},"observation_digest":"sha256:80ed9c20fbc8d5914ff48f0f961bcf19321f09b00839e48b8ea2d243580075b2","observation_id":"e4c26c1d-ba06-405a-9602-c300644a5c25","resolution":{"observed_at":"2026-08-09T16:38:06.631594Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.16834","last_updated":"2024-12-24T02:17:41Z","snapshot_observed_at":"2026-07-06T20:11:37.761713Z","submitted_at":"2024-12-22T02:43:07Z","title":"Online Learning from Strategic Human Feedback in LLM Fine-Tuning","version":2},"cited_work":{"arxiv_id":"2412.16834","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.16834","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Online learning from strategic human feedback in llm fine-tuning","venue":null,"work_id":"3356263b-4632-4e07-8752-e4c65785eddb","year":2024},"citing_paper":{"arxiv_id":"2502.06387","last_updated":"2026-04-07T06:33:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-02-10T12:15:27Z","title":"How Humans Help LLMs: Assessing and Incentivizing Human Preference Annotators","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-05-23T03:56:18.703995Z"},"links":{"cited_paper":"/paper/2412.16834","citing_paper":"/paper/2502.06387"},"observation_digest":"sha256:e77c39541aad7b5fdb936d98f61921b22502a4e7f5101f489cc77e6edec62871","observation_id":"e86a58fa-c6b6-4bea-968b-51222439eda9","resolution":{"observed_at":"2026-05-23T03:57:29.550406Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.16834","last_updated":"2024-12-24T02:17:41Z","snapshot_observed_at":"2026-07-06T20:11:37.761713Z","submitted_at":"2024-12-22T02:43:07Z","title":"Online Learning from Strategic Human Feedback in LLM Fine-Tuning","version":2},"cited_work":{"arxiv_id":"2412.16834","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.16834","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Online learning from strategic human feedback in llm fine-tuning","venue":null,"work_id":"3356263b-4632-4e07-8752-e4c65785eddb","year":2024},"citing_paper":{"arxiv_id":"2505.19134","last_updated":"2026-04-13T23:58:15Z","snapshot_observed_at":"2026-07-06T21:30:04.828669Z","submitted_at":"2025-05-25T13:11:55Z","title":"Incentivizing High-Quality Human Annotations with Golden Questions","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-19T13:41:26.730528Z"},"links":{"cited_paper":"/paper/2412.16834","citing_paper":"/paper/2505.19134"},"observation_digest":"sha256:70b2d43cf001c9bbf4fab7d770e6c6776a63adfe2ee0b074c604d3b9865bd235","observation_id":"a8d5d594-0c3c-4105-980d-49db6e563d74","resolution":{"observed_at":"2026-05-19T13:42:19.382745Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2412.16834/citation-record","integrity":"/paper/2412.16834/integrity","json":"/paper/2412.16834/citation-record.json","paper":"/paper/2412.16834"},"outbound":[],"paper":{"arxiv_id":"2412.16834","last_updated":"2024-12-24T02:17:41Z","latest_version":2,"primary_category":"cs.AI","snapshot_observed_at":"2026-07-06T20:11:37.761713Z","submitted_at":"2024-12-22T02:43:07Z","title":"Online Learning from Strategic Human Feedback in LLM Fine-Tuning"},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2412.16834."}