{"as_of":"2026-08-17T16:02:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9123bd0949cab9a2b34fc1ebd5c6969193f86298844ad01b35eddac29eaeaf2d","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":"2026-08-17T06:30:58.91139+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":"2026-08-16T11:13:53.556751Z","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":"2026-08-06T18:51:32.832846Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2311.04072","last_updated":"2024-04-15T15:25:53Z","snapshot_observed_at":"2026-08-16T14:45:15.190206Z","submitted_at":"2023-11-07T15:36:40Z","title":"Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.04072","snapshot_observed_at":"2026-08-12T05:43:31.514283Z","title":"Beyond imitation: Leveraging fine-grained quality signals for alignment","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.19943","last_updated":"2025-01-13T06:53:56Z","snapshot_observed_at":"2026-08-16T13:48:23.352188Z","submitted_at":"2024-11-29T18:58:22Z","title":"Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T05:43:31.514283Z"},"links":{"cited_paper":"/paper/2311.04072","citing_paper":"/paper/2411.19943"},"observation_digest":"sha256:cb2249fef818a3af41a2adc84dc55d9db9b27ee13e224caeb3a53616d5948841","observation_id":"9b99a00e-8979-476f-8f7d-adafd4504621","resolution":{"observed_at":"2026-08-12T05:43:31.514283Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.04072","last_updated":"2024-04-15T15:25:53Z","snapshot_observed_at":"2026-08-16T14:45:15.190206Z","submitted_at":"2023-11-07T15:36:40Z","title":"Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.04072","snapshot_observed_at":"2026-08-11T23:15:56.034022Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.02685","last_updated":"2024-12-03T18:56:07Z","snapshot_observed_at":"2026-08-12T01:39:13.359412Z","submitted_at":"2024-12-03T18:56:07Z","title":"T-REG: Preference Optimization with Token-Level Reward Regularization","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-11T23:15:56.034022Z"},"links":{"cited_paper":"/paper/2311.04072","citing_paper":"/paper/2412.02685"},"observation_digest":"sha256:aabd78864b9b07a12c4e6f0f67ef2fce55ee8ced7976a5b9856403b07a4ede89","observation_id":"bfd304e5-dfbb-4b13-a8f1-80603684b4e8","resolution":{"observed_at":"2026-08-11T23:15:56.034022Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.04072","last_updated":"2024-04-15T15:25:53Z","snapshot_observed_at":"2026-08-16T14:45:15.190206Z","submitted_at":"2023-11-07T15:36:40Z","title":"Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.04072","snapshot_observed_at":"2026-08-16T11:13:53.556751Z","title":"Beyond imitation: Leveraging fine-grained quality signals for alignment","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.16272","last_updated":"2025-04-22T21:09:33Z","snapshot_observed_at":"2026-08-16T17:39:00.881138Z","submitted_at":"2025-04-22T21:09:33Z","title":"Learning Explainable Dense Reward Shapes via Bayesian Optimization","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-16T11:13:53.556751Z"},"links":{"cited_paper":"/paper/2311.04072","citing_paper":"/paper/2504.16272"},"observation_digest":"sha256:b86125b7216c08ae81f0799d1c63b9ceb362161cbc90da74fe25f082eb6b55c5","observation_id":"5f8b3ec3-5902-41ba-ad03-94cc59b037b4","resolution":{"observed_at":"2026-08-16T11:13:53.556751Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.04072","last_updated":"2024-04-15T15:25:53Z","snapshot_observed_at":"2026-08-16T14:45:15.190206Z","submitted_at":"2023-11-07T15:36:40Z","title":"Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment","version":2},"cited_work":{"arxiv_id":"2311.04072","doi":null,"metadata_source":"pith","pith_arxiv_id":"2311.04072","snapshot_observed_at":"2026-08-06T18:51:32.832846Z","title":"Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment","venue":"cs.CL","work_id":"97b5e844-c147-4164-a408-191101c2eb83","year":2023},"citing_paper":{"arxiv_id":"2507.07375","last_updated":"2025-07-10T01:56:56Z","snapshot_observed_at":"2026-08-17T08:43:32.569566Z","submitted_at":"2025-07-10T01:56:56Z","title":"Bradley-Terry and Multi-Objective Reward Modeling Are Complementary","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-06T18:51:31.661655Z"},"links":{"cited_paper":"/paper/2311.04072","citing_paper":"/paper/2507.07375"},"observation_digest":"sha256:94376907d25140f4c9c5f39d6a14db6171fb4d0682ee0fd5ddae18bd615e1dc7","observation_id":"4885c4c4-937c-4e54-8052-92db587a203a","resolution":{"observed_at":"2026-08-06T18:51:32.838655Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2311.04072/citation-record","integrity":"/paper/2311.04072/integrity","json":"/paper/2311.04072/citation-record.json","paper":"/paper/2311.04072"},"outbound":[],"paper":{"arxiv_id":"2311.04072","last_updated":"2024-04-15T15:25:53Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-16T14:45:15.190206Z","submitted_at":"2023-11-07T15:36:40Z","title":"Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment"},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2311.04072."}