{"as_of":"2026-08-08T13:08:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:bb26fe678897e6f9c457786518a09fe94bbc017c663977f504adc8c3de73e51e","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":"2026-08-08T06:32:00.761636+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":"2026-08-07T15:33:11.638080Z","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":"2026-05-15T23:17:02.871625Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.13173","last_updated":"2025-02-17T19:56:21Z","snapshot_observed_at":"2026-08-07T18:11:02.754125Z","submitted_at":"2025-02-17T19:56:21Z","title":"Thinking Preference Optimization","version":1},"cited_work":{"arxiv_id":"2502.13173","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.13173","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Thinking preference optimization","venue":null,"work_id":"ded76404-6939-4901-93f0-f2f658d41107","year":2025},"citing_paper":{"arxiv_id":"2504.14945","last_updated":"2025-06-22T00:18:09Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-04-21T08:09:13Z","title":"Learning to Reason under Off-Policy Guidance","version":5},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-05-15T23:17:02.701393Z"},"links":{"cited_paper":"/paper/2502.13173","citing_paper":"/paper/2504.14945"},"observation_digest":"sha256:9935f8e1ff19c5434189c33c12f9cc994b035467a7192bc24a43350f5d4b0ef5","observation_id":"49e8f4e6-ecb4-4e4e-940f-cbda1466e8f4","resolution":{"observed_at":"2026-05-15T23:17:02.874286Z","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":"2502.13173","last_updated":"2025-02-17T19:56:21Z","snapshot_observed_at":"2026-08-07T18:11:02.754125Z","submitted_at":"2025-02-17T19:56:21Z","title":"Thinking Preference Optimization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.13173","snapshot_observed_at":"2026-08-07T15:33:11.638080Z","title":"Thinking preference optimization.arXiv preprint arXiv:2502.13173, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.14810","last_updated":"2025-05-25T14:52:51Z","snapshot_observed_at":"2026-08-07T15:27:03.992813Z","submitted_at":"2025-05-20T18:18:01Z","title":"Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T15:33:11.638080Z"},"links":{"cited_paper":"/paper/2502.13173","citing_paper":"/paper/2505.14810"},"observation_digest":"sha256:5682106200245516183d3eb1902445b0fb5e56856befc572e6a91d51ab74852a","observation_id":"de45736f-69f1-464f-8f18-338b7dba298d","resolution":{"observed_at":"2026-08-07T15:33:11.638080Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.13173","last_updated":"2025-02-17T19:56:21Z","snapshot_observed_at":"2026-08-07T18:11:02.754125Z","submitted_at":"2025-02-17T19:56:21Z","title":"Thinking Preference Optimization","version":1},"cited_work":{"arxiv_id":"2502.13173","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.13173","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Thinking preference optimization","venue":null,"work_id":"ded76404-6939-4901-93f0-f2f658d41107","year":2025},"citing_paper":{"arxiv_id":"2605.02290","last_updated":"2026-05-04T07:26:41Z","snapshot_observed_at":"2026-08-02T10:20:40.458806Z","submitted_at":"2026-05-04T07:26:41Z","title":"Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-05-09T16:29:05.186607Z"},"links":{"cited_paper":"/paper/2502.13173","citing_paper":"/paper/2605.02290"},"observation_digest":"sha256:7bbeb836b3a41a5c8ee7898d85b75cd6ee8d5260b6686c3d87c0bc69bfca7b34","observation_id":"4424dc0e-294f-4a6f-b7ad-a474df03c9f2","resolution":{"observed_at":"2026-05-11T16:31:09.212353Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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/2502.13173/citation-record","integrity":"/paper/2502.13173/integrity","json":"/paper/2502.13173/citation-record.json","paper":"/paper/2502.13173"},"outbound":[],"paper":{"arxiv_id":"2502.13173","last_updated":"2025-02-17T19:56:21Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T18:11:02.754125Z","submitted_at":"2025-02-17T19:56:21Z","title":"Thinking Preference Optimization"},"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 3 inbound Pith citation observations for arXiv:2502.13173."}