{"as_of":"2026-08-09T03:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5922a2811a8de8de7df5f954c9b16390c30e19a9975e28c1deb49422d76a62e8","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":"2026-08-06T15:02:21.710305Z","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":"2026-05-22T19:32:01.243236Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2410.01729","last_updated":"2024-10-02T16:39:58Z","snapshot_observed_at":"2026-07-06T19:26:22.646942Z","submitted_at":"2024-10-02T16:39:58Z","title":"Evaluating Robustness of Reward Models for Mathematical Reasoning","version":1},"cited_work":{"arxiv_id":"2410.01729","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.01729","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Evaluating robustness of reward models for mathematical reasoning","venue":null,"work_id":"52ff479f-b3dc-475b-bea5-be52d300937e","year":2024},"citing_paper":{"arxiv_id":"2504.12501","last_updated":"2026-08-03T01:47:58Z","snapshot_observed_at":"2026-08-07T16:01:39.307745Z","submitted_at":"2025-04-16T21:36:46Z","title":"Reinforcement Learning from Human Feedback","version":9},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-05-22T19:27:40.991325Z"},"links":{"cited_paper":"/paper/2410.01729","citing_paper":"/paper/2504.12501"},"observation_digest":"sha256:90c0bae7eac6309da938d165bcce3ea1945c106c1a1269a517f7848e79b5468e","observation_id":"527e699f-e68b-4a74-bf15-f56c990431a8","resolution":{"observed_at":"2026-05-22T19:32:01.245733Z","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":"2410.01729","last_updated":"2024-10-02T16:39:58Z","snapshot_observed_at":"2026-07-06T19:26:22.646942Z","submitted_at":"2024-10-02T16:39:58Z","title":"Evaluating Robustness of Reward Models for Mathematical Reasoning","version":1},"cited_work":{"arxiv_id":"2410.01729","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.01729","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Evaluating robustness of reward models for mathematical reasoning","venue":null,"work_id":"52ff479f-b3dc-475b-bea5-be52d300937e","year":2024},"citing_paper":{"arxiv_id":"2506.01937","last_updated":"2026-04-23T14:42:19Z","snapshot_observed_at":"2026-07-06T21:35:12.872021Z","submitted_at":"2025-06-02T17:54:04Z","title":"RewardBench 2: Advancing Reward Model Evaluation","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-19T11:18:03.965711Z"},"links":{"cited_paper":"/paper/2410.01729","citing_paper":"/paper/2506.01937"},"observation_digest":"sha256:884e481ba6d96bda89a2263c896b1718c4bfec7b779720d9c51b925d456335cf","observation_id":"dfcd7e52-6435-4ceb-b019-e2edd2d07cb4","resolution":{"observed_at":"2026-05-19T11:22:16.775009Z","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":"2410.01729","last_updated":"2024-10-02T16:39:58Z","snapshot_observed_at":"2026-07-06T19:26:22.646942Z","submitted_at":"2024-10-02T16:39:58Z","title":"Evaluating Robustness of Reward Models for Mathematical Reasoning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.01729","snapshot_observed_at":"2026-08-06T15:02:21.710305Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.17015","last_updated":"2025-07-22T20:57:09Z","snapshot_observed_at":"2026-08-07T12:17:11.302795Z","submitted_at":"2025-07-22T20:57:09Z","title":"Can External Validation Tools Improve Annotation Quality for LLM-as-a-Judge?","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-06T15:02:21.710305Z"},"links":{"cited_paper":"/paper/2410.01729","citing_paper":"/paper/2507.17015"},"observation_digest":"sha256:26fe0e0c3fe0cdd5a669a064557c07cbd3128752d25d48267ee500c24f00646b","observation_id":"f0871de8-dcc8-40d7-b89e-cd471039a507","resolution":{"observed_at":"2026-08-06T15:02:21.710305Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.01729","last_updated":"2024-10-02T16:39:58Z","snapshot_observed_at":"2026-07-06T19:26:22.646942Z","submitted_at":"2024-10-02T16:39:58Z","title":"Evaluating Robustness of Reward Models for Mathematical Reasoning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.01729","snapshot_observed_at":"2026-08-03T03:04:43.816244Z","title":"Evaluatingrobustnessofrewardmodelsformathematicalreasoning.arXiv preprint arXiv:2410.01729,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.09305","last_updated":"2026-06-28T18:13:37Z","snapshot_observed_at":"2026-08-08T13:06:41.126177Z","submitted_at":"2026-02-10T00:45:24Z","title":"Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-03T03:04:43.816244Z"},"links":{"cited_paper":"/paper/2410.01729","citing_paper":"/paper/2602.09305"},"observation_digest":"sha256:be33ba8e35089836fa66ebae6550991ee9a1121768bdad872c68bf818ae5f95d","observation_id":"e3e5fcea-855f-4fac-a5a7-a27e2495786e","resolution":{"observed_at":"2026-08-03T03:04:43.816244Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2410.01729/citation-record","integrity":"/paper/2410.01729/integrity","json":"/paper/2410.01729/citation-record.json","paper":"/paper/2410.01729"},"outbound":[],"paper":{"arxiv_id":"2410.01729","last_updated":"2024-10-02T16:39:58Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T19:26:22.646942Z","submitted_at":"2024-10-02T16:39:58Z","title":"Evaluating Robustness of Reward Models for Mathematical Reasoning"},"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 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2410.01729."}