{"as_of":"2026-08-09T23:32:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:511dce6f18d0b1b39eaa261ba7454bd1763a3eb39bb2c0f11b25d312b7029d62","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":"2026-08-09T06:31:02.800959+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":"2026-08-07T11:19:06.325253Z","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":"2026-05-22T22:57:13.286702Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2407.08733","last_updated":"2024-10-08T10:51:59Z","snapshot_observed_at":"2026-08-03T15:30:28.663561Z","submitted_at":"2024-07-11T17:58:58Z","title":"Is Your Model Really A Good Math Reasoner? Evaluating Mathematical Reasoning with Checklist","version":2},"cited_work":{"arxiv_id":"2407.08733","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2407.08733","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Is your model really a good math rea- soner? evaluating mathematical reasoning with checklist","venue":null,"work_id":"fe1fe562-2c48-4e97-9d49-e920f6edc68c","year":2024},"citing_paper":{"arxiv_id":"2503.16549","last_updated":"2026-04-18T11:44:37Z","snapshot_observed_at":"2026-08-08T08:24:44.422314Z","submitted_at":"2025-03-19T11:46:19Z","title":"MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problems","version":2},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-05-22T22:55:34.238427Z"},"links":{"cited_paper":"/paper/2407.08733","citing_paper":"/paper/2503.16549"},"observation_digest":"sha256:78de78e9b96dcde522c8ff53c6f8a764e529a9f5b77835bd8cb976c2af85ae2a","observation_id":"fb61cb14-68b1-4c57-9533-2a7d570d6265","resolution":{"observed_at":"2026-05-22T22:57:13.289581Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.08733","last_updated":"2024-10-08T10:51:59Z","snapshot_observed_at":"2026-08-03T15:30:28.663561Z","submitted_at":"2024-07-11T17:58:58Z","title":"Is Your Model Really A Good Math Reasoner? Evaluating Mathematical Reasoning with Checklist","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.08733","snapshot_observed_at":"2026-08-07T05:38:58.780594Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07418","last_updated":"2025-06-09T04:35:02Z","snapshot_observed_at":"2026-08-08T00:41:58.254546Z","submitted_at":"2025-06-09T04:35:02Z","title":"Evaluating Visual Mathematics in Multimodal LLMs: A Multilingual Benchmark Based on the Kangaroo Tests","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T05:38:58.780594Z"},"links":{"cited_paper":"/paper/2407.08733","citing_paper":"/paper/2506.07418"},"observation_digest":"sha256:7e01a6f3e9b9d36dcc833d6c1d1530d30adc6f29bf607051c74c59ea5aa5644b","observation_id":"af557481-fa63-43f1-bd55-bc3fbec83de0","resolution":{"observed_at":"2026-08-07T05:38:58.780594Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.08733","last_updated":"2024-10-08T10:51:59Z","snapshot_observed_at":"2026-08-03T15:30:28.663561Z","submitted_at":"2024-07-11T17:58:58Z","title":"Is Your Model Really A Good Math Reasoner? Evaluating Mathematical Reasoning with Checklist","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.08733","snapshot_observed_at":"2026-08-07T05:01:08.214730Z","title":"Wong, Xiaowei Huang, Qiufeng Wang, and Kaizhu Huang","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.09038","last_updated":"2025-06-10T17:57:30Z","snapshot_observed_at":"2026-08-08T13:22:08.459736Z","submitted_at":"2025-06-10T17:57:30Z","title":"AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T05:01:08.214730Z"},"links":{"cited_paper":"/paper/2407.08733","citing_paper":"/paper/2506.09038"},"observation_digest":"sha256:acfa21c577a0de6d2a33287b75156fa9e870dd86d74f9a43d20498544d055c2b","observation_id":"93414f8b-aa5c-451d-bc6b-2b20c9b5d85b","resolution":{"observed_at":"2026-08-07T05:01:08.214730Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.08733","last_updated":"2024-10-08T10:51:59Z","snapshot_observed_at":"2026-08-03T15:30:28.663561Z","submitted_at":"2024-07-11T17:58:58Z","title":"Is Your Model Really A Good Math Reasoner? Evaluating Mathematical Reasoning with Checklist","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.08733","snapshot_observed_at":"2026-08-07T11:19:06.325253Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.14805","last_updated":"2025-08-12T17:07:53Z","snapshot_observed_at":"2026-08-08T00:05:33.094743Z","submitted_at":"2025-06-03T13:44:14Z","title":"Argus Inspection: Do Multimodal Large Language Models Possess the Eye of Panoptes?","version":2},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-07T11:19:06.325253Z"},"links":{"cited_paper":"/paper/2407.08733","citing_paper":"/paper/2506.14805"},"observation_digest":"sha256:9ef35945edc0fef393ce27654a4f0fa0d08768b7141beab92e37aa1642400ac8","observation_id":"9ccbca64-5837-4fc4-9b4d-78460aff3c08","resolution":{"observed_at":"2026-08-07T11:19:06.325253Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2407.08733/citation-record","integrity":"/paper/2407.08733/integrity","json":"/paper/2407.08733/citation-record.json","paper":"/paper/2407.08733"},"outbound":[],"paper":{"arxiv_id":"2407.08733","last_updated":"2024-10-08T10:51:59Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-03T15:30:28.663561Z","submitted_at":"2024-07-11T17:58:58Z","title":"Is Your Model Really A Good Math Reasoner? Evaluating Mathematical Reasoning with Checklist"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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:2407.08733."}