{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2VV5CAQBVBISBUEPUNDKR5GXKS","short_pith_number":"pith:2VV5CAQB","schema_version":"1.0","canonical_sha256":"d56bd10201a85120d08fa346a8f4d7548bae242e28a57f70b45d4ca31d1cfa98","source":{"kind":"arxiv","id":"2506.05349","version":2},"attestation_state":"computed","paper":{"title":"VideoMathQA: Benchmarking Mathematical Reasoning via Multimodal Understanding in Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdelrahman Shaker, Anqi Tang, Fahad Shahbaz Khan, Hanoona Rasheed, Ming-Hsuan Yang, Muhammad Maaz, Salman Khan","submitted_at":"2025-06-05T17:59:58Z","abstract_excerpt":"Mathematical reasoning in real-world video settings presents a fundamentally different challenge than in static images or text. It requires interpreting fine-grained visual information, accurately reading handwritten or digital text, and integrating spoken cues, often dispersed non-linearly over time. In such multimodal contexts, success hinges not just on perception, but on selectively identifying and integrating the right contextual details from a rich and noisy stream of content. To this end, we introduce VideoMathQA, a benchmark designed to evaluate whether models can perform such temporal"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.05349","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T17:59:58Z","cross_cats_sorted":[],"title_canon_sha256":"1180b44a52a66ce88f2b96ce073e7f3ccce22ef3e809feccd779833fb9238e6b","abstract_canon_sha256":"8bbcdb78aae85f0cfeacd80aede55fa94b0fd807a2d99457f17606597f5e55bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:05.176684Z","signature_b64":"Ft6OUGeHwbmK7O1HX0VBuaG8liUtI8i6qmNDIoalbwyCDB8BdhysEz4iwCjBs09NNqNxjycbPPniqCWQtWseAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d56bd10201a85120d08fa346a8f4d7548bae242e28a57f70b45d4ca31d1cfa98","last_reissued_at":"2026-07-05T11:26:05.176201Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:05.176201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoMathQA: Benchmarking Mathematical Reasoning via Multimodal Understanding in Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdelrahman Shaker, Anqi Tang, Fahad Shahbaz Khan, Hanoona Rasheed, Ming-Hsuan Yang, Muhammad Maaz, Salman Khan","submitted_at":"2025-06-05T17:59:58Z","abstract_excerpt":"Mathematical reasoning in real-world video settings presents a fundamentally different challenge than in static images or text. It requires interpreting fine-grained visual information, accurately reading handwritten or digital text, and integrating spoken cues, often dispersed non-linearly over time. In such multimodal contexts, success hinges not just on perception, but on selectively identifying and integrating the right contextual details from a rich and noisy stream of content. To this end, we introduce VideoMathQA, a benchmark designed to evaluate whether models can perform such temporal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05349","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.05349/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.05349","created_at":"2026-07-05T11:26:05.176258+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05349v2","created_at":"2026-07-05T11:26:05.176258+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05349","created_at":"2026-07-05T11:26:05.176258+00:00"},{"alias_kind":"pith_short_12","alias_value":"2VV5CAQBVBIS","created_at":"2026-07-05T11:26:05.176258+00:00"},{"alias_kind":"pith_short_16","alias_value":"2VV5CAQBVBISBUEP","created_at":"2026-07-05T11:26:05.176258+00:00"},{"alias_kind":"pith_short_8","alias_value":"2VV5CAQB","created_at":"2026-07-05T11:26:05.176258+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03087","citing_title":"Learning to Solve, Forgetting to Retain: Correct-Set Turnover in RLVR","ref_index":126,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14733","citing_title":"Video-Zero: Self-Evolution Video Understanding","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2512.03043","citing_title":"OneThinker: All-in-one Reasoning Model for Image and Video","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27083","citing_title":"Co-Evolving Policy Distillation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09649","citing_title":"Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Eviction","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16893","citing_title":"EasyVideoR1: Easier RL for Video Understanding","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2VV5CAQBVBISBUEPUNDKR5GXKS","json":"https://pith.science/pith/2VV5CAQBVBISBUEPUNDKR5GXKS.json","graph_json":"https://pith.science/api/pith-number/2VV5CAQBVBISBUEPUNDKR5GXKS/graph.json","events_json":"https://pith.science/api/pith-number/2VV5CAQBVBISBUEPUNDKR5GXKS/events.json","paper":"https://pith.science/paper/2VV5CAQB"},"agent_actions":{"view_html":"https://pith.science/pith/2VV5CAQBVBISBUEPUNDKR5GXKS","download_json":"https://pith.science/pith/2VV5CAQBVBISBUEPUNDKR5GXKS.json","view_paper":"https://pith.science/paper/2VV5CAQB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05349&json=true","fetch_graph":"https://pith.science/api/pith-number/2VV5CAQBVBISBUEPUNDKR5GXKS/graph.json","fetch_events":"https://pith.science/api/pith-number/2VV5CAQBVBISBUEPUNDKR5GXKS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2VV5CAQBVBISBUEPUNDKR5GXKS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2VV5CAQBVBISBUEPUNDKR5GXKS/action/storage_attestation","attest_author":"https://pith.science/pith/2VV5CAQBVBISBUEPUNDKR5GXKS/action/author_attestation","sign_citation":"https://pith.science/pith/2VV5CAQBVBISBUEPUNDKR5GXKS/action/citation_signature","submit_replication":"https://pith.science/pith/2VV5CAQBVBISBUEPUNDKR5GXKS/action/replication_record"}},"created_at":"2026-07-05T11:26:05.176258+00:00","updated_at":"2026-07-05T11:26:05.176258+00:00"}