{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2VV5CAQBVBISBUEPUNDKR5GXKS","short_pith_number":"pith:2VV5CAQB","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"},"canonical_sha256":"d56bd10201a85120d08fa346a8f4d7548bae242e28a57f70b45d4ca31d1cfa98","source":{"kind":"arxiv","id":"2506.05349","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05349","created_at":"2026-07-05T11:26:05Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05349v2","created_at":"2026-07-05T11:26:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05349","created_at":"2026-07-05T11:26:05Z"},{"alias_kind":"pith_short_12","alias_value":"2VV5CAQBVBIS","created_at":"2026-07-05T11:26:05Z"},{"alias_kind":"pith_short_16","alias_value":"2VV5CAQBVBISBUEP","created_at":"2026-07-05T11:26:05Z"},{"alias_kind":"pith_short_8","alias_value":"2VV5CAQB","created_at":"2026-07-05T11:26:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2VV5CAQBVBISBUEPUNDKR5GXKS","target":"record","payload":{"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"},"canonical_sha256":"d56bd10201a85120d08fa346a8f4d7548bae242e28a57f70b45d4ca31d1cfa98","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"},"source_kind":"arxiv","source_id":"2506.05349","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:26:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RIaGA1jLzMxnFCdBp82tEptrv/RMINDhrqH8+pxbgTNcspwn7FzW6yaRlvW69RNxMb6NTFtivFdETpddvoKpBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:08:57.533674Z"},"content_sha256":"fd63bbcaca53b0c9c844e7c7fb67ada543ca7b6b5337c16e3d92716b11181a95","schema_version":"1.0","event_id":"sha256:fd63bbcaca53b0c9c844e7c7fb67ada543ca7b6b5337c16e3d92716b11181a95"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2VV5CAQBVBISBUEPUNDKR5GXKS","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:26:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1BWAeiJKp2M2hSefBY2C2JyMpGn2fjvzGoF1h6AuD0ZYX6JfJ7KFQ1YedBSBjpNDgGyQ4qSFkfAbzVFYtJMoDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:08:57.534296Z"},"content_sha256":"a98a442c95362eb16b5020cf88b1730976848bb5ee7bae37fd1033d22a0def37","schema_version":"1.0","event_id":"sha256:a98a442c95362eb16b5020cf88b1730976848bb5ee7bae37fd1033d22a0def37"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2VV5CAQBVBISBUEPUNDKR5GXKS/bundle.json","state_url":"https://pith.science/pith/2VV5CAQBVBISBUEPUNDKR5GXKS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2VV5CAQBVBISBUEPUNDKR5GXKS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T05:08:57Z","links":{"resolver":"https://pith.science/pith/2VV5CAQBVBISBUEPUNDKR5GXKS","bundle":"https://pith.science/pith/2VV5CAQBVBISBUEPUNDKR5GXKS/bundle.json","state":"https://pith.science/pith/2VV5CAQBVBISBUEPUNDKR5GXKS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2VV5CAQBVBISBUEPUNDKR5GXKS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2VV5CAQBVBISBUEPUNDKR5GXKS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8bbcdb78aae85f0cfeacd80aede55fa94b0fd807a2d99457f17606597f5e55bc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T17:59:58Z","title_canon_sha256":"1180b44a52a66ce88f2b96ce073e7f3ccce22ef3e809feccd779833fb9238e6b"},"schema_version":"1.0","source":{"id":"2506.05349","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05349","created_at":"2026-07-05T11:26:05Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05349v2","created_at":"2026-07-05T11:26:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05349","created_at":"2026-07-05T11:26:05Z"},{"alias_kind":"pith_short_12","alias_value":"2VV5CAQBVBIS","created_at":"2026-07-05T11:26:05Z"},{"alias_kind":"pith_short_16","alias_value":"2VV5CAQBVBISBUEP","created_at":"2026-07-05T11:26:05Z"},{"alias_kind":"pith_short_8","alias_value":"2VV5CAQB","created_at":"2026-07-05T11:26:05Z"}],"graph_snapshots":[{"event_id":"sha256:a98a442c95362eb16b5020cf88b1730976848bb5ee7bae37fd1033d22a0def37","target":"graph","created_at":"2026-07-05T11:26:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.05349/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Abdelrahman Shaker, Anqi Tang, Fahad Shahbaz Khan, Hanoona Rasheed, Ming-Hsuan Yang, Muhammad Maaz, Salman Khan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T17:59:58Z","title":"VideoMathQA: Benchmarking Mathematical Reasoning via Multimodal Understanding in Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05349","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fd63bbcaca53b0c9c844e7c7fb67ada543ca7b6b5337c16e3d92716b11181a95","target":"record","created_at":"2026-07-05T11:26:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8bbcdb78aae85f0cfeacd80aede55fa94b0fd807a2d99457f17606597f5e55bc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T17:59:58Z","title_canon_sha256":"1180b44a52a66ce88f2b96ce073e7f3ccce22ef3e809feccd779833fb9238e6b"},"schema_version":"1.0","source":{"id":"2506.05349","kind":"arxiv","version":2}},"canonical_sha256":"d56bd10201a85120d08fa346a8f4d7548bae242e28a57f70b45d4ca31d1cfa98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d56bd10201a85120d08fa346a8f4d7548bae242e28a57f70b45d4ca31d1cfa98","first_computed_at":"2026-07-05T11:26:05.176201Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:26:05.176201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ft6OUGeHwbmK7O1HX0VBuaG8liUtI8i6qmNDIoalbwyCDB8BdhysEz4iwCjBs09NNqNxjycbPPniqCWQtWseAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:26:05.176684Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.05349","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd63bbcaca53b0c9c844e7c7fb67ada543ca7b6b5337c16e3d92716b11181a95","sha256:a98a442c95362eb16b5020cf88b1730976848bb5ee7bae37fd1033d22a0def37"],"state_sha256":"4aabcac9a8e55d7f467313bb1622b4831722ef7e62afb82c25f63af19f170015"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nK5X/664T9rNlwb0RkYFvfeuc0GLDGJr31g2FexXacDQIs7lKyamMWILi1I8lvfBw4bPOup10V9h4/xKtcBtAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:08:57.538434Z","bundle_sha256":"ba797aa7e469d9e7b9120316309a8814848d8e3215ca1bd6e97f484e7c29fa30"}}