{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:D3MO3SCNX7MISWTEXMETMNEM4J","short_pith_number":"pith:D3MO3SCN","schema_version":"1.0","canonical_sha256":"1ed8edc84dbfd8895a64bb0936348ce27cdaa01fcf6da750ea63ce787d1c8997","source":{"kind":"arxiv","id":"2406.19392","version":2},"attestation_state":"computed","paper":{"title":"ReXTime: A Benchmark Suite for Reasoning-Across-Time in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hsi-Che Lin, Jr-Jen Chen, Yen-Chun Chen, Yu-Chiang Frank Wang, Yu-Chien Liao, Yu-Chu Yu","submitted_at":"2024-06-27T17:59:45Z","abstract_excerpt":"We introduce ReXTime, a benchmark designed to rigorously test AI models' ability to perform temporal reasoning within video events. Specifically, ReXTime focuses on reasoning across time, i.e. human-like understanding when the question and its corresponding answer occur in different video segments. This form of reasoning, requiring advanced understanding of cause-and-effect relationships across video segments, poses significant challenges to even the frontier multimodal large language models. To facilitate this evaluation, we develop an automated pipeline for generating temporal reasoning ques"},"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":"2406.19392","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-27T17:59:45Z","cross_cats_sorted":[],"title_canon_sha256":"23f6cb4201ce974c711b5fec876c9ba315c8b7be22a90a544b638b2aed122961","abstract_canon_sha256":"2c25a802c1c7113f1b4f7b229de76d6b0539384fe95f29483e16b85427692bde"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:21.969269Z","signature_b64":"D8ygnoopdBsyMxgOGBKfX4NXtKIAuittfy0U9HMLjVz8CYV8qx3U5r/wFP/+CeIKAN580+IjQ5l61A4FbvgSCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ed8edc84dbfd8895a64bb0936348ce27cdaa01fcf6da750ea63ce787d1c8997","last_reissued_at":"2026-07-05T08:39:21.968815Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:21.968815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReXTime: A Benchmark Suite for Reasoning-Across-Time in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hsi-Che Lin, Jr-Jen Chen, Yen-Chun Chen, Yu-Chiang Frank Wang, Yu-Chien Liao, Yu-Chu Yu","submitted_at":"2024-06-27T17:59:45Z","abstract_excerpt":"We introduce ReXTime, a benchmark designed to rigorously test AI models' ability to perform temporal reasoning within video events. Specifically, ReXTime focuses on reasoning across time, i.e. human-like understanding when the question and its corresponding answer occur in different video segments. This form of reasoning, requiring advanced understanding of cause-and-effect relationships across video segments, poses significant challenges to even the frontier multimodal large language models. To facilitate this evaluation, we develop an automated pipeline for generating temporal reasoning ques"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19392","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/2406.19392/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":"2406.19392","created_at":"2026-07-05T08:39:21.968874+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.19392v2","created_at":"2026-07-05T08:39:21.968874+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19392","created_at":"2026-07-05T08:39:21.968874+00:00"},{"alias_kind":"pith_short_12","alias_value":"D3MO3SCNX7MI","created_at":"2026-07-05T08:39:21.968874+00:00"},{"alias_kind":"pith_short_16","alias_value":"D3MO3SCNX7MISWTE","created_at":"2026-07-05T08:39:21.968874+00:00"},{"alias_kind":"pith_short_8","alias_value":"D3MO3SCN","created_at":"2026-07-05T08:39:21.968874+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26680","citing_title":"DynFrame: Adaptive Reasoning-Driven Multimodal Framework with Dynamic Frame Augmentation for Complex Video Understanding","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19559","citing_title":"EgoCoT-Bench: Benchmarking Grounded and Verifiable Operation-Centric Chain of Thought Reasoning for MLLMs","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D3MO3SCNX7MISWTEXMETMNEM4J","json":"https://pith.science/pith/D3MO3SCNX7MISWTEXMETMNEM4J.json","graph_json":"https://pith.science/api/pith-number/D3MO3SCNX7MISWTEXMETMNEM4J/graph.json","events_json":"https://pith.science/api/pith-number/D3MO3SCNX7MISWTEXMETMNEM4J/events.json","paper":"https://pith.science/paper/D3MO3SCN"},"agent_actions":{"view_html":"https://pith.science/pith/D3MO3SCNX7MISWTEXMETMNEM4J","download_json":"https://pith.science/pith/D3MO3SCNX7MISWTEXMETMNEM4J.json","view_paper":"https://pith.science/paper/D3MO3SCN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.19392&json=true","fetch_graph":"https://pith.science/api/pith-number/D3MO3SCNX7MISWTEXMETMNEM4J/graph.json","fetch_events":"https://pith.science/api/pith-number/D3MO3SCNX7MISWTEXMETMNEM4J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D3MO3SCNX7MISWTEXMETMNEM4J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D3MO3SCNX7MISWTEXMETMNEM4J/action/storage_attestation","attest_author":"https://pith.science/pith/D3MO3SCNX7MISWTEXMETMNEM4J/action/author_attestation","sign_citation":"https://pith.science/pith/D3MO3SCNX7MISWTEXMETMNEM4J/action/citation_signature","submit_replication":"https://pith.science/pith/D3MO3SCNX7MISWTEXMETMNEM4J/action/replication_record"}},"created_at":"2026-07-05T08:39:21.968874+00:00","updated_at":"2026-07-05T08:39:21.968874+00:00"}