{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PL42M4VBY2ZAOACKQAQ64CH6EO","short_pith_number":"pith:PL42M4VB","schema_version":"1.0","canonical_sha256":"7af9a672a1c6b207004a8021ee08fe23be30ef3c47a55d1dec9419836e4adc4c","source":{"kind":"arxiv","id":"2506.08817","version":3},"attestation_state":"computed","paper":{"title":"Video-CoT: A Comprehensive Dataset for Spatiotemporal Understanding of Videos Based on Chain-of-Thought","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongxuan Ma, Lingfeng Zhang, Pengwei Wang, Shanghang Zhang, Shuyi Zhang, Xiaoshuai Hao, Yingbo Tang, Zhongyuan Wang","submitted_at":"2025-06-10T14:08:56Z","abstract_excerpt":"Video content comprehension is essential for various applications, ranging from video analysis to interactive systems. Despite advancements in large-scale vision-language models (VLMs), these models often struggle to capture the nuanced, spatiotemporal details essential for thorough video analysis. To address this gap, we introduce Video-CoT, a groundbreaking dataset designed to enhance spatiotemporal understanding using Chain-of-Thought (CoT) methodologies. Video-CoT contains 192,000 fine-grained spa-tiotemporal question-answer pairs and 23,000 high-quality CoT-annotated samples, providing a "},"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":"2506.08817","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-10T14:08:56Z","cross_cats_sorted":[],"title_canon_sha256":"0f83d14951794cfbd1386633ec06acddd0fc84aa04aecb4d58bcf80ad0f73839","abstract_canon_sha256":"d9f6d2d67b33f52838e671f097807a7c1d1e2ce3cc4999b70b5745e76fe465b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:14.385597Z","signature_b64":"2/ww8feUoI0q8/j8uNsTYsNMXrQ9/T89TEV8l+FlJ4FTmpmeK+QDHcNrGrf8+W9/sMxnSlgbV6CR2zyxnudeCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7af9a672a1c6b207004a8021ee08fe23be30ef3c47a55d1dec9419836e4adc4c","last_reissued_at":"2026-07-05T11:20:14.384906Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:14.384906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video-CoT: A Comprehensive Dataset for Spatiotemporal Understanding of Videos Based on Chain-of-Thought","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongxuan Ma, Lingfeng Zhang, Pengwei Wang, Shanghang Zhang, Shuyi Zhang, Xiaoshuai Hao, Yingbo Tang, Zhongyuan Wang","submitted_at":"2025-06-10T14:08:56Z","abstract_excerpt":"Video content comprehension is essential for various applications, ranging from video analysis to interactive systems. Despite advancements in large-scale vision-language models (VLMs), these models often struggle to capture the nuanced, spatiotemporal details essential for thorough video analysis. To address this gap, we introduce Video-CoT, a groundbreaking dataset designed to enhance spatiotemporal understanding using Chain-of-Thought (CoT) methodologies. Video-CoT contains 192,000 fine-grained spa-tiotemporal question-answer pairs and 23,000 high-quality CoT-annotated samples, providing a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08817","kind":"arxiv","version":3},"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/2506.08817/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":"2506.08817","created_at":"2026-07-05T11:20:14.384973+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.08817v3","created_at":"2026-07-05T11:20:14.384973+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08817","created_at":"2026-07-05T11:20:14.384973+00:00"},{"alias_kind":"pith_short_12","alias_value":"PL42M4VBY2ZA","created_at":"2026-07-05T11:20:14.384973+00:00"},{"alias_kind":"pith_short_16","alias_value":"PL42M4VBY2ZAOACK","created_at":"2026-07-05T11:20:14.384973+00:00"},{"alias_kind":"pith_short_8","alias_value":"PL42M4VB","created_at":"2026-07-05T11:20:14.384973+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01241","citing_title":"OneVLA: A Unified Framework for Embodied Tasks","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2602.17555","citing_title":"GraphThinker: Reinforcing Temporally Grounded Video Reasoning with Event Graph Thinking","ref_index":72,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PL42M4VBY2ZAOACKQAQ64CH6EO","json":"https://pith.science/pith/PL42M4VBY2ZAOACKQAQ64CH6EO.json","graph_json":"https://pith.science/api/pith-number/PL42M4VBY2ZAOACKQAQ64CH6EO/graph.json","events_json":"https://pith.science/api/pith-number/PL42M4VBY2ZAOACKQAQ64CH6EO/events.json","paper":"https://pith.science/paper/PL42M4VB"},"agent_actions":{"view_html":"https://pith.science/pith/PL42M4VBY2ZAOACKQAQ64CH6EO","download_json":"https://pith.science/pith/PL42M4VBY2ZAOACKQAQ64CH6EO.json","view_paper":"https://pith.science/paper/PL42M4VB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.08817&json=true","fetch_graph":"https://pith.science/api/pith-number/PL42M4VBY2ZAOACKQAQ64CH6EO/graph.json","fetch_events":"https://pith.science/api/pith-number/PL42M4VBY2ZAOACKQAQ64CH6EO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PL42M4VBY2ZAOACKQAQ64CH6EO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PL42M4VBY2ZAOACKQAQ64CH6EO/action/storage_attestation","attest_author":"https://pith.science/pith/PL42M4VBY2ZAOACKQAQ64CH6EO/action/author_attestation","sign_citation":"https://pith.science/pith/PL42M4VBY2ZAOACKQAQ64CH6EO/action/citation_signature","submit_replication":"https://pith.science/pith/PL42M4VBY2ZAOACKQAQ64CH6EO/action/replication_record"}},"created_at":"2026-07-05T11:20:14.384973+00:00","updated_at":"2026-07-05T11:20:14.384973+00:00"}