{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PL42M4VBY2ZAOACKQAQ64CH6EO","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":"d9f6d2d67b33f52838e671f097807a7c1d1e2ce3cc4999b70b5745e76fe465b1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-10T14:08:56Z","title_canon_sha256":"0f83d14951794cfbd1386633ec06acddd0fc84aa04aecb4d58bcf80ad0f73839"},"schema_version":"1.0","source":{"id":"2506.08817","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08817","created_at":"2026-07-05T11:20:14Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08817v3","created_at":"2026-07-05T11:20:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08817","created_at":"2026-07-05T11:20:14Z"},{"alias_kind":"pith_short_12","alias_value":"PL42M4VBY2ZA","created_at":"2026-07-05T11:20:14Z"},{"alias_kind":"pith_short_16","alias_value":"PL42M4VBY2ZAOACK","created_at":"2026-07-05T11:20:14Z"},{"alias_kind":"pith_short_8","alias_value":"PL42M4VB","created_at":"2026-07-05T11:20:14Z"}],"graph_snapshots":[{"event_id":"sha256:f6b34a83e5a6b20d069f3cf4c404d5493a8f914c0f8d55dfd5d74684b2074de2","target":"graph","created_at":"2026-07-05T11:20:14Z","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/2506.08817/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Hongxuan Ma, Lingfeng Zhang, Pengwei Wang, Shanghang Zhang, Shuyi Zhang, Xiaoshuai Hao, Yingbo Tang, Zhongyuan Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-10T14:08:56Z","title":"Video-CoT: A Comprehensive Dataset for Spatiotemporal Understanding of Videos Based on Chain-of-Thought"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08817","kind":"arxiv","version":3},"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":"sha256:5fb2bbac7a89ec3edfaa2447e6444a98dc70a9efebd9f071ec0c845699fca319","target":"record","created_at":"2026-07-05T11:20:14Z","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":"d9f6d2d67b33f52838e671f097807a7c1d1e2ce3cc4999b70b5745e76fe465b1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-10T14:08:56Z","title_canon_sha256":"0f83d14951794cfbd1386633ec06acddd0fc84aa04aecb4d58bcf80ad0f73839"},"schema_version":"1.0","source":{"id":"2506.08817","kind":"arxiv","version":3}},"canonical_sha256":"7af9a672a1c6b207004a8021ee08fe23be30ef3c47a55d1dec9419836e4adc4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7af9a672a1c6b207004a8021ee08fe23be30ef3c47a55d1dec9419836e4adc4c","first_computed_at":"2026-07-05T11:20:14.384906Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:14.384906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2/ww8feUoI0q8/j8uNsTYsNMXrQ9/T89TEV8l+FlJ4FTmpmeK+QDHcNrGrf8+W9/sMxnSlgbV6CR2zyxnudeCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:14.385597Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.08817","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5fb2bbac7a89ec3edfaa2447e6444a98dc70a9efebd9f071ec0c845699fca319","sha256:f6b34a83e5a6b20d069f3cf4c404d5493a8f914c0f8d55dfd5d74684b2074de2"],"state_sha256":"acbc45964b755293dd6688fc0b030c92d865b7e780484e3d3b353ddcfbd45448"}