{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VFLHAXBTFUELPHYWDLE4YNMZK7","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":"39a9de1dd62515779eeb05a6da31f42ce9a01b07b0a650821f060da4df8c550d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-04T05:55:15Z","title_canon_sha256":"270bc7a10efa4518c1029d2039dcb1954246effde657c7c34e25d6d237efb1cf"},"schema_version":"1.0","source":{"id":"2606.05736","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05736","created_at":"2026-06-05T01:15:01Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05736v1","created_at":"2026-06-05T01:15:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05736","created_at":"2026-06-05T01:15:01Z"},{"alias_kind":"pith_short_12","alias_value":"VFLHAXBTFUEL","created_at":"2026-06-05T01:15:01Z"},{"alias_kind":"pith_short_16","alias_value":"VFLHAXBTFUELPHYW","created_at":"2026-06-05T01:15:01Z"},{"alias_kind":"pith_short_8","alias_value":"VFLHAXBT","created_at":"2026-06-05T01:15:01Z"}],"graph_snapshots":[{"event_id":"sha256:811721ce613b49549c7ac7c2f16805c9dcf1e1c91dfc0a5755b908d3148f2b84","target":"graph","created_at":"2026-06-05T01:15:01Z","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/2606.05736/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video reasoning aims to understand complex temporal events and causal relationships within videos. Recently, Chain-of-Thought (CoT) has been introduced to this field to enhance reasoning accuracy. However, existing CoT-based video reasoning methods primarily rely on text-only information for logical deduction, overlooking critical visual information during the inference process. Inspired by the human cognitive mechanism of reviewing visual segments during inference, we propose VTI-CoT, a Visual-Textual Interleaved CoT framework. VTI-CoT integrates textual reasoning steps with corresponding vis","authors_text":"Bairun Wang, Kunlin Yang, Lei Jin, Shufan Zhang, Xinzhu Ma, Xuanding Ding, Ziyue Lin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-04T05:55:15Z","title":"VTI-CoT: Visual-Textual Interleaved Chain of Thought for Video Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05736","kind":"arxiv","version":1},"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":"sha256:8bef1a25c75ac8cb9c590ad3c1a883f9aa8b5ce2e8080794ac5e18b72e1ee2cf","target":"record","created_at":"2026-06-05T01:15:01Z","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":"39a9de1dd62515779eeb05a6da31f42ce9a01b07b0a650821f060da4df8c550d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-04T05:55:15Z","title_canon_sha256":"270bc7a10efa4518c1029d2039dcb1954246effde657c7c34e25d6d237efb1cf"},"schema_version":"1.0","source":{"id":"2606.05736","kind":"arxiv","version":1}},"canonical_sha256":"a956705c332d08b79f161ac9cc359957f71a9df240a7f9bbda96df98bf15c224","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a956705c332d08b79f161ac9cc359957f71a9df240a7f9bbda96df98bf15c224","first_computed_at":"2026-06-05T01:15:01.150256Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:01.150256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jKWhh9kP3tF1k8k6rNWJrC36u29lev1ReZS4bKaXtwtmVC94Aa58ivrz7d6Dq34efFN7omJrYkz/bd0Lw9OhDQ==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:01.150754Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05736","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8bef1a25c75ac8cb9c590ad3c1a883f9aa8b5ce2e8080794ac5e18b72e1ee2cf","sha256:811721ce613b49549c7ac7c2f16805c9dcf1e1c91dfc0a5755b908d3148f2b84"],"state_sha256":"ef8302335208952921ed9a7cc19e25072432d6e9fd6d451024e95afd9d665886"}