{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FKDMJBWWWXRFGZ6USCV3Q3BWDZ","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":"1ffb42227ea28207201765e7b52abd447defd31e9bee6a7eb403dde347d2427a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-01T18:39:26Z","title_canon_sha256":"effec4488ee1f19668045184bce7ad4a9f246669de4224ad4cf46838e115941d"},"schema_version":"1.0","source":{"id":"2507.02001","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.02001","created_at":"2026-07-05T11:31:10Z"},{"alias_kind":"arxiv_version","alias_value":"2507.02001v1","created_at":"2026-07-05T11:31:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02001","created_at":"2026-07-05T11:31:10Z"},{"alias_kind":"pith_short_12","alias_value":"FKDMJBWWWXRF","created_at":"2026-07-05T11:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"FKDMJBWWWXRFGZ6U","created_at":"2026-07-05T11:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"FKDMJBWW","created_at":"2026-07-05T11:31:10Z"}],"graph_snapshots":[{"event_id":"sha256:24a5306cfcc42db6528ff3c970dcf14d4af8c3e472e8d3490a8487dffb0eff51","target":"graph","created_at":"2026-07-05T11:31:10Z","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/2507.02001/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite recent advances in Vision-Language Models (VLMs), long-video understanding remains a challenging problem. Although state-of-the-art long-context VLMs can process around 1000 input frames, they still struggle to effectively leverage this sequence length, and succumb to irrelevant distractors within the context window. We present Temporal Chain of Thought, an inference strategy for video question-answering that curates the model's input context. We use the VLM itself to iteratively identify and extract the most relevant frames from the video, which are then used for answering. We demonst","authors_text":"Ahmet Iscen, Alireza Fathi, Anurag Arnab, Cordelia Schmid, Mathilde Caron","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-01T18:39:26Z","title":"Temporal Chain of Thought: Long-Video Understanding by Thinking in Frames"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02001","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":"sha256:82e6a8e888f0e5115feb9b2fc792bfd1a73b4217b28f41b3fe6337975a1819c1","target":"record","created_at":"2026-07-05T11:31:10Z","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":"1ffb42227ea28207201765e7b52abd447defd31e9bee6a7eb403dde347d2427a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-01T18:39:26Z","title_canon_sha256":"effec4488ee1f19668045184bce7ad4a9f246669de4224ad4cf46838e115941d"},"schema_version":"1.0","source":{"id":"2507.02001","kind":"arxiv","version":1}},"canonical_sha256":"2a86c486d6b5e25367d490abb86c361e638379340fd41aaca4abfabdfb9458e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a86c486d6b5e25367d490abb86c361e638379340fd41aaca4abfabdfb9458e6","first_computed_at":"2026-07-05T11:31:10.281321Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:10.281321Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YspVEU0G5XWSfkZGl4ev/d8LogRcbUPxFxsR4PQ08gkekRLna5GrgytDr/+VxCwXqUGBMBXvM0I38rnjg4mEBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:10.281795Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.02001","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:82e6a8e888f0e5115feb9b2fc792bfd1a73b4217b28f41b3fe6337975a1819c1","sha256:24a5306cfcc42db6528ff3c970dcf14d4af8c3e472e8d3490a8487dffb0eff51"],"state_sha256":"67f5c736c8a33339cb194e1d2a42d6de790538e49272d8569862507b238884c7"}