{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:22YEYZH4H6S3S6ROAY7SBUE7IL","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":"ed07bb8f8c867c45ad6d993b0c5cd44270e97844a2d7cafa04f850d077399e95","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-18T02:29:19Z","title_canon_sha256":"953ba2ec944f65cd599f71be1bb3ca566b2b8e6892c427d3dc0dae997c48906c"},"schema_version":"1.0","source":{"id":"2507.13609","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.13609","created_at":"2026-07-05T11:39:20Z"},{"alias_kind":"arxiv_version","alias_value":"2507.13609v1","created_at":"2026-07-05T11:39:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13609","created_at":"2026-07-05T11:39:20Z"},{"alias_kind":"pith_short_12","alias_value":"22YEYZH4H6S3","created_at":"2026-07-05T11:39:20Z"},{"alias_kind":"pith_short_16","alias_value":"22YEYZH4H6S3S6RO","created_at":"2026-07-05T11:39:20Z"},{"alias_kind":"pith_short_8","alias_value":"22YEYZH4","created_at":"2026-07-05T11:39:20Z"}],"graph_snapshots":[{"event_id":"sha256:da7ce70f28b9beb4b4919085acfa78db98112efedc0aadeefaf8b106bd022b3c","target":"graph","created_at":"2026-07-05T11:39:20Z","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/2507.13609/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite recent progress in video large language models (VideoLLMs), a key open challenge remains: how to equip models with chain-of-thought (CoT) reasoning abilities grounded in fine-grained object-level video understanding. Existing instruction-tuned models, such as the Qwen and LLaVA series, are trained on high-level video-text pairs, often lacking structured annotations necessary for compositional, step-by-step reasoning. We propose CoTasks: Chain-of-Thought based Video Instruction Tuning Tasks, a new framework that decomposes complex video questions of existing datasets (e.g., NeXT-QA, STA","authors_text":"Hao Niu, Julio Vizcarra, Mori Kurokawa, Yanan Wang, Zhi Li","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-18T02:29:19Z","title":"CoTasks: Chain-of-Thought based Video Instruction Tuning Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13609","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:a26aaa71681394db0fb00b34251389227cd470eca11bd0ec8f1e183fd06e751f","target":"record","created_at":"2026-07-05T11:39:20Z","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":"ed07bb8f8c867c45ad6d993b0c5cd44270e97844a2d7cafa04f850d077399e95","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-18T02:29:19Z","title_canon_sha256":"953ba2ec944f65cd599f71be1bb3ca566b2b8e6892c427d3dc0dae997c48906c"},"schema_version":"1.0","source":{"id":"2507.13609","kind":"arxiv","version":1}},"canonical_sha256":"d6b04c64fc3fa5b97a2e063f20d09f42e026fe6a333df2c6696582246d9b8698","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6b04c64fc3fa5b97a2e063f20d09f42e026fe6a333df2c6696582246d9b8698","first_computed_at":"2026-07-05T11:39:20.130851Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:39:20.130851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G0XAQjBfdrHt0P0WQBQhca6dtAfFJCV2j+9Z9CVN5/rHBOa3s+tsId/bdLqW2IRGXEWdWZIJ4SdQE2S1/+xLDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:39:20.131357Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.13609","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a26aaa71681394db0fb00b34251389227cd470eca11bd0ec8f1e183fd06e751f","sha256:da7ce70f28b9beb4b4919085acfa78db98112efedc0aadeefaf8b106bd022b3c"],"state_sha256":"f355cc45609c81bf7532ae1fe7e579628e4d97c1b9ce60936502c4ff29130a2e"}