{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IUXYGNYWHVZMCDFSGC3FMPRMM7","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":"5cb9fcb7415928f94a879a2872bd1094e96ff9a4802d49f2bb84d86f1481e1ed","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-08T17:59:56Z","title_canon_sha256":"469c0d15adbd96a58fa5881c8367f13e8fde0ef3d902a0e1c26f3d1b7edc308a"},"schema_version":"1.0","source":{"id":"2306.05424","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.05424","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"arxiv_version","alias_value":"2306.05424v2","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05424","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"pith_short_12","alias_value":"IUXYGNYWHVZM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"IUXYGNYWHVZMCDFS","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"IUXYGNYW","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:8fcbb37aa5531c28e9e74daabe2bb99476c7ef955b68da3fc62183ad9367832f","target":"graph","created_at":"2026-05-17T23:38:53Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"The resulting model is capable of understanding and generating detailed conversations about videos."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The semi-automated pipeline for creating the 100,000 video-instruction pairs produces sufficiently clean training data without label noise that would degrade the model's ability to generate accurate conversations."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Video-ChatGPT is a multimodal model that combines a video visual encoder with an LLM to understand and generate conversations about videos, trained on a new dataset of 100,000 video-instruction pairs."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Video-ChatGPT combines a video-adapted visual encoder with a large language model to support detailed conversations about video content."}],"snapshot_sha256":"533f3463748ac8910ef18fcb487e600635e42d9003b546018bbba6b1a4d37d38"},"formal_canon":{"evidence_count":3,"snapshot_sha256":"a45098cacb1b8d38046a9f62e97c2526b9000811dbcbe5618d22fde14339f022"},"paper":{"abstract_excerpt":"Conversation agents fueled by Large Language Models (LLMs) are providing a new way to interact with visual data. While there have been initial attempts for image-based conversation models, this work addresses the under-explored field of \\emph{video-based conversation} by introducing Video-ChatGPT. It is a multimodal model that merges a video-adapted visual encoder with an LLM. The resulting model is capable of understanding and generating detailed conversations about videos. We introduce a new dataset of 100,000 video-instruction pairs used to train Video-ChatGPT acquired via manual and semi-a","authors_text":"Fahad Shahbaz Khan, Hanoona Rasheed, Muhammad Maaz, Salman Khan","cross_cats":[],"headline":"Video-ChatGPT combines a video-adapted visual encoder with a large language model to support detailed conversations about video content.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-08T17:59:56Z","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05424","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T03:29:56.240351Z","id":"a1200b5c-d98e-43aa-ac40-21ef3e152a62","model_set":{"reader":"grok-4.3"},"one_line_summary":"Video-ChatGPT is a multimodal model that combines a video visual encoder with an LLM to understand and generate conversations about videos, trained on a new dataset of 100,000 video-instruction pairs.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Video-ChatGPT combines a video-adapted visual encoder with a large language model to support detailed conversations about video content.","strongest_claim":"The resulting model is capable of understanding and generating detailed conversations about videos.","weakest_assumption":"The semi-automated pipeline for creating the 100,000 video-instruction pairs produces sufficiently clean training data without label noise that would degrade the model's ability to generate accurate conversations."}},"verdict_id":"a1200b5c-d98e-43aa-ac40-21ef3e152a62"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:adc2c2bead161b0f44f8cd53ff5403b25d4c17f093977096804558b2e7cb27fa","target":"record","created_at":"2026-05-17T23:38:53Z","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":"5cb9fcb7415928f94a879a2872bd1094e96ff9a4802d49f2bb84d86f1481e1ed","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-08T17:59:56Z","title_canon_sha256":"469c0d15adbd96a58fa5881c8367f13e8fde0ef3d902a0e1c26f3d1b7edc308a"},"schema_version":"1.0","source":{"id":"2306.05424","kind":"arxiv","version":2}},"canonical_sha256":"452f8337163d72c10cb230b6563e2c67d6aee88b03595c40c0d6f3600844b886","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"452f8337163d72c10cb230b6563e2c67d6aee88b03595c40c0d6f3600844b886","first_computed_at":"2026-05-17T23:38:53.670465Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:53.670465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VkzuK/WUbbHThUm2PH33A/HU+eJ54VW7IFbqnhItb9trEBRyFkrZzv4hBKgfhd9sGaFoB1T/L7vPEk6pbkEQDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:53.670969Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.05424","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:adc2c2bead161b0f44f8cd53ff5403b25d4c17f093977096804558b2e7cb27fa","sha256:8fcbb37aa5531c28e9e74daabe2bb99476c7ef955b68da3fc62183ad9367832f"],"state_sha256":"b5fb22c3a22b529b30f16977fa5662164a256d8b458b64c53e8d8cc677ecbad9"}