{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:UUEWGEC4KEVJJ3XGQKHYHXHIVG","short_pith_number":"pith:UUEWGEC4","canonical_record":{"source":{"id":"2305.06355","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-10T17:59:04Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e3575a6b651fa1290ff321835f068fe4277811869eb692b606f9acd4939c4078","abstract_canon_sha256":"599fdd9894ff7225f523216572baeefc1fd0de5fe5a54f8a08366467878be7b1"},"schema_version":"1.0"},"canonical_sha256":"a50963105c512a94eee6828f83dce8a9b03ddea7ca8b559f08471598dbfbcf55","source":{"kind":"arxiv","id":"2305.06355","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.06355","created_at":"2026-05-18T03:42:33Z"},{"alias_kind":"arxiv_version","alias_value":"2305.06355v2","created_at":"2026-05-18T03:42:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.06355","created_at":"2026-05-18T03:42:33Z"},{"alias_kind":"pith_short_12","alias_value":"UUEWGEC4KEVJ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"UUEWGEC4KEVJJ3XG","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"UUEWGEC4","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:UUEWGEC4KEVJJ3XGQKHYHXHIVG","target":"record","payload":{"canonical_record":{"source":{"id":"2305.06355","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-10T17:59:04Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e3575a6b651fa1290ff321835f068fe4277811869eb692b606f9acd4939c4078","abstract_canon_sha256":"599fdd9894ff7225f523216572baeefc1fd0de5fe5a54f8a08366467878be7b1"},"schema_version":"1.0"},"canonical_sha256":"a50963105c512a94eee6828f83dce8a9b03ddea7ca8b559f08471598dbfbcf55","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:42:33.150844Z","signature_b64":"/MKJIE+h0QCfW928nViuM+r9Nrgx1vWaG0+ZaRNCcKtvNAHv2RrkAuAq/yw9qPzE0X3uzZwJRviC+MmAFlmoAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a50963105c512a94eee6828f83dce8a9b03ddea7ca8b559f08471598dbfbcf55","last_reissued_at":"2026-05-18T03:42:33.150268Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:42:33.150268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.06355","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:42:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oT5oYgh8uFq1jlCNY1HQpbwF/J5rxOgShuk7NYPPJPTa0ZPDSAD8vutknpOrZWNmmMzj0tej898R1jL9DuBuBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T14:53:59.617158Z"},"content_sha256":"c18402a20cf417f920707f3e4fc54ddc9bf31d69e19d70712c62f2546b20752b","schema_version":"1.0","event_id":"sha256:c18402a20cf417f920707f3e4fc54ddc9bf31d69e19d70712c62f2546b20752b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:UUEWGEC4KEVJJ3XGQKHYHXHIVG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VideoChat: Chat-Centric Video Understanding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"VideoChat links video models to language models with a trainable interface for conversational video analysis.","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Kunchang Li, Limin Wang, Ping Luo, Wenhai Wang, Yali Wang, Yinan He, Yi Wang, Yizhuo Li, Yu Qiao","submitted_at":"2023-05-10T17:59:04Z","abstract_excerpt":"In this paper, we initiate an attempt of developing an end-to-end chat-centric video understanding system, coined as VideoChat. It integrates video foundation models and large language models via a learnable neural interface, excelling in spatiotemporal reasoning, event localization, and causal relationship inference. To instructively tune this system, we build a video-centric instruction dataset, composed of thousands of videos associated with detailed descriptions and conversations. This dataset emphasizes spatiotemporal reasoning and captures causal relationships, providing a valuable asset"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"It integrates video foundation models and large language models via a learnable neural interface, excelling in spatiotemporal reasoning, event localization, and causal relationship inference.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The learnable neural interface, when trained on the video-centric instruction dataset, can bridge modalities sufficiently to enable the claimed excelling performance in spatiotemporal reasoning, event localization, and causal inference.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"VideoChat integrates video models and LLMs via a learnable interface for chat-based spatiotemporal and causal video reasoning, trained on a new video-centric instruction dataset.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"VideoChat links video models to language models with a trainable interface for conversational video analysis.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ff8cbb0f3075d80c5db2fdcfa739184cfe47ea6c0c72e1606b45e82bdb5397f6"},"source":{"id":"2305.06355","kind":"arxiv","version":2},"verdict":{"id":"b1096997-ef4c-4177-80f0-c458f9275bc2","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T23:25:41.740675Z","strongest_claim":"It integrates video foundation models and large language models via a learnable neural interface, excelling in spatiotemporal reasoning, event localization, and causal relationship inference.","one_line_summary":"VideoChat integrates video models and LLMs via a learnable interface for chat-based spatiotemporal and causal video reasoning, trained on a new video-centric instruction dataset.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The learnable neural interface, when trained on the video-centric instruction dataset, can bridge modalities sufficiently to enable the claimed excelling performance in spatiotemporal reasoning, event localization, and causal inference.","pith_extraction_headline":"VideoChat links video models to language models with a trainable interface for conversational video analysis."},"references":{"count":59,"sample":[{"doi":"","year":2023,"title":"Anas Awadalla, Irena Gao, Joshua Gardner, Jack Hessel, Yusuf Hanafy, Wanrong Zhu, Kalyani Marathe, Yonatan Bitton, Samir Gadre, Jenia Jitsev, Simon Kornblith, Pang Wei Koh, Gabriel Ilharco, Mitchell W","work_id":"fe04ce32-7667-49a6-912b-ca2a272d8271","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Frozen in time: A joint video and image encoder for end-to-end retrieval","work_id":"14d60c0b-f95c-4e49-877b-d7529b229ac7","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1901,"title":"Language models are few-shot learners","work_id":"06921215-168b-4266-a8bd-53d84ad473f0","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Conceptual 12m: Pushing web-scale image-text pre-training to recognize long-tail visual concepts","work_id":"5d3c3db1-3a21-4551-8576-912217ab41b4","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Internvideo-ego4d: A pack of champion solutions to ego4d challenges","work_id":"54773a77-a0f2-43d2-9158-858d1d0652f9","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":59,"snapshot_sha256":"6788a45ae2d9d3b0e3f5c204c7777f62ca61f23bda4dc00d70d6df1cfb18a6b2","internal_anchors":16},"formal_canon":{"evidence_count":2,"snapshot_sha256":"fb45cd2fb87402480b3d0a8f5e8dda9f660e6aa48669229c03004cce4c248872"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"b1096997-ef4c-4177-80f0-c458f9275bc2"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:42:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"73EaECT2a/9sfkD6eiEptNt6pCMLVPkcNkH0v9mg6FFiyFsu6ixmytk2JLWQ9/YVj9CkYogAmvyQ0gkNkfgFBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T14:53:59.617674Z"},"content_sha256":"c5f34217acd99886b0ba7c089f82283ce3af93bc7d91468d83799fb1f85ef67b","schema_version":"1.0","event_id":"sha256:c5f34217acd99886b0ba7c089f82283ce3af93bc7d91468d83799fb1f85ef67b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UUEWGEC4KEVJJ3XGQKHYHXHIVG/bundle.json","state_url":"https://pith.science/pith/UUEWGEC4KEVJJ3XGQKHYHXHIVG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UUEWGEC4KEVJJ3XGQKHYHXHIVG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-01T14:53:59Z","links":{"resolver":"https://pith.science/pith/UUEWGEC4KEVJJ3XGQKHYHXHIVG","bundle":"https://pith.science/pith/UUEWGEC4KEVJJ3XGQKHYHXHIVG/bundle.json","state":"https://pith.science/pith/UUEWGEC4KEVJJ3XGQKHYHXHIVG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UUEWGEC4KEVJJ3XGQKHYHXHIVG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UUEWGEC4KEVJJ3XGQKHYHXHIVG","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":"599fdd9894ff7225f523216572baeefc1fd0de5fe5a54f8a08366467878be7b1","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-10T17:59:04Z","title_canon_sha256":"e3575a6b651fa1290ff321835f068fe4277811869eb692b606f9acd4939c4078"},"schema_version":"1.0","source":{"id":"2305.06355","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.06355","created_at":"2026-05-18T03:42:33Z"},{"alias_kind":"arxiv_version","alias_value":"2305.06355v2","created_at":"2026-05-18T03:42:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.06355","created_at":"2026-05-18T03:42:33Z"},{"alias_kind":"pith_short_12","alias_value":"UUEWGEC4KEVJ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"UUEWGEC4KEVJJ3XG","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"UUEWGEC4","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:c5f34217acd99886b0ba7c089f82283ce3af93bc7d91468d83799fb1f85ef67b","target":"graph","created_at":"2026-05-18T03:42:33Z","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":"It integrates video foundation models and large language models via a learnable neural interface, excelling in spatiotemporal reasoning, event localization, and causal relationship inference."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The learnable neural interface, when trained on the video-centric instruction dataset, can bridge modalities sufficiently to enable the claimed excelling performance in spatiotemporal reasoning, event localization, and causal inference."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"VideoChat integrates video models and LLMs via a learnable interface for chat-based spatiotemporal and causal video reasoning, trained on a new video-centric instruction dataset."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"VideoChat links video models to language models with a trainable interface for conversational video analysis."}],"snapshot_sha256":"ff8cbb0f3075d80c5db2fdcfa739184cfe47ea6c0c72e1606b45e82bdb5397f6"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"fb45cd2fb87402480b3d0a8f5e8dda9f660e6aa48669229c03004cce4c248872"},"paper":{"abstract_excerpt":"In this paper, we initiate an attempt of developing an end-to-end chat-centric video understanding system, coined as VideoChat. It integrates video foundation models and large language models via a learnable neural interface, excelling in spatiotemporal reasoning, event localization, and causal relationship inference. To instructively tune this system, we build a video-centric instruction dataset, composed of thousands of videos associated with detailed descriptions and conversations. This dataset emphasizes spatiotemporal reasoning and captures causal relationships, providing a valuable asset","authors_text":"Kunchang Li, Limin Wang, Ping Luo, Wenhai Wang, Yali Wang, Yinan He, Yi Wang, Yizhuo Li, Yu Qiao","cross_cats":["cs.CL"],"headline":"VideoChat links video models to language models with a trainable interface for conversational video analysis.","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-10T17:59:04Z","title":"VideoChat: Chat-Centric Video Understanding"},"references":{"count":59,"internal_anchors":16,"resolved_work":59,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Anas Awadalla, Irena Gao, Joshua Gardner, Jack Hessel, Yusuf Hanafy, Wanrong Zhu, Kalyani Marathe, Yonatan Bitton, Samir Gadre, Jenia Jitsev, Simon Kornblith, Pang Wei Koh, Gabriel Ilharco, Mitchell W","work_id":"fe04ce32-7667-49a6-912b-ca2a272d8271","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Frozen in time: A joint video and image encoder for end-to-end retrieval","work_id":"14d60c0b-f95c-4e49-877b-d7529b229ac7","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Language models are few-shot learners","work_id":"06921215-168b-4266-a8bd-53d84ad473f0","year":1901},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Conceptual 12m: Pushing web-scale image-text pre-training to recognize long-tail visual concepts","work_id":"5d3c3db1-3a21-4551-8576-912217ab41b4","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Internvideo-ego4d: A pack of champion solutions to ego4d challenges","work_id":"54773a77-a0f2-43d2-9158-858d1d0652f9","year":2022}],"snapshot_sha256":"6788a45ae2d9d3b0e3f5c204c7777f62ca61f23bda4dc00d70d6df1cfb18a6b2"},"source":{"id":"2305.06355","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-13T23:25:41.740675Z","id":"b1096997-ef4c-4177-80f0-c458f9275bc2","model_set":{"reader":"grok-4.3"},"one_line_summary":"VideoChat integrates video models and LLMs via a learnable interface for chat-based spatiotemporal and causal video reasoning, trained on a new video-centric instruction dataset.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"VideoChat links video models to language models with a trainable interface for conversational video analysis.","strongest_claim":"It integrates video foundation models and large language models via a learnable neural interface, excelling in spatiotemporal reasoning, event localization, and causal relationship inference.","weakest_assumption":"The learnable neural interface, when trained on the video-centric instruction dataset, can bridge modalities sufficiently to enable the claimed excelling performance in spatiotemporal reasoning, event localization, and causal inference."}},"verdict_id":"b1096997-ef4c-4177-80f0-c458f9275bc2"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c18402a20cf417f920707f3e4fc54ddc9bf31d69e19d70712c62f2546b20752b","target":"record","created_at":"2026-05-18T03:42:33Z","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":"599fdd9894ff7225f523216572baeefc1fd0de5fe5a54f8a08366467878be7b1","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-10T17:59:04Z","title_canon_sha256":"e3575a6b651fa1290ff321835f068fe4277811869eb692b606f9acd4939c4078"},"schema_version":"1.0","source":{"id":"2305.06355","kind":"arxiv","version":2}},"canonical_sha256":"a50963105c512a94eee6828f83dce8a9b03ddea7ca8b559f08471598dbfbcf55","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a50963105c512a94eee6828f83dce8a9b03ddea7ca8b559f08471598dbfbcf55","first_computed_at":"2026-05-18T03:42:33.150268Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:42:33.150268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/MKJIE+h0QCfW928nViuM+r9Nrgx1vWaG0+ZaRNCcKtvNAHv2RrkAuAq/yw9qPzE0X3uzZwJRviC+MmAFlmoAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:42:33.150844Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.06355","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c18402a20cf417f920707f3e4fc54ddc9bf31d69e19d70712c62f2546b20752b","sha256:c5f34217acd99886b0ba7c089f82283ce3af93bc7d91468d83799fb1f85ef67b"],"state_sha256":"c54b9639216f01a4d7b792440bf74bb801f5099259bd4a5851b5312ae2a1b4e3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CyBNsjr9sapx8/FyZ2HqJ5d4MAToKqRPV4uYEsfUoRz2qe00qK4Sv/szNvOtuSjgd2hw1SL05EzlOK25aLzyBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T14:53:59.620015Z","bundle_sha256":"f633ebdde10a4d4568ee79e072a726d5e93cbb608c7280e51253b09824593d0b"}}