{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GYJW6EC2WMDKYR6COZFFPMOLE4","short_pith_number":"pith:GYJW6EC2","schema_version":"1.0","canonical_sha256":"36136f105ab306ac47c2764a57b1cb271c4b9e2696f38544873586e64c78487b","source":{"kind":"arxiv","id":"2303.09713","version":2},"attestation_state":"computed","paper":{"title":"CHAMPAGNE: Learning Real-world Conversation from Large-Scale Web Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jack Hessel, Nouha Dziri, Seungju Han, Yejin Choi, Youngjae Yu","submitted_at":"2023-03-17T01:10:33Z","abstract_excerpt":"Visual information is central to conversation: body gestures and physical behaviour, for example, contribute to meaning that transcends words alone. To date, however, most neural conversational models are limited to just text. We introduce CHAMPAGNE, a generative model of conversations that can account for visual contexts. To train CHAMPAGNE, we collect and release YTD-18M, a large-scale corpus of 18M video-based dialogues. YTD-18M is constructed from web videos: crucial to our data collection pipeline is a pretrained language model that converts error-prone automatic transcripts to a cleaner "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2303.09713","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-17T01:10:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"739e5477e7036a9207acbd140d5e6b300cf5d9186e9ae4830361a1263c7e77bb","abstract_canon_sha256":"c11ef43c50ebc7161402b7c3a069fcda2ff1079a3529ae4d7e2f71a4a0121c5c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:41:47.743927Z","signature_b64":"qPLFdoB4OWhGPGzTgkBzTiy3ES0DQOYJYmw4i1lXPFunk0ZcWb+LEKXO9meoDwCtA63hKA/ZYsVpbUkFdVqeCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36136f105ab306ac47c2764a57b1cb271c4b9e2696f38544873586e64c78487b","last_reissued_at":"2026-07-05T06:41:47.743437Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:41:47.743437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CHAMPAGNE: Learning Real-world Conversation from Large-Scale Web Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jack Hessel, Nouha Dziri, Seungju Han, Yejin Choi, Youngjae Yu","submitted_at":"2023-03-17T01:10:33Z","abstract_excerpt":"Visual information is central to conversation: body gestures and physical behaviour, for example, contribute to meaning that transcends words alone. To date, however, most neural conversational models are limited to just text. We introduce CHAMPAGNE, a generative model of conversations that can account for visual contexts. To train CHAMPAGNE, we collect and release YTD-18M, a large-scale corpus of 18M video-based dialogues. YTD-18M is constructed from web videos: crucial to our data collection pipeline is a pretrained language model that converts error-prone automatic transcripts to a cleaner "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.09713","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2303.09713/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2303.09713","created_at":"2026-07-05T06:41:47.743495+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.09713v2","created_at":"2026-07-05T06:41:47.743495+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.09713","created_at":"2026-07-05T06:41:47.743495+00:00"},{"alias_kind":"pith_short_12","alias_value":"GYJW6EC2WMDK","created_at":"2026-07-05T06:41:47.743495+00:00"},{"alias_kind":"pith_short_16","alias_value":"GYJW6EC2WMDKYR6C","created_at":"2026-07-05T06:41:47.743495+00:00"},{"alias_kind":"pith_short_8","alias_value":"GYJW6EC2","created_at":"2026-07-05T06:41:47.743495+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GYJW6EC2WMDKYR6COZFFPMOLE4","json":"https://pith.science/pith/GYJW6EC2WMDKYR6COZFFPMOLE4.json","graph_json":"https://pith.science/api/pith-number/GYJW6EC2WMDKYR6COZFFPMOLE4/graph.json","events_json":"https://pith.science/api/pith-number/GYJW6EC2WMDKYR6COZFFPMOLE4/events.json","paper":"https://pith.science/paper/GYJW6EC2"},"agent_actions":{"view_html":"https://pith.science/pith/GYJW6EC2WMDKYR6COZFFPMOLE4","download_json":"https://pith.science/pith/GYJW6EC2WMDKYR6COZFFPMOLE4.json","view_paper":"https://pith.science/paper/GYJW6EC2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.09713&json=true","fetch_graph":"https://pith.science/api/pith-number/GYJW6EC2WMDKYR6COZFFPMOLE4/graph.json","fetch_events":"https://pith.science/api/pith-number/GYJW6EC2WMDKYR6COZFFPMOLE4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GYJW6EC2WMDKYR6COZFFPMOLE4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GYJW6EC2WMDKYR6COZFFPMOLE4/action/storage_attestation","attest_author":"https://pith.science/pith/GYJW6EC2WMDKYR6COZFFPMOLE4/action/author_attestation","sign_citation":"https://pith.science/pith/GYJW6EC2WMDKYR6COZFFPMOLE4/action/citation_signature","submit_replication":"https://pith.science/pith/GYJW6EC2WMDKYR6COZFFPMOLE4/action/replication_record"}},"created_at":"2026-07-05T06:41:47.743495+00:00","updated_at":"2026-07-05T06:41:47.743495+00:00"}