{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:2NLN7CU2I3R7ST5XLV7YBDAHNM","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":"4d0dd592bec78d46ec3b96e6f976667d370624711566adee324d18b163f7cf3f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-30T03:02:50Z","title_canon_sha256":"f52269bac3c1d80f1cc84a14ab88f7544749b9767c25d9126453ab844713453c"},"schema_version":"1.0","source":{"id":"2012.15015","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.15015","created_at":"2026-07-05T02:44:17Z"},{"alias_kind":"arxiv_version","alias_value":"2012.15015v2","created_at":"2026-07-05T02:44:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.15015","created_at":"2026-07-05T02:44:17Z"},{"alias_kind":"pith_short_12","alias_value":"2NLN7CU2I3R7","created_at":"2026-07-05T02:44:17Z"},{"alias_kind":"pith_short_16","alias_value":"2NLN7CU2I3R7ST5X","created_at":"2026-07-05T02:44:17Z"},{"alias_kind":"pith_short_8","alias_value":"2NLN7CU2","created_at":"2026-07-05T02:44:17Z"}],"graph_snapshots":[{"event_id":"sha256:9f8c47d500ca1b5b17d4b497af59c07ad40c41425a20a3366619780b1a070af6","target":"graph","created_at":"2026-07-05T02:44:17Z","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/2012.15015/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When humans converse, what a speaker will say next significantly depends on what he sees. Unfortunately, existing dialogue models generate dialogue utterances only based on preceding textual contexts, and visual contexts are rarely considered. This is due to a lack of a large-scale multi-module dialogue dataset with utterances paired with visual contexts. In this paper, we release {\\bf OpenViDial}, a large-scale multi-module dialogue dataset. The dialogue turns and visual contexts are extracted from movies and TV series, where each dialogue turn is paired with the corresponding visual context ","authors_text":"Fei Wu, Jiwei Li, Qinghong Han, Rui Yan, Shuhe Wang, Xiaofei Sun, Yuxian Meng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-30T03:02:50Z","title":"OpenViDial: A Large-Scale, Open-Domain Dialogue Dataset with Visual Contexts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.15015","kind":"arxiv","version":2},"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:ec8b52a99243f0480ea2a7d0ecc95d81fdb61a99129911d4362e901908a99b9c","target":"record","created_at":"2026-07-05T02:44:17Z","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":"4d0dd592bec78d46ec3b96e6f976667d370624711566adee324d18b163f7cf3f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-30T03:02:50Z","title_canon_sha256":"f52269bac3c1d80f1cc84a14ab88f7544749b9767c25d9126453ab844713453c"},"schema_version":"1.0","source":{"id":"2012.15015","kind":"arxiv","version":2}},"canonical_sha256":"d356df8a9a46e3f94fb75d7f808c076b311fea070c494a79127e2027f1047e0f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d356df8a9a46e3f94fb75d7f808c076b311fea070c494a79127e2027f1047e0f","first_computed_at":"2026-07-05T02:44:17.262426Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:44:17.262426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mZQL0+gx5xOaLfwP19ZTpoKvskZNOVUg2fwdyJKBldUB8HeFpAUm+yxjsNCKmUqSfzBRlalPDyYy4RsZOx7tDA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:44:17.262828Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.15015","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec8b52a99243f0480ea2a7d0ecc95d81fdb61a99129911d4362e901908a99b9c","sha256:9f8c47d500ca1b5b17d4b497af59c07ad40c41425a20a3366619780b1a070af6"],"state_sha256":"2008396a488fd7e2b46b40ddfd1f4a01a3aaf3edef0ff618eb80547f9242476a"}