{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:EQYN3GEQXWWRPZ7O4RHWFTOXDH","short_pith_number":"pith:EQYN3GEQ","schema_version":"1.0","canonical_sha256":"2430dd9890bdad17e7eee44f62cdd719fbb72c9ca0d3a9e6b9d1684f5b523eb9","source":{"kind":"arxiv","id":"2008.03946","version":2},"attestation_state":"computed","paper":{"title":"A Large-Scale Chinese Short-Text Conversation Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kaili Huang, Minlie Huang, Pei Ke, Xiaoyan Zhu, Yida Wang, Yinhe Zheng, Yong Jiang","submitted_at":"2020-08-10T08:12:49Z","abstract_excerpt":"The advancements of neural dialogue generation models show promising results on modeling short-text conversations. However, training such models usually needs a large-scale high-quality dialogue corpus, which is hard to access. In this paper, we present a large-scale cleaned Chinese conversation dataset, LCCC, which contains a base version (6.8million dialogues) and a large version (12.0 million dialogues). The quality of our dataset is ensured by a rigorous data cleaning pipeline, which is built based on a set of rules and a classifier that is trained on manually annotated 110K dialogue pairs"},"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":"2008.03946","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-10T08:12:49Z","cross_cats_sorted":[],"title_canon_sha256":"05a77c517f7e6bcf0665ab646acdaec60100c54da9ddc165754d72764d395c1d","abstract_canon_sha256":"efbecaaef1030c93634ec69d7e94b96758c428cf84c9a96bf4909446e6c89e5a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:17:33.945703Z","signature_b64":"9BpHaTpR0RA4BLXdcpPMGPQFq4Kt+ZJTSe1+0GiGuijtoiCu0nbZ+wHsz1stDTOMG2yBQuePT1mlTulQrfnTCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2430dd9890bdad17e7eee44f62cdd719fbb72c9ca0d3a9e6b9d1684f5b523eb9","last_reissued_at":"2026-07-05T04:17:33.945258Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:17:33.945258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Large-Scale Chinese Short-Text Conversation Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kaili Huang, Minlie Huang, Pei Ke, Xiaoyan Zhu, Yida Wang, Yinhe Zheng, Yong Jiang","submitted_at":"2020-08-10T08:12:49Z","abstract_excerpt":"The advancements of neural dialogue generation models show promising results on modeling short-text conversations. However, training such models usually needs a large-scale high-quality dialogue corpus, which is hard to access. In this paper, we present a large-scale cleaned Chinese conversation dataset, LCCC, which contains a base version (6.8million dialogues) and a large version (12.0 million dialogues). The quality of our dataset is ensured by a rigorous data cleaning pipeline, which is built based on a set of rules and a classifier that is trained on manually annotated 110K dialogue pairs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.03946","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/2008.03946/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":"2008.03946","created_at":"2026-07-05T04:17:33.945322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.03946v2","created_at":"2026-07-05T04:17:33.945322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.03946","created_at":"2026-07-05T04:17:33.945322+00:00"},{"alias_kind":"pith_short_12","alias_value":"EQYN3GEQXWWR","created_at":"2026-07-05T04:17:33.945322+00:00"},{"alias_kind":"pith_short_16","alias_value":"EQYN3GEQXWWRPZ7O","created_at":"2026-07-05T04:17:33.945322+00:00"},{"alias_kind":"pith_short_8","alias_value":"EQYN3GEQ","created_at":"2026-07-05T04:17:33.945322+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/EQYN3GEQXWWRPZ7O4RHWFTOXDH","json":"https://pith.science/pith/EQYN3GEQXWWRPZ7O4RHWFTOXDH.json","graph_json":"https://pith.science/api/pith-number/EQYN3GEQXWWRPZ7O4RHWFTOXDH/graph.json","events_json":"https://pith.science/api/pith-number/EQYN3GEQXWWRPZ7O4RHWFTOXDH/events.json","paper":"https://pith.science/paper/EQYN3GEQ"},"agent_actions":{"view_html":"https://pith.science/pith/EQYN3GEQXWWRPZ7O4RHWFTOXDH","download_json":"https://pith.science/pith/EQYN3GEQXWWRPZ7O4RHWFTOXDH.json","view_paper":"https://pith.science/paper/EQYN3GEQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.03946&json=true","fetch_graph":"https://pith.science/api/pith-number/EQYN3GEQXWWRPZ7O4RHWFTOXDH/graph.json","fetch_events":"https://pith.science/api/pith-number/EQYN3GEQXWWRPZ7O4RHWFTOXDH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EQYN3GEQXWWRPZ7O4RHWFTOXDH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EQYN3GEQXWWRPZ7O4RHWFTOXDH/action/storage_attestation","attest_author":"https://pith.science/pith/EQYN3GEQXWWRPZ7O4RHWFTOXDH/action/author_attestation","sign_citation":"https://pith.science/pith/EQYN3GEQXWWRPZ7O4RHWFTOXDH/action/citation_signature","submit_replication":"https://pith.science/pith/EQYN3GEQXWWRPZ7O4RHWFTOXDH/action/replication_record"}},"created_at":"2026-07-05T04:17:33.945322+00:00","updated_at":"2026-07-05T04:17:33.945322+00:00"}