{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:EQYN3GEQXWWRPZ7O4RHWFTOXDH","short_pith_number":"pith:EQYN3GEQ","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"},"canonical_sha256":"2430dd9890bdad17e7eee44f62cdd719fbb72c9ca0d3a9e6b9d1684f5b523eb9","source":{"kind":"arxiv","id":"2008.03946","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.03946","created_at":"2026-07-05T04:17:33Z"},{"alias_kind":"arxiv_version","alias_value":"2008.03946v2","created_at":"2026-07-05T04:17:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.03946","created_at":"2026-07-05T04:17:33Z"},{"alias_kind":"pith_short_12","alias_value":"EQYN3GEQXWWR","created_at":"2026-07-05T04:17:33Z"},{"alias_kind":"pith_short_16","alias_value":"EQYN3GEQXWWRPZ7O","created_at":"2026-07-05T04:17:33Z"},{"alias_kind":"pith_short_8","alias_value":"EQYN3GEQ","created_at":"2026-07-05T04:17:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:EQYN3GEQXWWRPZ7O4RHWFTOXDH","target":"record","payload":{"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"},"canonical_sha256":"2430dd9890bdad17e7eee44f62cdd719fbb72c9ca0d3a9e6b9d1684f5b523eb9","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"},"source_kind":"arxiv","source_id":"2008.03946","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":"2026-07-05T04:17:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1ySWTtXLk4h8l7I4kWkMLqXZfQZGV6nY4SoajAo6WmfT9eM0kusaqkAZW5WpGzZlbF9K7pJlfXwb8yZ7zi7BDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:48:33.014239Z"},"content_sha256":"867d37cecb769a41117cfffb107ca98e786f78e61e3ac4a33eef514506fd56d9","schema_version":"1.0","event_id":"sha256:867d37cecb769a41117cfffb107ca98e786f78e61e3ac4a33eef514506fd56d9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:EQYN3GEQXWWRPZ7O4RHWFTOXDH","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:17:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hFrw0P4ISkDdmgPyKu6W1eKNkTbA38jVEX+YMM5NsKBKOGQdoj1Fhz325QXcHJOAZN4zuRnvjBC1UHu3kVxZCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:48:33.014814Z"},"content_sha256":"8ce1a9dbfa9339bc9a14fb5f8baa84b6b26662cf288fd49e6e429de81e4e45b4","schema_version":"1.0","event_id":"sha256:8ce1a9dbfa9339bc9a14fb5f8baa84b6b26662cf288fd49e6e429de81e4e45b4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EQYN3GEQXWWRPZ7O4RHWFTOXDH/bundle.json","state_url":"https://pith.science/pith/EQYN3GEQXWWRPZ7O4RHWFTOXDH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EQYN3GEQXWWRPZ7O4RHWFTOXDH/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":"2026-08-03T18:48:33Z","links":{"resolver":"https://pith.science/pith/EQYN3GEQXWWRPZ7O4RHWFTOXDH","bundle":"https://pith.science/pith/EQYN3GEQXWWRPZ7O4RHWFTOXDH/bundle.json","state":"https://pith.science/pith/EQYN3GEQXWWRPZ7O4RHWFTOXDH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EQYN3GEQXWWRPZ7O4RHWFTOXDH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:EQYN3GEQXWWRPZ7O4RHWFTOXDH","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":"efbecaaef1030c93634ec69d7e94b96758c428cf84c9a96bf4909446e6c89e5a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-10T08:12:49Z","title_canon_sha256":"05a77c517f7e6bcf0665ab646acdaec60100c54da9ddc165754d72764d395c1d"},"schema_version":"1.0","source":{"id":"2008.03946","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.03946","created_at":"2026-07-05T04:17:33Z"},{"alias_kind":"arxiv_version","alias_value":"2008.03946v2","created_at":"2026-07-05T04:17:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.03946","created_at":"2026-07-05T04:17:33Z"},{"alias_kind":"pith_short_12","alias_value":"EQYN3GEQXWWR","created_at":"2026-07-05T04:17:33Z"},{"alias_kind":"pith_short_16","alias_value":"EQYN3GEQXWWRPZ7O","created_at":"2026-07-05T04:17:33Z"},{"alias_kind":"pith_short_8","alias_value":"EQYN3GEQ","created_at":"2026-07-05T04:17:33Z"}],"graph_snapshots":[{"event_id":"sha256:8ce1a9dbfa9339bc9a14fb5f8baa84b6b26662cf288fd49e6e429de81e4e45b4","target":"graph","created_at":"2026-07-05T04:17:33Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2008.03946/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Kaili Huang, Minlie Huang, Pei Ke, Xiaoyan Zhu, Yida Wang, Yinhe Zheng, Yong Jiang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-10T08:12:49Z","title":"A Large-Scale Chinese Short-Text Conversation Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.03946","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":"sha256:867d37cecb769a41117cfffb107ca98e786f78e61e3ac4a33eef514506fd56d9","target":"record","created_at":"2026-07-05T04:17:33Z","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":"efbecaaef1030c93634ec69d7e94b96758c428cf84c9a96bf4909446e6c89e5a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-10T08:12:49Z","title_canon_sha256":"05a77c517f7e6bcf0665ab646acdaec60100c54da9ddc165754d72764d395c1d"},"schema_version":"1.0","source":{"id":"2008.03946","kind":"arxiv","version":2}},"canonical_sha256":"2430dd9890bdad17e7eee44f62cdd719fbb72c9ca0d3a9e6b9d1684f5b523eb9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2430dd9890bdad17e7eee44f62cdd719fbb72c9ca0d3a9e6b9d1684f5b523eb9","first_computed_at":"2026-07-05T04:17:33.945258Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:17:33.945258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9BpHaTpR0RA4BLXdcpPMGPQFq4Kt+ZJTSe1+0GiGuijtoiCu0nbZ+wHsz1stDTOMG2yBQuePT1mlTulQrfnTCw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:17:33.945703Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.03946","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:867d37cecb769a41117cfffb107ca98e786f78e61e3ac4a33eef514506fd56d9","sha256:8ce1a9dbfa9339bc9a14fb5f8baa84b6b26662cf288fd49e6e429de81e4e45b4"],"state_sha256":"9d05513d06decdbfac706588b73125e11c59ded30d1c6cc4f8b0452e69191e8e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uttDmBk1dtc77cjvHzzdehTGTXSWI4Cu4aBPsahwaB4Mmb1h5TLMInkGY6Iv1rMP4y6mN6FDWdYzaGQ6nJokDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T18:48:33.020202Z","bundle_sha256":"68bbdab0f84abceaa1ac926b3e856e3558d4abfed21272c1188257b87691ab79"}}