{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:4Q74IDHKCEKWE7X6GORKPCMR7C","short_pith_number":"pith:4Q74IDHK","schema_version":"1.0","canonical_sha256":"e43fc40cea1115627efe33a2a78991f884c21f00fd64ebaa4b9ca6bea5b92e3c","source":{"kind":"arxiv","id":"2004.03329","version":2},"attestation_state":"computed","paper":{"title":"MedDialog: Two Large-scale Medical Dialogue Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hongchao Fang, Jiaqi Zeng, Meng Zhou, Penghui Zhu, Pengtao Xie, Ruisi Zhang, Ruoyu Zhang, Shu Chen, Sicheng Wang, Xiangyu Dong, Xuehai He, Yue Yang, Zeqian Ju","submitted_at":"2020-04-07T13:07:09Z","abstract_excerpt":"Medical dialogue systems are promising in assisting in telemedicine to increase access to healthcare services, improve the quality of patient care, and reduce medical costs. To facilitate the research and development of medical dialogue systems, we build two large-scale medical dialogue datasets: MedDialog-EN and MedDialog-CN. MedDialog-EN is an English dataset containing 0.3 million conversations between patients and doctors and 0.5 million utterances. MedDialog-CN is an Chinese dataset containing 1.1 million conversations and 4 million utterances. To our best knowledge, MedDialog-(EN,CN) are"},"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":"2004.03329","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-07T13:07:09Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"bfdb00b4ba47028e2fa4b600cd85d1de64e7a69e202eef49ba5aba78a9a64e27","abstract_canon_sha256":"3e72a5e3d1fec4656590dfed7041ce56e2f8b6ffefc38c00678b671b188569fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:17:07.297327Z","signature_b64":"HNLzZfFaXDd/8tD7a3h+4UAtdsrfqwxFK60d3yihSFYRBXuYQOLf6JGSYZsqqFPKzUjIwynVQW04fxEVkvuBAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e43fc40cea1115627efe33a2a78991f884c21f00fd64ebaa4b9ca6bea5b92e3c","last_reissued_at":"2026-07-05T01:17:07.296904Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:17:07.296904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MedDialog: Two Large-scale Medical Dialogue Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hongchao Fang, Jiaqi Zeng, Meng Zhou, Penghui Zhu, Pengtao Xie, Ruisi Zhang, Ruoyu Zhang, Shu Chen, Sicheng Wang, Xiangyu Dong, Xuehai He, Yue Yang, Zeqian Ju","submitted_at":"2020-04-07T13:07:09Z","abstract_excerpt":"Medical dialogue systems are promising in assisting in telemedicine to increase access to healthcare services, improve the quality of patient care, and reduce medical costs. To facilitate the research and development of medical dialogue systems, we build two large-scale medical dialogue datasets: MedDialog-EN and MedDialog-CN. MedDialog-EN is an English dataset containing 0.3 million conversations between patients and doctors and 0.5 million utterances. MedDialog-CN is an Chinese dataset containing 1.1 million conversations and 4 million utterances. To our best knowledge, MedDialog-(EN,CN) are"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.03329","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/2004.03329/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":"2004.03329","created_at":"2026-07-05T01:17:07.296962+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.03329v2","created_at":"2026-07-05T01:17:07.296962+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.03329","created_at":"2026-07-05T01:17:07.296962+00:00"},{"alias_kind":"pith_short_12","alias_value":"4Q74IDHKCEKW","created_at":"2026-07-05T01:17:07.296962+00:00"},{"alias_kind":"pith_short_16","alias_value":"4Q74IDHKCEKWE7X6","created_at":"2026-07-05T01:17:07.296962+00:00"},{"alias_kind":"pith_short_8","alias_value":"4Q74IDHK","created_at":"2026-07-05T01:17:07.296962+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22047","citing_title":"Active Evidence-Seeking and Diagnostic Reasoning in Large Language Models for Clinical Decision Support","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2505.19630","citing_title":"Real-World Doctor Agent with Proactive Consultation through Multi-Agent Reinforcement Learning","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2510.22609","citing_title":"CLIN-LLM: A Safety-Constrained Hybrid Framework for Clinical Diagnosis and Treatment Generation","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08326","citing_title":"ProMedical: Hierarchical Fine-Grained Criteria Modeling for Medical LLM Alignment via Explicit Injection","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4Q74IDHKCEKWE7X6GORKPCMR7C","json":"https://pith.science/pith/4Q74IDHKCEKWE7X6GORKPCMR7C.json","graph_json":"https://pith.science/api/pith-number/4Q74IDHKCEKWE7X6GORKPCMR7C/graph.json","events_json":"https://pith.science/api/pith-number/4Q74IDHKCEKWE7X6GORKPCMR7C/events.json","paper":"https://pith.science/paper/4Q74IDHK"},"agent_actions":{"view_html":"https://pith.science/pith/4Q74IDHKCEKWE7X6GORKPCMR7C","download_json":"https://pith.science/pith/4Q74IDHKCEKWE7X6GORKPCMR7C.json","view_paper":"https://pith.science/paper/4Q74IDHK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.03329&json=true","fetch_graph":"https://pith.science/api/pith-number/4Q74IDHKCEKWE7X6GORKPCMR7C/graph.json","fetch_events":"https://pith.science/api/pith-number/4Q74IDHKCEKWE7X6GORKPCMR7C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4Q74IDHKCEKWE7X6GORKPCMR7C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4Q74IDHKCEKWE7X6GORKPCMR7C/action/storage_attestation","attest_author":"https://pith.science/pith/4Q74IDHKCEKWE7X6GORKPCMR7C/action/author_attestation","sign_citation":"https://pith.science/pith/4Q74IDHKCEKWE7X6GORKPCMR7C/action/citation_signature","submit_replication":"https://pith.science/pith/4Q74IDHKCEKWE7X6GORKPCMR7C/action/replication_record"}},"created_at":"2026-07-05T01:17:07.296962+00:00","updated_at":"2026-07-05T01:17:07.296962+00:00"}