{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2BMLPVV3DK3E4XW7QNNY3HTH3L","short_pith_number":"pith:2BMLPVV3","schema_version":"1.0","canonical_sha256":"d058b7d6bb1ab64e5edf835b8d9e67dae659369134d43b8d96c16e6ded161a57","source":{"kind":"arxiv","id":"1911.09969","version":4},"attestation_state":"computed","paper":{"title":"The JDDC Corpus: A Large-Scale Multi-Turn Chinese Dialogue Dataset for E-commerce Customer Service","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Bowen Zhou, Jingyan Zhou, Lei Shen, Meng Chen, Ruixue Liu, Shaozu Yuan, Xiaodong He, Youzheng Wu","submitted_at":"2019-11-22T10:55:50Z","abstract_excerpt":"Human conversations are complicated and building a human-like dialogue agent is an extremely challenging task. With the rapid development of deep learning techniques, data-driven models become more and more prevalent which need a huge amount of real conversation data. In this paper, we construct a large-scale real scenario Chinese E-commerce conversation corpus, JDDC, with more than 1 million multi-turn dialogues, 20 million utterances, and 150 million words. The dataset reflects several characteristics of human-human conversations, e.g., goal-driven, and long-term dependency among the context"},"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":"1911.09969","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-22T10:55:50Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"293b6f8b592ec2d59d373ce4e19154061651fd118809a13e9993ed5f4e1749d5","abstract_canon_sha256":"608ce31fbf64df951bf06fcb6bc8bdb2a38f7dcc5aa8b816a334ae8a07fe2d8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:50:09.957872Z","signature_b64":"gsZMJ2nKtATLJ+9tSpcxHmsOpUcDT3bTYfs5wCLF/68WED75vsgnW0pkWgZzD7r1oDjGimpOsGWf4c7JiT5VAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d058b7d6bb1ab64e5edf835b8d9e67dae659369134d43b8d96c16e6ded161a57","last_reissued_at":"2026-07-05T00:50:09.957385Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:50:09.957385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The JDDC Corpus: A Large-Scale Multi-Turn Chinese Dialogue Dataset for E-commerce Customer Service","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Bowen Zhou, Jingyan Zhou, Lei Shen, Meng Chen, Ruixue Liu, Shaozu Yuan, Xiaodong He, Youzheng Wu","submitted_at":"2019-11-22T10:55:50Z","abstract_excerpt":"Human conversations are complicated and building a human-like dialogue agent is an extremely challenging task. With the rapid development of deep learning techniques, data-driven models become more and more prevalent which need a huge amount of real conversation data. In this paper, we construct a large-scale real scenario Chinese E-commerce conversation corpus, JDDC, with more than 1 million multi-turn dialogues, 20 million utterances, and 150 million words. The dataset reflects several characteristics of human-human conversations, e.g., goal-driven, and long-term dependency among the context"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.09969","kind":"arxiv","version":4},"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/1911.09969/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":"1911.09969","created_at":"2026-07-05T00:50:09.957438+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.09969v4","created_at":"2026-07-05T00:50:09.957438+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.09969","created_at":"2026-07-05T00:50:09.957438+00:00"},{"alias_kind":"pith_short_12","alias_value":"2BMLPVV3DK3E","created_at":"2026-07-05T00:50:09.957438+00:00"},{"alias_kind":"pith_short_16","alias_value":"2BMLPVV3DK3E4XW7","created_at":"2026-07-05T00:50:09.957438+00:00"},{"alias_kind":"pith_short_8","alias_value":"2BMLPVV3","created_at":"2026-07-05T00:50:09.957438+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.04908","citing_title":"MERCI: Multimodal Emotional and peRsonal Conversational Interactions Dataset","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2BMLPVV3DK3E4XW7QNNY3HTH3L","json":"https://pith.science/pith/2BMLPVV3DK3E4XW7QNNY3HTH3L.json","graph_json":"https://pith.science/api/pith-number/2BMLPVV3DK3E4XW7QNNY3HTH3L/graph.json","events_json":"https://pith.science/api/pith-number/2BMLPVV3DK3E4XW7QNNY3HTH3L/events.json","paper":"https://pith.science/paper/2BMLPVV3"},"agent_actions":{"view_html":"https://pith.science/pith/2BMLPVV3DK3E4XW7QNNY3HTH3L","download_json":"https://pith.science/pith/2BMLPVV3DK3E4XW7QNNY3HTH3L.json","view_paper":"https://pith.science/paper/2BMLPVV3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.09969&json=true","fetch_graph":"https://pith.science/api/pith-number/2BMLPVV3DK3E4XW7QNNY3HTH3L/graph.json","fetch_events":"https://pith.science/api/pith-number/2BMLPVV3DK3E4XW7QNNY3HTH3L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2BMLPVV3DK3E4XW7QNNY3HTH3L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2BMLPVV3DK3E4XW7QNNY3HTH3L/action/storage_attestation","attest_author":"https://pith.science/pith/2BMLPVV3DK3E4XW7QNNY3HTH3L/action/author_attestation","sign_citation":"https://pith.science/pith/2BMLPVV3DK3E4XW7QNNY3HTH3L/action/citation_signature","submit_replication":"https://pith.science/pith/2BMLPVV3DK3E4XW7QNNY3HTH3L/action/replication_record"}},"created_at":"2026-07-05T00:50:09.957438+00:00","updated_at":"2026-07-05T00:50:09.957438+00:00"}