{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:6ICF4JZYSO33RIJLRFBIZBYZ54","short_pith_number":"pith:6ICF4JZY","schema_version":"1.0","canonical_sha256":"f2045e273893b7b8a12b89428c8719ef3a1e4761e1d022f5da2a4917e7021d33","source":{"kind":"arxiv","id":"2002.04793","version":2},"attestation_state":"computed","paper":{"title":"ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Baolin Peng, Jianfeng Gao, Jinchao Li, Minlie Huang, Qi Zhu, Ryuichi Takanobu, Xiang Li, Xiaoyan Zhu, Yan Fang, Zheng Zhang","submitted_at":"2020-02-12T04:31:40Z","abstract_excerpt":"We present ConvLab-2, an open-source toolkit that enables researchers to build task-oriented dialogue systems with state-of-the-art models, perform an end-to-end evaluation, and diagnose the weakness of systems. As the successor of ConvLab (Lee et al., 2019b), ConvLab-2 inherits ConvLab's framework but integrates more powerful dialogue models and supports more datasets. Besides, we have developed an analysis tool and an interactive tool to assist researchers in diagnosing dialogue systems. The analysis tool presents rich statistics and summarizes common mistakes from simulated dialogues, which"},"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":"2002.04793","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-12T04:31:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a88602f4fce019af26486097442334036fb845eeca7fb7b0fa33c75f9296e54d","abstract_canon_sha256":"d121d58876efa208b4b7e204befef87fc0a16983fe1dacf1a0399b481aed2c9a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:14.313960Z","signature_b64":"uHzy4pMWWAJ4TeZwhsZRn6xTtuOyrc4Msu7TcxL3gM65D8yqvi1LkIPvSeKaKI4HTRm9oUPWKAc8kjCFIpYlAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2045e273893b7b8a12b89428c8719ef3a1e4761e1d022f5da2a4917e7021d33","last_reissued_at":"2026-07-05T00:59:14.313477Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:14.313477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Baolin Peng, Jianfeng Gao, Jinchao Li, Minlie Huang, Qi Zhu, Ryuichi Takanobu, Xiang Li, Xiaoyan Zhu, Yan Fang, Zheng Zhang","submitted_at":"2020-02-12T04:31:40Z","abstract_excerpt":"We present ConvLab-2, an open-source toolkit that enables researchers to build task-oriented dialogue systems with state-of-the-art models, perform an end-to-end evaluation, and diagnose the weakness of systems. As the successor of ConvLab (Lee et al., 2019b), ConvLab-2 inherits ConvLab's framework but integrates more powerful dialogue models and supports more datasets. Besides, we have developed an analysis tool and an interactive tool to assist researchers in diagnosing dialogue systems. The analysis tool presents rich statistics and summarizes common mistakes from simulated dialogues, which"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.04793","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/2002.04793/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":"2002.04793","created_at":"2026-07-05T00:59:14.313536+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.04793v2","created_at":"2026-07-05T00:59:14.313536+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.04793","created_at":"2026-07-05T00:59:14.313536+00:00"},{"alias_kind":"pith_short_12","alias_value":"6ICF4JZYSO33","created_at":"2026-07-05T00:59:14.313536+00:00"},{"alias_kind":"pith_short_16","alias_value":"6ICF4JZYSO33RIJL","created_at":"2026-07-05T00:59:14.313536+00:00"},{"alias_kind":"pith_short_8","alias_value":"6ICF4JZY","created_at":"2026-07-05T00:59:14.313536+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.23345","citing_title":"Bridging Reasoning and Action: Hybrid LLM-RL Framework for Efficient Cross-Domain Task-Oriented Dialogue","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6ICF4JZYSO33RIJLRFBIZBYZ54","json":"https://pith.science/pith/6ICF4JZYSO33RIJLRFBIZBYZ54.json","graph_json":"https://pith.science/api/pith-number/6ICF4JZYSO33RIJLRFBIZBYZ54/graph.json","events_json":"https://pith.science/api/pith-number/6ICF4JZYSO33RIJLRFBIZBYZ54/events.json","paper":"https://pith.science/paper/6ICF4JZY"},"agent_actions":{"view_html":"https://pith.science/pith/6ICF4JZYSO33RIJLRFBIZBYZ54","download_json":"https://pith.science/pith/6ICF4JZYSO33RIJLRFBIZBYZ54.json","view_paper":"https://pith.science/paper/6ICF4JZY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.04793&json=true","fetch_graph":"https://pith.science/api/pith-number/6ICF4JZYSO33RIJLRFBIZBYZ54/graph.json","fetch_events":"https://pith.science/api/pith-number/6ICF4JZYSO33RIJLRFBIZBYZ54/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6ICF4JZYSO33RIJLRFBIZBYZ54/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6ICF4JZYSO33RIJLRFBIZBYZ54/action/storage_attestation","attest_author":"https://pith.science/pith/6ICF4JZYSO33RIJLRFBIZBYZ54/action/author_attestation","sign_citation":"https://pith.science/pith/6ICF4JZYSO33RIJLRFBIZBYZ54/action/citation_signature","submit_replication":"https://pith.science/pith/6ICF4JZYSO33RIJLRFBIZBYZ54/action/replication_record"}},"created_at":"2026-07-05T00:59:14.313536+00:00","updated_at":"2026-07-05T00:59:14.313536+00:00"}