{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:HJRWUB3SJJNNWBQEQR2MBMF77F","short_pith_number":"pith:HJRWUB3S","schema_version":"1.0","canonical_sha256":"3a636a07724a5adb06048474c0b0bff97141c71738fcd00357f7eed85eae5256","source":{"kind":"arxiv","id":"2009.10430","version":1},"attestation_state":"computed","paper":{"title":"Dual Learning for Dialogue State Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kai Yu, Lu Chen, Su Zhu, Yanbin Zhao, Zhi Chen","submitted_at":"2020-09-22T10:15:09Z","abstract_excerpt":"In task-oriented multi-turn dialogue systems, dialogue state refers to a compact representation of the user goal in the context of dialogue history. Dialogue state tracking (DST) is to estimate the dialogue state at each turn. Due to the dependency on complicated dialogue history contexts, DST data annotation is more expensive than single-sentence language understanding, which makes the task more challenging. In this work, we formulate DST as a sequence generation problem and propose a novel dual-learning framework to make full use of unlabeled data. In the dual-learning framework, there are t"},"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":"2009.10430","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-22T10:15:09Z","cross_cats_sorted":[],"title_canon_sha256":"8130b6ce4151e4af5af71338669ddbccad73a7d8c38e08f2f03db1ab86a040d0","abstract_canon_sha256":"7bea8aa9678e35a16c06b129deefeff016b4c08fa5cdfe038bfaf592870b4577"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:37:19.194975Z","signature_b64":"Ic/Ngd/H7J/YNW2r//7XPkOOdGpg00spgKJ55IDDmCZPxhtKSGqd7ZXLc8HVNDV38oQaxarvjWYt852fzJReBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a636a07724a5adb06048474c0b0bff97141c71738fcd00357f7eed85eae5256","last_reissued_at":"2026-07-05T01:37:19.194596Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:37:19.194596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual Learning for Dialogue State Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kai Yu, Lu Chen, Su Zhu, Yanbin Zhao, Zhi Chen","submitted_at":"2020-09-22T10:15:09Z","abstract_excerpt":"In task-oriented multi-turn dialogue systems, dialogue state refers to a compact representation of the user goal in the context of dialogue history. Dialogue state tracking (DST) is to estimate the dialogue state at each turn. Due to the dependency on complicated dialogue history contexts, DST data annotation is more expensive than single-sentence language understanding, which makes the task more challenging. In this work, we formulate DST as a sequence generation problem and propose a novel dual-learning framework to make full use of unlabeled data. In the dual-learning framework, there are t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.10430","kind":"arxiv","version":1},"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/2009.10430/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":"2009.10430","created_at":"2026-07-05T01:37:19.194650+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.10430v1","created_at":"2026-07-05T01:37:19.194650+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.10430","created_at":"2026-07-05T01:37:19.194650+00:00"},{"alias_kind":"pith_short_12","alias_value":"HJRWUB3SJJNN","created_at":"2026-07-05T01:37:19.194650+00:00"},{"alias_kind":"pith_short_16","alias_value":"HJRWUB3SJJNNWBQE","created_at":"2026-07-05T01:37:19.194650+00:00"},{"alias_kind":"pith_short_8","alias_value":"HJRWUB3S","created_at":"2026-07-05T01:37:19.194650+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/HJRWUB3SJJNNWBQEQR2MBMF77F","json":"https://pith.science/pith/HJRWUB3SJJNNWBQEQR2MBMF77F.json","graph_json":"https://pith.science/api/pith-number/HJRWUB3SJJNNWBQEQR2MBMF77F/graph.json","events_json":"https://pith.science/api/pith-number/HJRWUB3SJJNNWBQEQR2MBMF77F/events.json","paper":"https://pith.science/paper/HJRWUB3S"},"agent_actions":{"view_html":"https://pith.science/pith/HJRWUB3SJJNNWBQEQR2MBMF77F","download_json":"https://pith.science/pith/HJRWUB3SJJNNWBQEQR2MBMF77F.json","view_paper":"https://pith.science/paper/HJRWUB3S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.10430&json=true","fetch_graph":"https://pith.science/api/pith-number/HJRWUB3SJJNNWBQEQR2MBMF77F/graph.json","fetch_events":"https://pith.science/api/pith-number/HJRWUB3SJJNNWBQEQR2MBMF77F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HJRWUB3SJJNNWBQEQR2MBMF77F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HJRWUB3SJJNNWBQEQR2MBMF77F/action/storage_attestation","attest_author":"https://pith.science/pith/HJRWUB3SJJNNWBQEQR2MBMF77F/action/author_attestation","sign_citation":"https://pith.science/pith/HJRWUB3SJJNNWBQEQR2MBMF77F/action/citation_signature","submit_replication":"https://pith.science/pith/HJRWUB3SJJNNWBQEQR2MBMF77F/action/replication_record"}},"created_at":"2026-07-05T01:37:19.194650+00:00","updated_at":"2026-07-05T01:37:19.194650+00:00"}