{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WST2HX3XDM7BBUXUSNRXP6GR6V","short_pith_number":"pith:WST2HX3X","schema_version":"1.0","canonical_sha256":"b4a7a3df771b3e10d2f4936377f8d1f55e6e279c4b3cc0efc82a3876e12f6325","source":{"kind":"arxiv","id":"1907.03040","version":1},"attestation_state":"computed","paper":{"title":"BERT-DST: Scalable End-to-End Dialogue State Tracking with Bidirectional Encoder Representations from Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guan-Lin Chao, Ian Lane","submitted_at":"2019-07-05T22:41:02Z","abstract_excerpt":"An important yet rarely tackled problem in dialogue state tracking (DST) is scalability for dynamic ontology (e.g., movie, restaurant) and unseen slot values. We focus on a specific condition, where the ontology is unknown to the state tracker, but the target slot value (except for none and dontcare), possibly unseen during training, can be found as word segment in the dialogue context. Prior approaches often rely on candidate generation from n-gram enumeration or slot tagger outputs, which can be inefficient or suffer from error propagation. We propose BERT-DST, an end-to-end dialogue state 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":"1907.03040","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-05T22:41:02Z","cross_cats_sorted":[],"title_canon_sha256":"ea08b7ae178ce7831f2fc05e724b5912b0c585a6279576a9ce34655625b4482b","abstract_canon_sha256":"bc9410819b6476b4048795339b7a47b21bfd139a722e0e80c9be7ba9a938dd3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:19.093691Z","signature_b64":"t8KfOgaehomwoh2MiDfbcCo/zQYUEMSMwDlEYVCYda2S3VwO3dMMSix4aExxaBbl4w/bdcIz1UHHP/BuLd4kBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4a7a3df771b3e10d2f4936377f8d1f55e6e279c4b3cc0efc82a3876e12f6325","last_reissued_at":"2026-05-17T23:41:19.093050Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:19.093050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BERT-DST: Scalable End-to-End Dialogue State Tracking with Bidirectional Encoder Representations from Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guan-Lin Chao, Ian Lane","submitted_at":"2019-07-05T22:41:02Z","abstract_excerpt":"An important yet rarely tackled problem in dialogue state tracking (DST) is scalability for dynamic ontology (e.g., movie, restaurant) and unseen slot values. We focus on a specific condition, where the ontology is unknown to the state tracker, but the target slot value (except for none and dontcare), possibly unseen during training, can be found as word segment in the dialogue context. Prior approaches often rely on candidate generation from n-gram enumeration or slot tagger outputs, which can be inefficient or suffer from error propagation. We propose BERT-DST, an end-to-end dialogue state t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.03040","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":""},"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":"1907.03040","created_at":"2026-05-17T23:41:19.093143+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.03040v1","created_at":"2026-05-17T23:41:19.093143+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.03040","created_at":"2026-05-17T23:41:19.093143+00:00"},{"alias_kind":"pith_short_12","alias_value":"WST2HX3XDM7B","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"WST2HX3XDM7BBUXU","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"WST2HX3X","created_at":"2026-05-18T12:33:30.264802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.03040","citing_title":"BERT-DST: Scalable End-to-End Dialogue State Tracking with Bidirectional Encoder Representations from Transformer","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WST2HX3XDM7BBUXUSNRXP6GR6V","json":"https://pith.science/pith/WST2HX3XDM7BBUXUSNRXP6GR6V.json","graph_json":"https://pith.science/api/pith-number/WST2HX3XDM7BBUXUSNRXP6GR6V/graph.json","events_json":"https://pith.science/api/pith-number/WST2HX3XDM7BBUXUSNRXP6GR6V/events.json","paper":"https://pith.science/paper/WST2HX3X"},"agent_actions":{"view_html":"https://pith.science/pith/WST2HX3XDM7BBUXUSNRXP6GR6V","download_json":"https://pith.science/pith/WST2HX3XDM7BBUXUSNRXP6GR6V.json","view_paper":"https://pith.science/paper/WST2HX3X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.03040&json=true","fetch_graph":"https://pith.science/api/pith-number/WST2HX3XDM7BBUXUSNRXP6GR6V/graph.json","fetch_events":"https://pith.science/api/pith-number/WST2HX3XDM7BBUXUSNRXP6GR6V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WST2HX3XDM7BBUXUSNRXP6GR6V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WST2HX3XDM7BBUXUSNRXP6GR6V/action/storage_attestation","attest_author":"https://pith.science/pith/WST2HX3XDM7BBUXUSNRXP6GR6V/action/author_attestation","sign_citation":"https://pith.science/pith/WST2HX3XDM7BBUXUSNRXP6GR6V/action/citation_signature","submit_replication":"https://pith.science/pith/WST2HX3XDM7BBUXUSNRXP6GR6V/action/replication_record"}},"created_at":"2026-05-17T23:41:19.093143+00:00","updated_at":"2026-05-17T23:41:19.093143+00:00"}