{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:SFNL5J5KCFA4QKNTSEI653P4A4","short_pith_number":"pith:SFNL5J5K","schema_version":"1.0","canonical_sha256":"915abea7aa1141c829b39111eeedfc0715f9f2e305f260f97b29ba73e74f6a7b","source":{"kind":"arxiv","id":"1506.07190","version":1},"attestation_state":"computed","paper":{"title":"Multi-domain Dialog State Tracking using Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Blaise Thomson, David Vandyke, Diarmuid \\'O S\\'eaghdha, Milica Ga\\v{s}i\\'c, Nikola Mrk\\v{s}i\\'c, Pei-Hao Su, Steve Young, Tsung-Hsien Wen","submitted_at":"2015-06-23T20:16:06Z","abstract_excerpt":"Dialog state tracking is a key component of many modern dialog systems, most of which are designed with a single, well-defined domain in mind. This paper shows that dialog data drawn from different dialog domains can be used to train a general belief tracking model which can operate across all of these domains, exhibiting superior performance to each of the domain-specific models. We propose a training procedure which uses out-of-domain data to initialise belief tracking models for entirely new domains. This procedure leads to improvements in belief tracking performance regardless of the amoun"},"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":"1506.07190","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-06-23T20:16:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d332cc40db8ca26db2eff4981e0c1a43889ad5e77736aafd9dc16980fde97a0d","abstract_canon_sha256":"6e9830b99f75faee0ad5a5d585c8ff313283479f04bd696205221423303ad7a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:39:54.644131Z","signature_b64":"74rMgYnijwiVNds4/Ou6AS/DdNv9rObeELB3aNNemcWFxbhKBRpDaAgAf1Hgk5kJawcBsEW3/dN2RFTchYBLBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"915abea7aa1141c829b39111eeedfc0715f9f2e305f260f97b29ba73e74f6a7b","last_reissued_at":"2026-05-18T01:39:54.643656Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:39:54.643656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-domain Dialog State Tracking using Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Blaise Thomson, David Vandyke, Diarmuid \\'O S\\'eaghdha, Milica Ga\\v{s}i\\'c, Nikola Mrk\\v{s}i\\'c, Pei-Hao Su, Steve Young, Tsung-Hsien Wen","submitted_at":"2015-06-23T20:16:06Z","abstract_excerpt":"Dialog state tracking is a key component of many modern dialog systems, most of which are designed with a single, well-defined domain in mind. This paper shows that dialog data drawn from different dialog domains can be used to train a general belief tracking model which can operate across all of these domains, exhibiting superior performance to each of the domain-specific models. We propose a training procedure which uses out-of-domain data to initialise belief tracking models for entirely new domains. This procedure leads to improvements in belief tracking performance regardless of the amoun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.07190","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":"1506.07190","created_at":"2026-05-18T01:39:54.643713+00:00"},{"alias_kind":"arxiv_version","alias_value":"1506.07190v1","created_at":"2026-05-18T01:39:54.643713+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.07190","created_at":"2026-05-18T01:39:54.643713+00:00"},{"alias_kind":"pith_short_12","alias_value":"SFNL5J5KCFA4","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_16","alias_value":"SFNL5J5KCFA4QKNT","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_8","alias_value":"SFNL5J5K","created_at":"2026-05-18T12:29:39.896362+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/SFNL5J5KCFA4QKNTSEI653P4A4","json":"https://pith.science/pith/SFNL5J5KCFA4QKNTSEI653P4A4.json","graph_json":"https://pith.science/api/pith-number/SFNL5J5KCFA4QKNTSEI653P4A4/graph.json","events_json":"https://pith.science/api/pith-number/SFNL5J5KCFA4QKNTSEI653P4A4/events.json","paper":"https://pith.science/paper/SFNL5J5K"},"agent_actions":{"view_html":"https://pith.science/pith/SFNL5J5KCFA4QKNTSEI653P4A4","download_json":"https://pith.science/pith/SFNL5J5KCFA4QKNTSEI653P4A4.json","view_paper":"https://pith.science/paper/SFNL5J5K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1506.07190&json=true","fetch_graph":"https://pith.science/api/pith-number/SFNL5J5KCFA4QKNTSEI653P4A4/graph.json","fetch_events":"https://pith.science/api/pith-number/SFNL5J5KCFA4QKNTSEI653P4A4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SFNL5J5KCFA4QKNTSEI653P4A4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SFNL5J5KCFA4QKNTSEI653P4A4/action/storage_attestation","attest_author":"https://pith.science/pith/SFNL5J5KCFA4QKNTSEI653P4A4/action/author_attestation","sign_citation":"https://pith.science/pith/SFNL5J5KCFA4QKNTSEI653P4A4/action/citation_signature","submit_replication":"https://pith.science/pith/SFNL5J5KCFA4QKNTSEI653P4A4/action/replication_record"}},"created_at":"2026-05-18T01:39:54.643713+00:00","updated_at":"2026-05-18T01:39:54.643713+00:00"}