{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VT7IW2DEYS5RMRUBXK2FPJT5ZV","short_pith_number":"pith:VT7IW2DE","schema_version":"1.0","canonical_sha256":"acfe8b6864c4bb164681bab457a67dcd4ccb961b705101a290551bcabeb23ab8","source":{"kind":"arxiv","id":"1805.09655","version":3},"attestation_state":"computed","paper":{"title":"Global-Locally Self-Attentive Dialogue State Tracker","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Caiming Xiong, Richard Socher, Victor Zhong","submitted_at":"2018-05-19T19:23:38Z","abstract_excerpt":"Dialogue state tracking, which estimates user goals and requests given the dialogue context, is an essential part of task-oriented dialogue systems. In this paper, we propose the Global-Locally Self-Attentive Dialogue State Tracker (GLAD), which learns representations of the user utterance and previous system actions with global-local modules. Our model uses global modules to share parameters between estimators for different types (called slots) of dialogue states, and uses local modules to learn slot-specific features. We show that this significantly improves tracking of rare states and achie"},"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":"1805.09655","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-19T19:23:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"faa5deb34d561e5a48629e1b10a186a6e70a14d5f6d1d2c77eae267bf8c52265","abstract_canon_sha256":"267f55306d49faca3cd3af7138806f25f32097b4106725601a7d84d0f04bf4e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:20.208680Z","signature_b64":"g0NyF1NUZ413wC84oTaxqE+X6x1iIwLIX+9D7+geY0VfOo7l1D7uIezkn3/mIGgpDocw8xyg+Zdas1S7wnd4Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acfe8b6864c4bb164681bab457a67dcd4ccb961b705101a290551bcabeb23ab8","last_reissued_at":"2026-05-18T00:06:20.208061Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:20.208061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Global-Locally Self-Attentive Dialogue State Tracker","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Caiming Xiong, Richard Socher, Victor Zhong","submitted_at":"2018-05-19T19:23:38Z","abstract_excerpt":"Dialogue state tracking, which estimates user goals and requests given the dialogue context, is an essential part of task-oriented dialogue systems. In this paper, we propose the Global-Locally Self-Attentive Dialogue State Tracker (GLAD), which learns representations of the user utterance and previous system actions with global-local modules. Our model uses global modules to share parameters between estimators for different types (called slots) of dialogue states, and uses local modules to learn slot-specific features. We show that this significantly improves tracking of rare states and achie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09655","kind":"arxiv","version":3},"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":"1805.09655","created_at":"2026-05-18T00:06:20.208176+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.09655v3","created_at":"2026-05-18T00:06:20.208176+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09655","created_at":"2026-05-18T00:06:20.208176+00:00"},{"alias_kind":"pith_short_12","alias_value":"VT7IW2DEYS5R","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"VT7IW2DEYS5RMRUB","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"VT7IW2DE","created_at":"2026-05-18T12:32:59.047623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.00883","citing_title":"HyST: A Hybrid Approach for Flexible and Accurate Dialogue State Tracking","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VT7IW2DEYS5RMRUBXK2FPJT5ZV","json":"https://pith.science/pith/VT7IW2DEYS5RMRUBXK2FPJT5ZV.json","graph_json":"https://pith.science/api/pith-number/VT7IW2DEYS5RMRUBXK2FPJT5ZV/graph.json","events_json":"https://pith.science/api/pith-number/VT7IW2DEYS5RMRUBXK2FPJT5ZV/events.json","paper":"https://pith.science/paper/VT7IW2DE"},"agent_actions":{"view_html":"https://pith.science/pith/VT7IW2DEYS5RMRUBXK2FPJT5ZV","download_json":"https://pith.science/pith/VT7IW2DEYS5RMRUBXK2FPJT5ZV.json","view_paper":"https://pith.science/paper/VT7IW2DE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.09655&json=true","fetch_graph":"https://pith.science/api/pith-number/VT7IW2DEYS5RMRUBXK2FPJT5ZV/graph.json","fetch_events":"https://pith.science/api/pith-number/VT7IW2DEYS5RMRUBXK2FPJT5ZV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VT7IW2DEYS5RMRUBXK2FPJT5ZV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VT7IW2DEYS5RMRUBXK2FPJT5ZV/action/storage_attestation","attest_author":"https://pith.science/pith/VT7IW2DEYS5RMRUBXK2FPJT5ZV/action/author_attestation","sign_citation":"https://pith.science/pith/VT7IW2DEYS5RMRUBXK2FPJT5ZV/action/citation_signature","submit_replication":"https://pith.science/pith/VT7IW2DEYS5RMRUBXK2FPJT5ZV/action/replication_record"}},"created_at":"2026-05-18T00:06:20.208176+00:00","updated_at":"2026-05-18T00:06:20.208176+00:00"}