{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BCDRNTECU7VEMPSZNQZW6IBZN2","short_pith_number":"pith:BCDRNTEC","schema_version":"1.0","canonical_sha256":"088716cc82a7ea463e596c336f20396ea3af7c81763c154b1a362b1aecd76826","source":{"kind":"arxiv","id":"2203.08568","version":3},"attestation_state":"computed","paper":{"title":"In-Context Learning for Few-Shot Dialogue State Tracking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chia-Hsuan Lee, Mari Ostendorf, Noah A. Smith, Tao Yu, Tianbao Xie, Yushi Hu","submitted_at":"2022-03-16T11:58:24Z","abstract_excerpt":"Collecting and annotating task-oriented dialogues is time-consuming and costly; thus, zero and few shot learning could greatly benefit dialogue state tracking (DST). In this work, we propose an in-context learning (ICL) framework for zero-shot and few-shot learning DST, where a large pre-trained language model (LM) takes a test instance and a few exemplars as input, and directly decodes the dialogue state without any parameter updates. To better leverage a tabular domain description in the LM prompt, we reformulate DST into a text-to-SQL problem. We also propose a novel approach to retrieve an"},"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":"2203.08568","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-16T11:58:24Z","cross_cats_sorted":[],"title_canon_sha256":"55880f153e66d5f3536321b9b0cfca0e159427b5ab67507e835675669496cbc7","abstract_canon_sha256":"6c90b3496629e75ed88b82443afcf1b5441676e750fbba22de1edc1b24462cce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:10:36.974164Z","signature_b64":"pLtLUcXnBKZnBDDlt6e4TSWKjSbXf3sTiJ2gWU8Qfg7mdf2bfcJ9g3qAOWsbzc2jQg9l9HlnpWjpJnImJ1wUDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"088716cc82a7ea463e596c336f20396ea3af7c81763c154b1a362b1aecd76826","last_reissued_at":"2026-07-05T05:10:36.973653Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:10:36.973653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In-Context Learning for Few-Shot Dialogue State Tracking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chia-Hsuan Lee, Mari Ostendorf, Noah A. Smith, Tao Yu, Tianbao Xie, Yushi Hu","submitted_at":"2022-03-16T11:58:24Z","abstract_excerpt":"Collecting and annotating task-oriented dialogues is time-consuming and costly; thus, zero and few shot learning could greatly benefit dialogue state tracking (DST). In this work, we propose an in-context learning (ICL) framework for zero-shot and few-shot learning DST, where a large pre-trained language model (LM) takes a test instance and a few exemplars as input, and directly decodes the dialogue state without any parameter updates. To better leverage a tabular domain description in the LM prompt, we reformulate DST into a text-to-SQL problem. We also propose a novel approach to retrieve an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.08568","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2203.08568/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":"2203.08568","created_at":"2026-07-05T05:10:36.973715+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.08568v3","created_at":"2026-07-05T05:10:36.973715+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.08568","created_at":"2026-07-05T05:10:36.973715+00:00"},{"alias_kind":"pith_short_12","alias_value":"BCDRNTECU7VE","created_at":"2026-07-05T05:10:36.973715+00:00"},{"alias_kind":"pith_short_16","alias_value":"BCDRNTECU7VEMPSZ","created_at":"2026-07-05T05:10:36.973715+00:00"},{"alias_kind":"pith_short_8","alias_value":"BCDRNTEC","created_at":"2026-07-05T05:10:36.973715+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.04449","citing_title":"GEM: Graph-Enhanced Mixture-of-Experts with ReAct Agents for Dialogue State Tracking","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BCDRNTECU7VEMPSZNQZW6IBZN2","json":"https://pith.science/pith/BCDRNTECU7VEMPSZNQZW6IBZN2.json","graph_json":"https://pith.science/api/pith-number/BCDRNTECU7VEMPSZNQZW6IBZN2/graph.json","events_json":"https://pith.science/api/pith-number/BCDRNTECU7VEMPSZNQZW6IBZN2/events.json","paper":"https://pith.science/paper/BCDRNTEC"},"agent_actions":{"view_html":"https://pith.science/pith/BCDRNTECU7VEMPSZNQZW6IBZN2","download_json":"https://pith.science/pith/BCDRNTECU7VEMPSZNQZW6IBZN2.json","view_paper":"https://pith.science/paper/BCDRNTEC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.08568&json=true","fetch_graph":"https://pith.science/api/pith-number/BCDRNTECU7VEMPSZNQZW6IBZN2/graph.json","fetch_events":"https://pith.science/api/pith-number/BCDRNTECU7VEMPSZNQZW6IBZN2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BCDRNTECU7VEMPSZNQZW6IBZN2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BCDRNTECU7VEMPSZNQZW6IBZN2/action/storage_attestation","attest_author":"https://pith.science/pith/BCDRNTECU7VEMPSZNQZW6IBZN2/action/author_attestation","sign_citation":"https://pith.science/pith/BCDRNTECU7VEMPSZNQZW6IBZN2/action/citation_signature","submit_replication":"https://pith.science/pith/BCDRNTECU7VEMPSZNQZW6IBZN2/action/replication_record"}},"created_at":"2026-07-05T05:10:36.973715+00:00","updated_at":"2026-07-05T05:10:36.973715+00:00"}