{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7VCFZ253K5B45CSHKPJ7M65EF2","short_pith_number":"pith:7VCFZ253","schema_version":"1.0","canonical_sha256":"fd445cebbb5743ce8a4753d3f67ba42e89fc7acbfa1a56a689124dcaffee921f","source":{"kind":"arxiv","id":"2402.12234","version":1},"attestation_state":"computed","paper":{"title":"Task-Oriented Dialogue with In-Context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alan Nichol, Daksh Varshneya, Thomas Werkmeister, Tom Bocklisch","submitted_at":"2024-02-19T15:43:35Z","abstract_excerpt":"We describe a system for building task-oriented dialogue systems combining the in-context learning abilities of large language models (LLMs) with the deterministic execution of business logic. LLMs are used to translate between the surface form of the conversation and a domain-specific language (DSL) which is used to progress the business logic. We compare our approach to the intent-based NLU approach predominantly used in industry today. Our experiments show that developing chatbots with our system requires significantly less effort than established approaches, that these chatbots can success"},"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":"2402.12234","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T15:43:35Z","cross_cats_sorted":[],"title_canon_sha256":"9458d77a45bb375b0854651954d7df75068c66ce48ac52cc05253bef8480fa63","abstract_canon_sha256":"891cbe21c65d1e8c97cda0048200a6396eb72e63bea5eea0e27e29cc66a081f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:46:50.917984Z","signature_b64":"w13MihOai42It0Y942PmxlIboHuOkGrSP2fud595vf8UpbKY5cyLTCp0Fq67MtVHUwhbEVQsYvl0M74YtzYlDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd445cebbb5743ce8a4753d3f67ba42e89fc7acbfa1a56a689124dcaffee921f","last_reissued_at":"2026-07-05T07:46:50.917614Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:46:50.917614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Task-Oriented Dialogue with In-Context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alan Nichol, Daksh Varshneya, Thomas Werkmeister, Tom Bocklisch","submitted_at":"2024-02-19T15:43:35Z","abstract_excerpt":"We describe a system for building task-oriented dialogue systems combining the in-context learning abilities of large language models (LLMs) with the deterministic execution of business logic. LLMs are used to translate between the surface form of the conversation and a domain-specific language (DSL) which is used to progress the business logic. We compare our approach to the intent-based NLU approach predominantly used in industry today. Our experiments show that developing chatbots with our system requires significantly less effort than established approaches, that these chatbots can success"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12234","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/2402.12234/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":"2402.12234","created_at":"2026-07-05T07:46:50.917677+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.12234v1","created_at":"2026-07-05T07:46:50.917677+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12234","created_at":"2026-07-05T07:46:50.917677+00:00"},{"alias_kind":"pith_short_12","alias_value":"7VCFZ253K5B4","created_at":"2026-07-05T07:46:50.917677+00:00"},{"alias_kind":"pith_short_16","alias_value":"7VCFZ253K5B45CSH","created_at":"2026-07-05T07:46:50.917677+00:00"},{"alias_kind":"pith_short_8","alias_value":"7VCFZ253","created_at":"2026-07-05T07:46:50.917677+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22240","citing_title":"Unlocking Proactivity in Task-Oriented Dialogue","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22240","citing_title":"Unlocking Proactivity in Task-Oriented Dialogue","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19121","citing_title":"Ringdown Signatures of Dehnen Dark Matter Halos: Fluid Modes and Detectability with Space-Based Detectors","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7VCFZ253K5B45CSHKPJ7M65EF2","json":"https://pith.science/pith/7VCFZ253K5B45CSHKPJ7M65EF2.json","graph_json":"https://pith.science/api/pith-number/7VCFZ253K5B45CSHKPJ7M65EF2/graph.json","events_json":"https://pith.science/api/pith-number/7VCFZ253K5B45CSHKPJ7M65EF2/events.json","paper":"https://pith.science/paper/7VCFZ253"},"agent_actions":{"view_html":"https://pith.science/pith/7VCFZ253K5B45CSHKPJ7M65EF2","download_json":"https://pith.science/pith/7VCFZ253K5B45CSHKPJ7M65EF2.json","view_paper":"https://pith.science/paper/7VCFZ253","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.12234&json=true","fetch_graph":"https://pith.science/api/pith-number/7VCFZ253K5B45CSHKPJ7M65EF2/graph.json","fetch_events":"https://pith.science/api/pith-number/7VCFZ253K5B45CSHKPJ7M65EF2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7VCFZ253K5B45CSHKPJ7M65EF2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7VCFZ253K5B45CSHKPJ7M65EF2/action/storage_attestation","attest_author":"https://pith.science/pith/7VCFZ253K5B45CSHKPJ7M65EF2/action/author_attestation","sign_citation":"https://pith.science/pith/7VCFZ253K5B45CSHKPJ7M65EF2/action/citation_signature","submit_replication":"https://pith.science/pith/7VCFZ253K5B45CSHKPJ7M65EF2/action/replication_record"}},"created_at":"2026-07-05T07:46:50.917677+00:00","updated_at":"2026-07-05T07:46:50.917677+00:00"}