{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:GRF3L43E2PLNGYZD2AZ5DMNBIC","short_pith_number":"pith:GRF3L43E","schema_version":"1.0","canonical_sha256":"344bb5f364d3d6d36323d033d1b1a1409a60aebe908837a5c09a80c0d6208783","source":{"kind":"arxiv","id":"1907.05774","version":2},"attestation_state":"computed","paper":{"title":"Hello, It's GPT-2 -- How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ivan Vuli\\'c, Pawe{\\l} Budzianowski","submitted_at":"2019-07-12T14:55:06Z","abstract_excerpt":"Data scarcity is a long-standing and crucial challenge that hinders quick development of task-oriented dialogue systems across multiple domains: task-oriented dialogue models are expected to learn grammar, syntax, dialogue reasoning, decision making, and language generation from absurdly small amounts of task-specific data. In this paper, we demonstrate that recent progress in language modeling pre-training and transfer learning shows promise to overcome this problem. We propose a task-oriented dialogue model that operates solely on text input: it effectively bypasses explicit policy and langu"},"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":"1907.05774","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-12T14:55:06Z","cross_cats_sorted":[],"title_canon_sha256":"05d023fbdf468ae13f17407d85442e9ace22a77a29c06cb46bb88c991669c552","abstract_canon_sha256":"30c96f7d267bc81e79922ea4ba42269b56e1e4eb17ffc1d054a005d240c7f7de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:51:24.085490Z","signature_b64":"XH/l1z5RDs+1jHw6IOD8Xz6QQFqU8XYSmJU5/9YBCfqkl1rLJY07D35myrsgvG/aY9GxZ9T3bCmM9aEzEjU9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"344bb5f364d3d6d36323d033d1b1a1409a60aebe908837a5c09a80c0d6208783","last_reissued_at":"2026-07-04T23:51:24.084997Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:51:24.084997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hello, It's GPT-2 -- How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ivan Vuli\\'c, Pawe{\\l} Budzianowski","submitted_at":"2019-07-12T14:55:06Z","abstract_excerpt":"Data scarcity is a long-standing and crucial challenge that hinders quick development of task-oriented dialogue systems across multiple domains: task-oriented dialogue models are expected to learn grammar, syntax, dialogue reasoning, decision making, and language generation from absurdly small amounts of task-specific data. In this paper, we demonstrate that recent progress in language modeling pre-training and transfer learning shows promise to overcome this problem. We propose a task-oriented dialogue model that operates solely on text input: it effectively bypasses explicit policy and langu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.05774","kind":"arxiv","version":2},"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/1907.05774/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":"1907.05774","created_at":"2026-07-04T23:51:24.085068+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.05774v2","created_at":"2026-07-04T23:51:24.085068+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.05774","created_at":"2026-07-04T23:51:24.085068+00:00"},{"alias_kind":"pith_short_12","alias_value":"GRF3L43E2PLN","created_at":"2026-07-04T23:51:24.085068+00:00"},{"alias_kind":"pith_short_16","alias_value":"GRF3L43E2PLNGYZD","created_at":"2026-07-04T23:51:24.085068+00:00"},{"alias_kind":"pith_short_8","alias_value":"GRF3L43E","created_at":"2026-07-04T23:51:24.085068+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.01088","citing_title":"CRONOS: Enhancing Deep Learning with Scalable GPU Accelerated Convex Neural Networks","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17900","citing_title":"DuIVRS-2: An LLM-based Interactive Voice Response System for Large-scale POI Attribute Acquisition","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01224","citing_title":"Lost in the Tower of Babel: The Adverse Effects of Incidental Multilingualism in LLMs","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GRF3L43E2PLNGYZD2AZ5DMNBIC","json":"https://pith.science/pith/GRF3L43E2PLNGYZD2AZ5DMNBIC.json","graph_json":"https://pith.science/api/pith-number/GRF3L43E2PLNGYZD2AZ5DMNBIC/graph.json","events_json":"https://pith.science/api/pith-number/GRF3L43E2PLNGYZD2AZ5DMNBIC/events.json","paper":"https://pith.science/paper/GRF3L43E"},"agent_actions":{"view_html":"https://pith.science/pith/GRF3L43E2PLNGYZD2AZ5DMNBIC","download_json":"https://pith.science/pith/GRF3L43E2PLNGYZD2AZ5DMNBIC.json","view_paper":"https://pith.science/paper/GRF3L43E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.05774&json=true","fetch_graph":"https://pith.science/api/pith-number/GRF3L43E2PLNGYZD2AZ5DMNBIC/graph.json","fetch_events":"https://pith.science/api/pith-number/GRF3L43E2PLNGYZD2AZ5DMNBIC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GRF3L43E2PLNGYZD2AZ5DMNBIC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GRF3L43E2PLNGYZD2AZ5DMNBIC/action/storage_attestation","attest_author":"https://pith.science/pith/GRF3L43E2PLNGYZD2AZ5DMNBIC/action/author_attestation","sign_citation":"https://pith.science/pith/GRF3L43E2PLNGYZD2AZ5DMNBIC/action/citation_signature","submit_replication":"https://pith.science/pith/GRF3L43E2PLNGYZD2AZ5DMNBIC/action/replication_record"}},"created_at":"2026-07-04T23:51:24.085068+00:00","updated_at":"2026-07-04T23:51:24.085068+00:00"}