{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:NNEOJLWR6S4ZIAUQCJEBJW54AJ","short_pith_number":"pith:NNEOJLWR","schema_version":"1.0","canonical_sha256":"6b48e4aed1f4b9940290124814dbbc0268d1c1217e6c7cfbe7eb6e676545d378","source":{"kind":"arxiv","id":"2012.15504","version":1},"attestation_state":"computed","paper":{"title":"Continual Learning in Task-Oriented Dialogue Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrea Madotto, Bing Liu, Eunjoon Cho, Paul Crook, Seungwhan Moon, Zhaojiang Lin, Zhenpeng Zhou, Zhiguang Wang, Zhou Yu","submitted_at":"2020-12-31T08:44:25Z","abstract_excerpt":"Continual learning in task-oriented dialogue systems can allow us to add new domains and functionalities through time without incurring the high cost of a whole system retraining. In this paper, we propose a continual learning benchmark for task-oriented dialogue systems with 37 domains to be learned continuously in four settings, such as intent recognition, state tracking, natural language generation, and end-to-end. Moreover, we implement and compare multiple existing continual learning baselines, and we propose a simple yet effective architectural method based on residual adapters. Our expe"},"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":"2012.15504","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-31T08:44:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c80f7826171a98caf570aadbb119339293e2e9288d9cdcf88a425dafb4761950","abstract_canon_sha256":"054d01d71deff6bb53ae4e646b4a28a83c29d138ef3c81de62955ae706967328"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:03:19.161184Z","signature_b64":"SKiEBWFmIe5dyx1HqKBfJYJsg9ZAWvpENLk7RaWGCU/w/bjvUdvFYjq8wQFONLWaRfzL6EXRZ9KEdwgD/ClJAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b48e4aed1f4b9940290124814dbbc0268d1c1217e6c7cfbe7eb6e676545d378","last_reissued_at":"2026-07-05T02:03:19.160794Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:03:19.160794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continual Learning in Task-Oriented Dialogue Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrea Madotto, Bing Liu, Eunjoon Cho, Paul Crook, Seungwhan Moon, Zhaojiang Lin, Zhenpeng Zhou, Zhiguang Wang, Zhou Yu","submitted_at":"2020-12-31T08:44:25Z","abstract_excerpt":"Continual learning in task-oriented dialogue systems can allow us to add new domains and functionalities through time without incurring the high cost of a whole system retraining. In this paper, we propose a continual learning benchmark for task-oriented dialogue systems with 37 domains to be learned continuously in four settings, such as intent recognition, state tracking, natural language generation, and end-to-end. Moreover, we implement and compare multiple existing continual learning baselines, and we propose a simple yet effective architectural method based on residual adapters. Our expe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.15504","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/2012.15504/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":"2012.15504","created_at":"2026-07-05T02:03:19.160852+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.15504v1","created_at":"2026-07-05T02:03:19.160852+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.15504","created_at":"2026-07-05T02:03:19.160852+00:00"},{"alias_kind":"pith_short_12","alias_value":"NNEOJLWR6S4Z","created_at":"2026-07-05T02:03:19.160852+00:00"},{"alias_kind":"pith_short_16","alias_value":"NNEOJLWR6S4ZIAUQ","created_at":"2026-07-05T02:03:19.160852+00:00"},{"alias_kind":"pith_short_8","alias_value":"NNEOJLWR","created_at":"2026-07-05T02:03:19.160852+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2403.14608","citing_title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","ref_index":171,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NNEOJLWR6S4ZIAUQCJEBJW54AJ","json":"https://pith.science/pith/NNEOJLWR6S4ZIAUQCJEBJW54AJ.json","graph_json":"https://pith.science/api/pith-number/NNEOJLWR6S4ZIAUQCJEBJW54AJ/graph.json","events_json":"https://pith.science/api/pith-number/NNEOJLWR6S4ZIAUQCJEBJW54AJ/events.json","paper":"https://pith.science/paper/NNEOJLWR"},"agent_actions":{"view_html":"https://pith.science/pith/NNEOJLWR6S4ZIAUQCJEBJW54AJ","download_json":"https://pith.science/pith/NNEOJLWR6S4ZIAUQCJEBJW54AJ.json","view_paper":"https://pith.science/paper/NNEOJLWR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.15504&json=true","fetch_graph":"https://pith.science/api/pith-number/NNEOJLWR6S4ZIAUQCJEBJW54AJ/graph.json","fetch_events":"https://pith.science/api/pith-number/NNEOJLWR6S4ZIAUQCJEBJW54AJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NNEOJLWR6S4ZIAUQCJEBJW54AJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NNEOJLWR6S4ZIAUQCJEBJW54AJ/action/storage_attestation","attest_author":"https://pith.science/pith/NNEOJLWR6S4ZIAUQCJEBJW54AJ/action/author_attestation","sign_citation":"https://pith.science/pith/NNEOJLWR6S4ZIAUQCJEBJW54AJ/action/citation_signature","submit_replication":"https://pith.science/pith/NNEOJLWR6S4ZIAUQCJEBJW54AJ/action/replication_record"}},"created_at":"2026-07-05T02:03:19.160852+00:00","updated_at":"2026-07-05T02:03:19.160852+00:00"}