{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:T65JIFD322ZMJZGFMB3KCLQBR2","short_pith_number":"pith:T65JIFD3","schema_version":"1.0","canonical_sha256":"9fba94147bd6b2c4e4c56076a12e018eb89e39bbd8ceb77d3c57d1c588de60a6","source":{"kind":"arxiv","id":"2009.12005","version":2},"attestation_state":"computed","paper":{"title":"MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrea Madotto, Genta Indra Winata, Pascale Fung, Zhaojiang Lin","submitted_at":"2020-09-25T02:19:13Z","abstract_excerpt":"In this paper, we propose Minimalist Transfer Learning (MinTL) to simplify the system design process of task-oriented dialogue systems and alleviate the over-dependency on annotated data. MinTL is a simple yet effective transfer learning framework, which allows us to plug-and-play pre-trained seq2seq models, and jointly learn dialogue state tracking and dialogue response generation. Unlike previous approaches, which use a copy mechanism to \"carryover\" the old dialogue states to the new one, we introduce Levenshtein belief spans (Lev), that allows efficient dialogue state tracking with a minima"},"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":"2009.12005","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-25T02:19:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d76b34ee7d8ed9541aedf7eac6dece9c13cfe4cabf0711235eb38fa6ca092dcd","abstract_canon_sha256":"25afe97b3d399446eb4c39fda2bb77e736117c7cfebd750089fb9a1be1860494"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:38:21.628115Z","signature_b64":"ousg+N5HIELcXXzXFSXOc7M/OlDNh2xXexpb/I59rRqwhkuchOYsD45g/WvPxqYVsvbrhg4i4bScaPhi+W9ECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fba94147bd6b2c4e4c56076a12e018eb89e39bbd8ceb77d3c57d1c588de60a6","last_reissued_at":"2026-07-05T01:38:21.627697Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:38:21.627697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrea Madotto, Genta Indra Winata, Pascale Fung, Zhaojiang Lin","submitted_at":"2020-09-25T02:19:13Z","abstract_excerpt":"In this paper, we propose Minimalist Transfer Learning (MinTL) to simplify the system design process of task-oriented dialogue systems and alleviate the over-dependency on annotated data. MinTL is a simple yet effective transfer learning framework, which allows us to plug-and-play pre-trained seq2seq models, and jointly learn dialogue state tracking and dialogue response generation. Unlike previous approaches, which use a copy mechanism to \"carryover\" the old dialogue states to the new one, we introduce Levenshtein belief spans (Lev), that allows efficient dialogue state tracking with a minima"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.12005","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/2009.12005/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":"2009.12005","created_at":"2026-07-05T01:38:21.627755+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.12005v2","created_at":"2026-07-05T01:38:21.627755+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.12005","created_at":"2026-07-05T01:38:21.627755+00:00"},{"alias_kind":"pith_short_12","alias_value":"T65JIFD322ZM","created_at":"2026-07-05T01:38:21.627755+00:00"},{"alias_kind":"pith_short_16","alias_value":"T65JIFD322ZMJZGF","created_at":"2026-07-05T01:38:21.627755+00:00"},{"alias_kind":"pith_short_8","alias_value":"T65JIFD3","created_at":"2026-07-05T01:38:21.627755+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.17390","citing_title":"PicPersona-TOD : A Dataset for Personalizing Utterance Style in Task-Oriented Dialogue with Image Persona","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T65JIFD322ZMJZGFMB3KCLQBR2","json":"https://pith.science/pith/T65JIFD322ZMJZGFMB3KCLQBR2.json","graph_json":"https://pith.science/api/pith-number/T65JIFD322ZMJZGFMB3KCLQBR2/graph.json","events_json":"https://pith.science/api/pith-number/T65JIFD322ZMJZGFMB3KCLQBR2/events.json","paper":"https://pith.science/paper/T65JIFD3"},"agent_actions":{"view_html":"https://pith.science/pith/T65JIFD322ZMJZGFMB3KCLQBR2","download_json":"https://pith.science/pith/T65JIFD322ZMJZGFMB3KCLQBR2.json","view_paper":"https://pith.science/paper/T65JIFD3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.12005&json=true","fetch_graph":"https://pith.science/api/pith-number/T65JIFD322ZMJZGFMB3KCLQBR2/graph.json","fetch_events":"https://pith.science/api/pith-number/T65JIFD322ZMJZGFMB3KCLQBR2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T65JIFD322ZMJZGFMB3KCLQBR2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T65JIFD322ZMJZGFMB3KCLQBR2/action/storage_attestation","attest_author":"https://pith.science/pith/T65JIFD322ZMJZGFMB3KCLQBR2/action/author_attestation","sign_citation":"https://pith.science/pith/T65JIFD322ZMJZGFMB3KCLQBR2/action/citation_signature","submit_replication":"https://pith.science/pith/T65JIFD322ZMJZGFMB3KCLQBR2/action/replication_record"}},"created_at":"2026-07-05T01:38:21.627755+00:00","updated_at":"2026-07-05T01:38:21.627755+00:00"}