{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:XB4IEFAZWBLJSMXSYL3QI6WGGX","short_pith_number":"pith:XB4IEFAZ","schema_version":"1.0","canonical_sha256":"b878821419b0569932f2c2f7047ac635dd40b1330ea6aa4212395bff3fed27ed","source":{"kind":"arxiv","id":"2008.06239","version":2},"attestation_state":"computed","paper":{"title":"Language Models as Few-Shot Learner for Task-Oriented Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Andrea Madotto, Pascale Fung, Zhaojiang Lin, Zihan Liu","submitted_at":"2020-08-14T08:23:21Z","abstract_excerpt":"Task-oriented dialogue systems use four connected modules, namely, Natural Language Understanding (NLU), a Dialogue State Tracking (DST), Dialogue Policy (DP) and Natural Language Generation (NLG). A research challenge is to learn each module with the least amount of samples (i.e., few-shots) given the high cost related to the data collection. The most common and effective technique to solve this problem is transfer learning, where large language models, either pre-trained on text or task-specific data, are fine-tuned on the few samples. These methods require fine-tuning steps and a set of par"},"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":"2008.06239","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-14T08:23:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bc4a50050a0fb16579a6e9ca80bf40cdbb79f45bdae952275dbf3a05809eab38","abstract_canon_sha256":"b22b8dd136c93df67d6cab2f59c4b74a7055d3259f175268d4a2f4ab8c284cd0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:28:31.884646Z","signature_b64":"unzwkDG07PKtyJzhvq0vyz9J/8PO6PFfh+tSd1V7PbJE25eMUhj4AcWiVOvLX66yohuyd3bVwd6v5tx3XX8qAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b878821419b0569932f2c2f7047ac635dd40b1330ea6aa4212395bff3fed27ed","last_reissued_at":"2026-07-05T01:28:31.884168Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:28:31.884168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Models as Few-Shot Learner for Task-Oriented Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Andrea Madotto, Pascale Fung, Zhaojiang Lin, Zihan Liu","submitted_at":"2020-08-14T08:23:21Z","abstract_excerpt":"Task-oriented dialogue systems use four connected modules, namely, Natural Language Understanding (NLU), a Dialogue State Tracking (DST), Dialogue Policy (DP) and Natural Language Generation (NLG). A research challenge is to learn each module with the least amount of samples (i.e., few-shots) given the high cost related to the data collection. The most common and effective technique to solve this problem is transfer learning, where large language models, either pre-trained on text or task-specific data, are fine-tuned on the few samples. These methods require fine-tuning steps and a set of par"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.06239","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/2008.06239/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":"2008.06239","created_at":"2026-07-05T01:28:31.884225+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.06239v2","created_at":"2026-07-05T01:28:31.884225+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.06239","created_at":"2026-07-05T01:28:31.884225+00:00"},{"alias_kind":"pith_short_12","alias_value":"XB4IEFAZWBLJ","created_at":"2026-07-05T01:28:31.884225+00:00"},{"alias_kind":"pith_short_16","alias_value":"XB4IEFAZWBLJSMXS","created_at":"2026-07-05T01:28:31.884225+00:00"},{"alias_kind":"pith_short_8","alias_value":"XB4IEFAZ","created_at":"2026-07-05T01:28:31.884225+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.13768","citing_title":"From Extraction to Synthesis: Entangled Heuristics for Agent-Augmented Strategic Reasoning","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XB4IEFAZWBLJSMXSYL3QI6WGGX","json":"https://pith.science/pith/XB4IEFAZWBLJSMXSYL3QI6WGGX.json","graph_json":"https://pith.science/api/pith-number/XB4IEFAZWBLJSMXSYL3QI6WGGX/graph.json","events_json":"https://pith.science/api/pith-number/XB4IEFAZWBLJSMXSYL3QI6WGGX/events.json","paper":"https://pith.science/paper/XB4IEFAZ"},"agent_actions":{"view_html":"https://pith.science/pith/XB4IEFAZWBLJSMXSYL3QI6WGGX","download_json":"https://pith.science/pith/XB4IEFAZWBLJSMXSYL3QI6WGGX.json","view_paper":"https://pith.science/paper/XB4IEFAZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.06239&json=true","fetch_graph":"https://pith.science/api/pith-number/XB4IEFAZWBLJSMXSYL3QI6WGGX/graph.json","fetch_events":"https://pith.science/api/pith-number/XB4IEFAZWBLJSMXSYL3QI6WGGX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XB4IEFAZWBLJSMXSYL3QI6WGGX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XB4IEFAZWBLJSMXSYL3QI6WGGX/action/storage_attestation","attest_author":"https://pith.science/pith/XB4IEFAZWBLJSMXSYL3QI6WGGX/action/author_attestation","sign_citation":"https://pith.science/pith/XB4IEFAZWBLJSMXSYL3QI6WGGX/action/citation_signature","submit_replication":"https://pith.science/pith/XB4IEFAZWBLJSMXSYL3QI6WGGX/action/replication_record"}},"created_at":"2026-07-05T01:28:31.884225+00:00","updated_at":"2026-07-05T01:28:31.884225+00:00"}