{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XD33UMD5BPLNIW2G4AVHAGKTU5","short_pith_number":"pith:XD33UMD5","schema_version":"1.0","canonical_sha256":"b8f7ba307d0bd6d45b46e02a701953a76a16fda1ea84112c700d50984ef5bbe0","source":{"kind":"arxiv","id":"2204.08426","version":1},"attestation_state":"computed","paper":{"title":"CHAI: A CHatbot AI for Task-Oriented Dialogue with Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Justin Fu, Mengjiao Yang, Sergey Levine, Siddharth Verma","submitted_at":"2022-04-18T17:43:21Z","abstract_excerpt":"Conventionally, generation of natural language for dialogue agents may be viewed as a statistical learning problem: determine the patterns in human-provided data and generate appropriate responses with similar statistical properties. However, dialogue can also be regarded as a goal directed process, where speakers attempt to accomplish a specific task. Reinforcement learning (RL) algorithms are designed specifically for solving such goal-directed problems, but the most direct way to apply RL -- through trial-and-error learning in human conversations, -- is costly. In this paper, we study how o"},"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":"2204.08426","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-18T17:43:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"af406eae9b6aa1687b7dcae0a5c51d273fd2c7aaffb3853b7a6f4857f727fd2c","abstract_canon_sha256":"1d213c3c86b2205df7bacd86d6634e51e9b72229fb3383bee909848d9745d2b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:15:25.993083Z","signature_b64":"STv0N8uOH/UOmAce5/kmnaNEJQZo9j53JAAH2wxaNra9gg84DDdCAneVK83hx0OSAvmcytXu4RGvt946+ziHBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8f7ba307d0bd6d45b46e02a701953a76a16fda1ea84112c700d50984ef5bbe0","last_reissued_at":"2026-07-05T04:15:25.992612Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:15:25.992612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CHAI: A CHatbot AI for Task-Oriented Dialogue with Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Justin Fu, Mengjiao Yang, Sergey Levine, Siddharth Verma","submitted_at":"2022-04-18T17:43:21Z","abstract_excerpt":"Conventionally, generation of natural language for dialogue agents may be viewed as a statistical learning problem: determine the patterns in human-provided data and generate appropriate responses with similar statistical properties. However, dialogue can also be regarded as a goal directed process, where speakers attempt to accomplish a specific task. Reinforcement learning (RL) algorithms are designed specifically for solving such goal-directed problems, but the most direct way to apply RL -- through trial-and-error learning in human conversations, -- is costly. In this paper, we study how o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.08426","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/2204.08426/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":"2204.08426","created_at":"2026-07-05T04:15:25.992668+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.08426v1","created_at":"2026-07-05T04:15:25.992668+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.08426","created_at":"2026-07-05T04:15:25.992668+00:00"},{"alias_kind":"pith_short_12","alias_value":"XD33UMD5BPLN","created_at":"2026-07-05T04:15:25.992668+00:00"},{"alias_kind":"pith_short_16","alias_value":"XD33UMD5BPLNIW2G","created_at":"2026-07-05T04:15:25.992668+00:00"},{"alias_kind":"pith_short_8","alias_value":"XD33UMD5","created_at":"2026-07-05T04:15:25.992668+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2409.12917","citing_title":"Training Language Models to Self-Correct via Reinforcement Learning","ref_index":175,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XD33UMD5BPLNIW2G4AVHAGKTU5","json":"https://pith.science/pith/XD33UMD5BPLNIW2G4AVHAGKTU5.json","graph_json":"https://pith.science/api/pith-number/XD33UMD5BPLNIW2G4AVHAGKTU5/graph.json","events_json":"https://pith.science/api/pith-number/XD33UMD5BPLNIW2G4AVHAGKTU5/events.json","paper":"https://pith.science/paper/XD33UMD5"},"agent_actions":{"view_html":"https://pith.science/pith/XD33UMD5BPLNIW2G4AVHAGKTU5","download_json":"https://pith.science/pith/XD33UMD5BPLNIW2G4AVHAGKTU5.json","view_paper":"https://pith.science/paper/XD33UMD5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.08426&json=true","fetch_graph":"https://pith.science/api/pith-number/XD33UMD5BPLNIW2G4AVHAGKTU5/graph.json","fetch_events":"https://pith.science/api/pith-number/XD33UMD5BPLNIW2G4AVHAGKTU5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XD33UMD5BPLNIW2G4AVHAGKTU5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XD33UMD5BPLNIW2G4AVHAGKTU5/action/storage_attestation","attest_author":"https://pith.science/pith/XD33UMD5BPLNIW2G4AVHAGKTU5/action/author_attestation","sign_citation":"https://pith.science/pith/XD33UMD5BPLNIW2G4AVHAGKTU5/action/citation_signature","submit_replication":"https://pith.science/pith/XD33UMD5BPLNIW2G4AVHAGKTU5/action/replication_record"}},"created_at":"2026-07-05T04:15:25.992668+00:00","updated_at":"2026-07-05T04:15:25.992668+00:00"}