{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:XD33UMD5BPLNIW2G4AVHAGKTU5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1d213c3c86b2205df7bacd86d6634e51e9b72229fb3383bee909848d9745d2b1","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-18T17:43:21Z","title_canon_sha256":"af406eae9b6aa1687b7dcae0a5c51d273fd2c7aaffb3853b7a6f4857f727fd2c"},"schema_version":"1.0","source":{"id":"2204.08426","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.08426","created_at":"2026-07-05T04:15:25Z"},{"alias_kind":"arxiv_version","alias_value":"2204.08426v1","created_at":"2026-07-05T04:15:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.08426","created_at":"2026-07-05T04:15:25Z"},{"alias_kind":"pith_short_12","alias_value":"XD33UMD5BPLN","created_at":"2026-07-05T04:15:25Z"},{"alias_kind":"pith_short_16","alias_value":"XD33UMD5BPLNIW2G","created_at":"2026-07-05T04:15:25Z"},{"alias_kind":"pith_short_8","alias_value":"XD33UMD5","created_at":"2026-07-05T04:15:25Z"}],"graph_snapshots":[{"event_id":"sha256:11f3875a5b3ea6c6c58ed51e660944ca4b558229b784fef99218b7ab931df453","target":"graph","created_at":"2026-07-05T04:15:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2204.08426/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Justin Fu, Mengjiao Yang, Sergey Levine, Siddharth Verma","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-18T17:43:21Z","title":"CHAI: A CHatbot AI for Task-Oriented Dialogue with Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.08426","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0af7c533659136da6016d558bb49a7bfe953114ca451da54e364d81a47ccc7b6","target":"record","created_at":"2026-07-05T04:15:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1d213c3c86b2205df7bacd86d6634e51e9b72229fb3383bee909848d9745d2b1","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-18T17:43:21Z","title_canon_sha256":"af406eae9b6aa1687b7dcae0a5c51d273fd2c7aaffb3853b7a6f4857f727fd2c"},"schema_version":"1.0","source":{"id":"2204.08426","kind":"arxiv","version":1}},"canonical_sha256":"b8f7ba307d0bd6d45b46e02a701953a76a16fda1ea84112c700d50984ef5bbe0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b8f7ba307d0bd6d45b46e02a701953a76a16fda1ea84112c700d50984ef5bbe0","first_computed_at":"2026-07-05T04:15:25.992612Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:15:25.992612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"STv0N8uOH/UOmAce5/kmnaNEJQZo9j53JAAH2wxaNra9gg84DDdCAneVK83hx0OSAvmcytXu4RGvt946+ziHBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:15:25.993083Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.08426","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0af7c533659136da6016d558bb49a7bfe953114ca451da54e364d81a47ccc7b6","sha256:11f3875a5b3ea6c6c58ed51e660944ca4b558229b784fef99218b7ab931df453"],"state_sha256":"7ad16e895f51b69c421bf2fe17b64497889d43a2ba5eda6ac9a9e8fcfd14b9f6"}