{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:XD33UMD5BPLNIW2G4AVHAGKTU5","short_pith_number":"pith:XD33UMD5","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"},"canonical_sha256":"b8f7ba307d0bd6d45b46e02a701953a76a16fda1ea84112c700d50984ef5bbe0","source":{"kind":"arxiv","id":"2204.08426","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:XD33UMD5BPLNIW2G4AVHAGKTU5","target":"record","payload":{"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"},"canonical_sha256":"b8f7ba307d0bd6d45b46e02a701953a76a16fda1ea84112c700d50984ef5bbe0","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"},"source_kind":"arxiv","source_id":"2204.08426","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:15:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"olA1WOjc9egySuol1zf96ydUd5RosIHw6eunBGvcfsWZXrsT2XJTM4+PzvONUixNj2Tn/ZG9tJhpz7cHOFqjAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:06:58.640393Z"},"content_sha256":"0af7c533659136da6016d558bb49a7bfe953114ca451da54e364d81a47ccc7b6","schema_version":"1.0","event_id":"sha256:0af7c533659136da6016d558bb49a7bfe953114ca451da54e364d81a47ccc7b6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:XD33UMD5BPLNIW2G4AVHAGKTU5","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:15:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BaY9cjXk9hjukDS8jj6xKhFORLwNAGgrs55gltwnD4U4BK/EtR//ZC5v3UtWWHuiQAah/uqHvClXbl7n3AOuAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:06:58.640797Z"},"content_sha256":"11f3875a5b3ea6c6c58ed51e660944ca4b558229b784fef99218b7ab931df453","schema_version":"1.0","event_id":"sha256:11f3875a5b3ea6c6c58ed51e660944ca4b558229b784fef99218b7ab931df453"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XD33UMD5BPLNIW2G4AVHAGKTU5/bundle.json","state_url":"https://pith.science/pith/XD33UMD5BPLNIW2G4AVHAGKTU5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XD33UMD5BPLNIW2G4AVHAGKTU5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T09:06:58Z","links":{"resolver":"https://pith.science/pith/XD33UMD5BPLNIW2G4AVHAGKTU5","bundle":"https://pith.science/pith/XD33UMD5BPLNIW2G4AVHAGKTU5/bundle.json","state":"https://pith.science/pith/XD33UMD5BPLNIW2G4AVHAGKTU5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XD33UMD5BPLNIW2G4AVHAGKTU5/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SFvEmQr0bz2AnUsllWsRYwmwdJwbC+iRxips40PeqAmsCNs7CDGSy9+GCRvI4nqUEufssq8xxNHN1lbAcOemAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T09:06:58.644665Z","bundle_sha256":"c54b05c0110f68a048aa90e3486721122e9ba138c4b5693ebf56747652eb2528"}}