{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:JW67U2SAZQLZJ3IMQDZL7AP2TO","short_pith_number":"pith:JW67U2SA","canonical_record":{"source":{"id":"2209.08429","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-17T23:44:13Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"b747c4dd65589c355c34ea0d49aca9d3337a875fd41bf3ebd68d5805c0107168","abstract_canon_sha256":"eccbb1a8fe15f92185f88e6fb12dffc8339cb2062165d4a43fc52bdaa37308fb"},"schema_version":"1.0"},"canonical_sha256":"4dbdfa6a40cc1794ed0c80f2bf81fa9ba49f5fbed95d0e0eccd39680538f4fe7","source":{"kind":"arxiv","id":"2209.08429","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.08429","created_at":"2026-07-05T06:09:44Z"},{"alias_kind":"arxiv_version","alias_value":"2209.08429v1","created_at":"2026-07-05T06:09:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.08429","created_at":"2026-07-05T06:09:44Z"},{"alias_kind":"pith_short_12","alias_value":"JW67U2SAZQLZ","created_at":"2026-07-05T06:09:44Z"},{"alias_kind":"pith_short_16","alias_value":"JW67U2SAZQLZJ3IM","created_at":"2026-07-05T06:09:44Z"},{"alias_kind":"pith_short_8","alias_value":"JW67U2SA","created_at":"2026-07-05T06:09:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:JW67U2SAZQLZJ3IMQDZL7AP2TO","target":"record","payload":{"canonical_record":{"source":{"id":"2209.08429","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-17T23:44:13Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"b747c4dd65589c355c34ea0d49aca9d3337a875fd41bf3ebd68d5805c0107168","abstract_canon_sha256":"eccbb1a8fe15f92185f88e6fb12dffc8339cb2062165d4a43fc52bdaa37308fb"},"schema_version":"1.0"},"canonical_sha256":"4dbdfa6a40cc1794ed0c80f2bf81fa9ba49f5fbed95d0e0eccd39680538f4fe7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:09:44.947895Z","signature_b64":"bt7BbgYogZ5kKsJW7r8OvYkOCCKRt0SsbIF0fu8kUtmzqjKv7ptHjBhdVUiTpIca1p46OrBHChCh14jEAo2JBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4dbdfa6a40cc1794ed0c80f2bf81fa9ba49f5fbed95d0e0eccd39680538f4fe7","last_reissued_at":"2026-07-05T06:09:44.947431Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:09:44.947431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.08429","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":"2026-07-05T06:09:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wVff8RrfeY3PuZ97Pd9DWNucooDqQ0tdEeJndPpkRtmf4TpTXaAxWR6XhobiPhUBNbit6LC/Ex2isAD4tYBuBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T07:54:50.009889Z"},"content_sha256":"221a83d6cde9c38f5a245b1cd27e66fc1cdb321f1cab36b3b32958b37534217f","schema_version":"1.0","event_id":"sha256:221a83d6cde9c38f5a245b1cd27e66fc1cdb321f1cab36b3b32958b37534217f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:JW67U2SAZQLZJ3IMQDZL7AP2TO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Constrained Policy Optimization for Controlled Self-Learning in Conversational AI Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Mohammad Kachuee, Sungjin Lee","submitted_at":"2022-09-17T23:44:13Z","abstract_excerpt":"Recently, self-learning methods based on user satisfaction metrics and contextual bandits have shown promising results to enable consistent improvements in conversational AI systems. However, directly targeting such metrics by off-policy bandit learning objectives often increases the risk of making abrupt policy changes that break the current user experience. In this study, we introduce a scalable framework for supporting fine-grained exploration targets for individual domains via user-defined constraints. For example, we may want to ensure fewer policy deviations in business-critical domains "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.08429","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/2209.08429/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":"2026-07-05T06:09:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hVm37kkKwm+/o/vvOIWYp771j3PSEW3BUEMTSEmK3B7uTi1oiy8bH32id2R/x/ASjAmeYkhMaZbdWLuLmHmnBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T07:54:50.010840Z"},"content_sha256":"76ddc9ba46d9980893d95c8b96bd3ed5660f34aee3429aa0018a4244076711fa","schema_version":"1.0","event_id":"sha256:76ddc9ba46d9980893d95c8b96bd3ed5660f34aee3429aa0018a4244076711fa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JW67U2SAZQLZJ3IMQDZL7AP2TO/bundle.json","state_url":"https://pith.science/pith/JW67U2SAZQLZJ3IMQDZL7AP2TO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JW67U2SAZQLZJ3IMQDZL7AP2TO/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":"2026-08-13T07:54:50Z","links":{"resolver":"https://pith.science/pith/JW67U2SAZQLZJ3IMQDZL7AP2TO","bundle":"https://pith.science/pith/JW67U2SAZQLZJ3IMQDZL7AP2TO/bundle.json","state":"https://pith.science/pith/JW67U2SAZQLZJ3IMQDZL7AP2TO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JW67U2SAZQLZJ3IMQDZL7AP2TO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:JW67U2SAZQLZJ3IMQDZL7AP2TO","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":"eccbb1a8fe15f92185f88e6fb12dffc8339cb2062165d4a43fc52bdaa37308fb","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-17T23:44:13Z","title_canon_sha256":"b747c4dd65589c355c34ea0d49aca9d3337a875fd41bf3ebd68d5805c0107168"},"schema_version":"1.0","source":{"id":"2209.08429","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.08429","created_at":"2026-07-05T06:09:44Z"},{"alias_kind":"arxiv_version","alias_value":"2209.08429v1","created_at":"2026-07-05T06:09:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.08429","created_at":"2026-07-05T06:09:44Z"},{"alias_kind":"pith_short_12","alias_value":"JW67U2SAZQLZ","created_at":"2026-07-05T06:09:44Z"},{"alias_kind":"pith_short_16","alias_value":"JW67U2SAZQLZJ3IM","created_at":"2026-07-05T06:09:44Z"},{"alias_kind":"pith_short_8","alias_value":"JW67U2SA","created_at":"2026-07-05T06:09:44Z"}],"graph_snapshots":[{"event_id":"sha256:76ddc9ba46d9980893d95c8b96bd3ed5660f34aee3429aa0018a4244076711fa","target":"graph","created_at":"2026-07-05T06:09:44Z","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/2209.08429/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, self-learning methods based on user satisfaction metrics and contextual bandits have shown promising results to enable consistent improvements in conversational AI systems. However, directly targeting such metrics by off-policy bandit learning objectives often increases the risk of making abrupt policy changes that break the current user experience. In this study, we introduce a scalable framework for supporting fine-grained exploration targets for individual domains via user-defined constraints. For example, we may want to ensure fewer policy deviations in business-critical domains ","authors_text":"Mohammad Kachuee, Sungjin Lee","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-17T23:44:13Z","title":"Constrained Policy Optimization for Controlled Self-Learning in Conversational AI Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.08429","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":"sha256:221a83d6cde9c38f5a245b1cd27e66fc1cdb321f1cab36b3b32958b37534217f","target":"record","created_at":"2026-07-05T06:09:44Z","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":"eccbb1a8fe15f92185f88e6fb12dffc8339cb2062165d4a43fc52bdaa37308fb","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-17T23:44:13Z","title_canon_sha256":"b747c4dd65589c355c34ea0d49aca9d3337a875fd41bf3ebd68d5805c0107168"},"schema_version":"1.0","source":{"id":"2209.08429","kind":"arxiv","version":1}},"canonical_sha256":"4dbdfa6a40cc1794ed0c80f2bf81fa9ba49f5fbed95d0e0eccd39680538f4fe7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4dbdfa6a40cc1794ed0c80f2bf81fa9ba49f5fbed95d0e0eccd39680538f4fe7","first_computed_at":"2026-07-05T06:09:44.947431Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:09:44.947431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bt7BbgYogZ5kKsJW7r8OvYkOCCKRt0SsbIF0fu8kUtmzqjKv7ptHjBhdVUiTpIca1p46OrBHChCh14jEAo2JBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:09:44.947895Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.08429","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:221a83d6cde9c38f5a245b1cd27e66fc1cdb321f1cab36b3b32958b37534217f","sha256:76ddc9ba46d9980893d95c8b96bd3ed5660f34aee3429aa0018a4244076711fa"],"state_sha256":"2183cc1a2b99351d1d13dbc4dc462b58f9f08df347ff45cd47c999a8472293e8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZTK7rEEH9sd28OEz/jFrvD4vnPwRrwcoWE/0pdVo/1DRZlMNmuX9P+oIMB5O/LJ0231R1Q1FdU1K0bqkgHHrCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T07:54:50.016728Z","bundle_sha256":"1214a48a4ad484bd0bb85aa6972b7e21ecf13f04d8926bf5ea04357b533e3b47"}}