{"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"}