{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:YPNOPOV5ZNS4PHGCPMNM4SA2J5","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":"be34720e55def66e33fa7f8df1eb62fbf340dea40ea0878d9c447e3701f42169","cross_cats_sorted":["cs.LG","stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-12-23T06:26:44Z","title_canon_sha256":"af59c634973959d5b59e8c0b2c52bdfd013b771792b3b93fb1f345d8e42fd1cf"},"schema_version":"1.0","source":{"id":"2212.12167","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.12167","created_at":"2026-07-05T05:27:52Z"},{"alias_kind":"arxiv_version","alias_value":"2212.12167v1","created_at":"2026-07-05T05:27:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.12167","created_at":"2026-07-05T05:27:52Z"},{"alias_kind":"pith_short_12","alias_value":"YPNOPOV5ZNS4","created_at":"2026-07-05T05:27:52Z"},{"alias_kind":"pith_short_16","alias_value":"YPNOPOV5ZNS4PHGC","created_at":"2026-07-05T05:27:52Z"},{"alias_kind":"pith_short_8","alias_value":"YPNOPOV5","created_at":"2026-07-05T05:27:52Z"}],"graph_snapshots":[{"event_id":"sha256:e9388c8bf7205f74d90061e56850ca6d14199dc36e66cac1cc86e3215defcc9a","target":"graph","created_at":"2026-07-05T05:27:52Z","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/2212.12167/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Motivated by the human-machine interaction such as training chatbots for improving customer satisfaction, we study human-guided human-machine interaction involving private information. We model this interaction as a two-player turn-based game, where one player (Alice, a human) guides the other player (Bob, a machine) towards a common goal. Specifically, we focus on offline reinforcement learning (RL) in this game, where the goal is to find a policy pair for Alice and Bob that maximizes their expected total rewards based on an offline dataset collected a priori. The offline setting presents two","authors_text":"Lan Wang, Zhaoran Wang, Zhengling Qi, Zhuoran Yang, Zuyue Fu","cross_cats":["cs.LG","stat.ME"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-12-23T06:26:44Z","title":"Offline Reinforcement Learning for Human-Guided Human-Machine Interaction with Private Information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.12167","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:a6d0f13c7ce8c49d25f4fd6db8463885cbe22c1cb117a6c7fee42e8d9a779156","target":"record","created_at":"2026-07-05T05:27:52Z","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":"be34720e55def66e33fa7f8df1eb62fbf340dea40ea0878d9c447e3701f42169","cross_cats_sorted":["cs.LG","stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-12-23T06:26:44Z","title_canon_sha256":"af59c634973959d5b59e8c0b2c52bdfd013b771792b3b93fb1f345d8e42fd1cf"},"schema_version":"1.0","source":{"id":"2212.12167","kind":"arxiv","version":1}},"canonical_sha256":"c3dae7babdcb65c79cc27b1ace481a4f536d7b0267dadad95db89e413c38380c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3dae7babdcb65c79cc27b1ace481a4f536d7b0267dadad95db89e413c38380c","first_computed_at":"2026-07-05T05:27:52.582966Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:27:52.582966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BSWxzxTFw+LMLv/gTasgJqAIy2MWVcWkOKSVKSvhFKas/GbsmdjkBBKEwYEE9V77iYQEdl3NswXnRCLsaycGDw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:27:52.583363Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.12167","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6d0f13c7ce8c49d25f4fd6db8463885cbe22c1cb117a6c7fee42e8d9a779156","sha256:e9388c8bf7205f74d90061e56850ca6d14199dc36e66cac1cc86e3215defcc9a"],"state_sha256":"505a5e3a69abc4c9824ef2171e87001dbd97759b7d44a9c21a0b4239660025c6"}