{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:TR7TAOFS7XLATXNNHZ65R5BE2P","short_pith_number":"pith:TR7TAOFS","canonical_record":{"source":{"id":"2209.15448","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-29T16:03:07Z","cross_cats_sorted":["math.ST","stat.ME","stat.TH"],"title_canon_sha256":"5cf94f626c06484fcae286e5f5980366284733f0b792961ffeea6fd170d651f7","abstract_canon_sha256":"8197e758b406debe6a931cc1bbfb2f1afe4205a575f51365736907366d91265d"},"schema_version":"1.0"},"canonical_sha256":"9c7f3038b2fdd609ddad3e7dd8f424d3f6f79831f1f0a083f58847facfd2d2a1","source":{"kind":"arxiv","id":"2209.15448","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.15448","created_at":"2026-06-04T01:08:24Z"},{"alias_kind":"arxiv_version","alias_value":"2209.15448v3","created_at":"2026-06-04T01:08:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.15448","created_at":"2026-06-04T01:08:24Z"},{"alias_kind":"pith_short_12","alias_value":"TR7TAOFS7XLA","created_at":"2026-06-04T01:08:24Z"},{"alias_kind":"pith_short_16","alias_value":"TR7TAOFS7XLATXNN","created_at":"2026-06-04T01:08:24Z"},{"alias_kind":"pith_short_8","alias_value":"TR7TAOFS","created_at":"2026-06-04T01:08:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:TR7TAOFS7XLATXNNHZ65R5BE2P","target":"record","payload":{"canonical_record":{"source":{"id":"2209.15448","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-29T16:03:07Z","cross_cats_sorted":["math.ST","stat.ME","stat.TH"],"title_canon_sha256":"5cf94f626c06484fcae286e5f5980366284733f0b792961ffeea6fd170d651f7","abstract_canon_sha256":"8197e758b406debe6a931cc1bbfb2f1afe4205a575f51365736907366d91265d"},"schema_version":"1.0"},"canonical_sha256":"9c7f3038b2fdd609ddad3e7dd8f424d3f6f79831f1f0a083f58847facfd2d2a1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:24.138248Z","signature_b64":"FqDgR4IRylzY0D71ZseLlRDuv9e+IinQgjbOq5vYog3AyPc4CNx/g9hC2mYHUGhSTF0dsB3wUW9oupRwDOh/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c7f3038b2fdd609ddad3e7dd8f424d3f6f79831f1f0a083f58847facfd2d2a1","last_reissued_at":"2026-06-04T01:08:24.137658Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:24.137658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.15448","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-04T01:08:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QopxI2qZcS/pt7ExJwnArN179PT/Gzcck2qPtnFBv67/mNbGla8XlfvHrA01iEXte2cwU35R7veEoEjyumttBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:22:40.022728Z"},"content_sha256":"307fa799549782f4a480d78bb2fe9fe02ef76e8805a1e8ee7a67b6c98d4dd861","schema_version":"1.0","event_id":"sha256:307fa799549782f4a480d78bb2fe9fe02ef76e8805a1e8ee7a67b6c98d4dd861"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:TR7TAOFS7XLATXNNHZ65R5BE2P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Blessing from Human-AI Interaction: Super Reinforcement Learning in Confounded Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.ME","stat.TH"],"primary_cat":"cs.LG","authors_text":"Chengchun Shi, Jiayi Wang, Zhengling Qi","submitted_at":"2022-09-29T16:03:07Z","abstract_excerpt":"As AI becomes more prevalent throughout society, effective methods of integrating humans and AI systems that leverage their respective strengths and mitigate risk have become an important priority. In this paper, we introduce the paradigm of super policy learning that takes advantage of Human-AI interaction for data driven sequential decision making. This approach utilizes the observed action, either from AI or humans, as input for achieving a stronger oracle in policy learning for the decision maker (humans or AI). In the decision process with unmeasured confounding, the actions taken by past"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.15448","kind":"arxiv","version":3},"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/2209.15448/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":"2026-06-04T01:08:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"go/vRr+LOBIffNx01g4N0NtvpsUUKCcPc4QgP4+2LbuZD8exM/IhaJesIOfVmmgOvWBRmw4RgkKEuXJ+vjYPBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:22:40.024199Z"},"content_sha256":"232813ed48ac07cdc4313bb11d25203a61c8fdab34515488fb8ae393a6d88dbb","schema_version":"1.0","event_id":"sha256:232813ed48ac07cdc4313bb11d25203a61c8fdab34515488fb8ae393a6d88dbb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TR7TAOFS7XLATXNNHZ65R5BE2P/bundle.json","state_url":"https://pith.science/pith/TR7TAOFS7XLATXNNHZ65R5BE2P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TR7TAOFS7XLATXNNHZ65R5BE2P/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":"2026-08-08T10:22:40Z","links":{"resolver":"https://pith.science/pith/TR7TAOFS7XLATXNNHZ65R5BE2P","bundle":"https://pith.science/pith/TR7TAOFS7XLATXNNHZ65R5BE2P/bundle.json","state":"https://pith.science/pith/TR7TAOFS7XLATXNNHZ65R5BE2P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TR7TAOFS7XLATXNNHZ65R5BE2P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TR7TAOFS7XLATXNNHZ65R5BE2P","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":"8197e758b406debe6a931cc1bbfb2f1afe4205a575f51365736907366d91265d","cross_cats_sorted":["math.ST","stat.ME","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-29T16:03:07Z","title_canon_sha256":"5cf94f626c06484fcae286e5f5980366284733f0b792961ffeea6fd170d651f7"},"schema_version":"1.0","source":{"id":"2209.15448","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.15448","created_at":"2026-06-04T01:08:24Z"},{"alias_kind":"arxiv_version","alias_value":"2209.15448v3","created_at":"2026-06-04T01:08:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.15448","created_at":"2026-06-04T01:08:24Z"},{"alias_kind":"pith_short_12","alias_value":"TR7TAOFS7XLA","created_at":"2026-06-04T01:08:24Z"},{"alias_kind":"pith_short_16","alias_value":"TR7TAOFS7XLATXNN","created_at":"2026-06-04T01:08:24Z"},{"alias_kind":"pith_short_8","alias_value":"TR7TAOFS","created_at":"2026-06-04T01:08:24Z"}],"graph_snapshots":[{"event_id":"sha256:232813ed48ac07cdc4313bb11d25203a61c8fdab34515488fb8ae393a6d88dbb","target":"graph","created_at":"2026-06-04T01:08:24Z","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/2209.15448/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As AI becomes more prevalent throughout society, effective methods of integrating humans and AI systems that leverage their respective strengths and mitigate risk have become an important priority. In this paper, we introduce the paradigm of super policy learning that takes advantage of Human-AI interaction for data driven sequential decision making. This approach utilizes the observed action, either from AI or humans, as input for achieving a stronger oracle in policy learning for the decision maker (humans or AI). In the decision process with unmeasured confounding, the actions taken by past","authors_text":"Chengchun Shi, Jiayi Wang, Zhengling Qi","cross_cats":["math.ST","stat.ME","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-29T16:03:07Z","title":"Blessing from Human-AI Interaction: Super Reinforcement Learning in Confounded Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.15448","kind":"arxiv","version":3},"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":"sha256:307fa799549782f4a480d78bb2fe9fe02ef76e8805a1e8ee7a67b6c98d4dd861","target":"record","created_at":"2026-06-04T01:08:24Z","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":"8197e758b406debe6a931cc1bbfb2f1afe4205a575f51365736907366d91265d","cross_cats_sorted":["math.ST","stat.ME","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-29T16:03:07Z","title_canon_sha256":"5cf94f626c06484fcae286e5f5980366284733f0b792961ffeea6fd170d651f7"},"schema_version":"1.0","source":{"id":"2209.15448","kind":"arxiv","version":3}},"canonical_sha256":"9c7f3038b2fdd609ddad3e7dd8f424d3f6f79831f1f0a083f58847facfd2d2a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c7f3038b2fdd609ddad3e7dd8f424d3f6f79831f1f0a083f58847facfd2d2a1","first_computed_at":"2026-06-04T01:08:24.137658Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:08:24.137658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FqDgR4IRylzY0D71ZseLlRDuv9e+IinQgjbOq5vYog3AyPc4CNx/g9hC2mYHUGhSTF0dsB3wUW9oupRwDOh/BQ==","signature_status":"signed_v1","signed_at":"2026-06-04T01:08:24.138248Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.15448","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:307fa799549782f4a480d78bb2fe9fe02ef76e8805a1e8ee7a67b6c98d4dd861","sha256:232813ed48ac07cdc4313bb11d25203a61c8fdab34515488fb8ae393a6d88dbb"],"state_sha256":"ce87b726ef1a8c6b8744a59052e95d58373dc28b44a192568a54e5c10edf2805"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ePLAmJDGXND4KBFP8TCkbhQMXstLm5nl/tsaSxQ5mRJ1nLhwghjVu2Q92PfBsDWsvigHpRQQ1LJh0ruYjxOTAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T10:22:40.040053Z","bundle_sha256":"e82e15bb19d38793ec4f5b85d7a115df7c9e56894d2949c99dba5296b1e95d79"}}