{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:KKV4A5JHBF7HUGF7OVJFKPP2E2","short_pith_number":"pith:KKV4A5JH","canonical_record":{"source":{"id":"2102.09907","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-02-19T13:01:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c1832bf1372c23921f2797dafdf7dac559ea558df40a7cc3a8508bd3637cf139","abstract_canon_sha256":"ba7ffc5c6f6bd08825831ce2c7d41641a3da2924af8a7b0fd5d9abed689116be"},"schema_version":"1.0"},"canonical_sha256":"52abc07527097e7a18bf7552553dfa26b64bb86a3876831ec067778921ab17a8","source":{"kind":"arxiv","id":"2102.09907","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.09907","created_at":"2026-07-05T09:20:21Z"},{"alias_kind":"arxiv_version","alias_value":"2102.09907v3","created_at":"2026-07-05T09:20:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.09907","created_at":"2026-07-05T09:20:21Z"},{"alias_kind":"pith_short_12","alias_value":"KKV4A5JHBF7H","created_at":"2026-07-05T09:20:21Z"},{"alias_kind":"pith_short_16","alias_value":"KKV4A5JHBF7HUGF7","created_at":"2026-07-05T09:20:21Z"},{"alias_kind":"pith_short_8","alias_value":"KKV4A5JH","created_at":"2026-07-05T09:20:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:KKV4A5JHBF7HUGF7OVJFKPP2E2","target":"record","payload":{"canonical_record":{"source":{"id":"2102.09907","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-02-19T13:01:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c1832bf1372c23921f2797dafdf7dac559ea558df40a7cc3a8508bd3637cf139","abstract_canon_sha256":"ba7ffc5c6f6bd08825831ce2c7d41641a3da2924af8a7b0fd5d9abed689116be"},"schema_version":"1.0"},"canonical_sha256":"52abc07527097e7a18bf7552553dfa26b64bb86a3876831ec067778921ab17a8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:21.285426Z","signature_b64":"X2hzcjrNb8uYrLLYKI/29SFBzVYR2OcBZU2AwdLaWPBugt2LjqINTeoVrPGm88YpNLvC6WnmbtoMzvzNBCnZBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52abc07527097e7a18bf7552553dfa26b64bb86a3876831ec067778921ab17a8","last_reissued_at":"2026-07-05T09:20:21.284914Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:21.284914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.09907","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":"2026-07-05T09:20:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aUPWhx6G3gmdHv8REBrm4S1jvwEDmzTJ7uRix3VVWRd2LdPXk8xiE+x6F96kO8Iu64pTpVwFAeZtTUGQEnf9AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:11:56.253682Z"},"content_sha256":"c2ecaf9e1c6f1c4becd1474c85c7a3743d232e443efaac6099d715080f0dea3a","schema_version":"1.0","event_id":"sha256:c2ecaf9e1c6f1c4becd1474c85c7a3743d232e443efaac6099d715080f0dea3a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:KKV4A5JHBF7HUGF7OVJFKPP2E2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Instrumental Variable Value Iteration for Causal Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Luofeng Liao, Mladen Kolar, Yixin Wang, Zhaoran Wang, Zhuoran Yang, Zuyue Fu","submitted_at":"2021-02-19T13:01:40Z","abstract_excerpt":"In offline reinforcement learning (RL) an optimal policy is learned solely from a priori collected observational data. However, in observational data, actions are often confounded by unobserved variables. Instrumental variables (IVs), in the context of RL, are the variables whose influence on the state variables is all mediated by the action. When a valid instrument is present, we can recover the confounded transition dynamics through observational data. We study a confounded Markov decision process where the transition dynamics admit an additive nonlinear functional form. Using IVs, we derive"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.09907","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/2102.09907/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":"2026-07-05T09:20:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sowT+yI0syjhvui9+0XR4yZJ3lLeBCj3KpEs0HhFyfX+GolCFGW7/+HICrRmxD/fGpziw/W2Q/Zi7H/jzH4NAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:11:56.254193Z"},"content_sha256":"244b34a0ceb057232a475200106825ba56385fe2165abb297c8dfe61e5a0277c","schema_version":"1.0","event_id":"sha256:244b34a0ceb057232a475200106825ba56385fe2165abb297c8dfe61e5a0277c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KKV4A5JHBF7HUGF7OVJFKPP2E2/bundle.json","state_url":"https://pith.science/pith/KKV4A5JHBF7HUGF7OVJFKPP2E2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KKV4A5JHBF7HUGF7OVJFKPP2E2/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":"2026-08-09T13:11:56Z","links":{"resolver":"https://pith.science/pith/KKV4A5JHBF7HUGF7OVJFKPP2E2","bundle":"https://pith.science/pith/KKV4A5JHBF7HUGF7OVJFKPP2E2/bundle.json","state":"https://pith.science/pith/KKV4A5JHBF7HUGF7OVJFKPP2E2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KKV4A5JHBF7HUGF7OVJFKPP2E2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:KKV4A5JHBF7HUGF7OVJFKPP2E2","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":"ba7ffc5c6f6bd08825831ce2c7d41641a3da2924af8a7b0fd5d9abed689116be","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-02-19T13:01:40Z","title_canon_sha256":"c1832bf1372c23921f2797dafdf7dac559ea558df40a7cc3a8508bd3637cf139"},"schema_version":"1.0","source":{"id":"2102.09907","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.09907","created_at":"2026-07-05T09:20:21Z"},{"alias_kind":"arxiv_version","alias_value":"2102.09907v3","created_at":"2026-07-05T09:20:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.09907","created_at":"2026-07-05T09:20:21Z"},{"alias_kind":"pith_short_12","alias_value":"KKV4A5JHBF7H","created_at":"2026-07-05T09:20:21Z"},{"alias_kind":"pith_short_16","alias_value":"KKV4A5JHBF7HUGF7","created_at":"2026-07-05T09:20:21Z"},{"alias_kind":"pith_short_8","alias_value":"KKV4A5JH","created_at":"2026-07-05T09:20:21Z"}],"graph_snapshots":[{"event_id":"sha256:244b34a0ceb057232a475200106825ba56385fe2165abb297c8dfe61e5a0277c","target":"graph","created_at":"2026-07-05T09:20:21Z","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/2102.09907/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In offline reinforcement learning (RL) an optimal policy is learned solely from a priori collected observational data. However, in observational data, actions are often confounded by unobserved variables. Instrumental variables (IVs), in the context of RL, are the variables whose influence on the state variables is all mediated by the action. When a valid instrument is present, we can recover the confounded transition dynamics through observational data. We study a confounded Markov decision process where the transition dynamics admit an additive nonlinear functional form. Using IVs, we derive","authors_text":"Luofeng Liao, Mladen Kolar, Yixin Wang, Zhaoran Wang, Zhuoran Yang, Zuyue Fu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-02-19T13:01:40Z","title":"Instrumental Variable Value Iteration for Causal Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.09907","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:c2ecaf9e1c6f1c4becd1474c85c7a3743d232e443efaac6099d715080f0dea3a","target":"record","created_at":"2026-07-05T09:20:21Z","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":"ba7ffc5c6f6bd08825831ce2c7d41641a3da2924af8a7b0fd5d9abed689116be","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-02-19T13:01:40Z","title_canon_sha256":"c1832bf1372c23921f2797dafdf7dac559ea558df40a7cc3a8508bd3637cf139"},"schema_version":"1.0","source":{"id":"2102.09907","kind":"arxiv","version":3}},"canonical_sha256":"52abc07527097e7a18bf7552553dfa26b64bb86a3876831ec067778921ab17a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"52abc07527097e7a18bf7552553dfa26b64bb86a3876831ec067778921ab17a8","first_computed_at":"2026-07-05T09:20:21.284914Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:20:21.284914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X2hzcjrNb8uYrLLYKI/29SFBzVYR2OcBZU2AwdLaWPBugt2LjqINTeoVrPGm88YpNLvC6WnmbtoMzvzNBCnZBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:20:21.285426Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.09907","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2ecaf9e1c6f1c4becd1474c85c7a3743d232e443efaac6099d715080f0dea3a","sha256:244b34a0ceb057232a475200106825ba56385fe2165abb297c8dfe61e5a0277c"],"state_sha256":"fcfe2f290149e3816c5f956133d84b6b012aa6394be18df2b467c194ab2bf1a7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vy4UTlYczh2yjCjHgSFMeDb9qwigUA+MMtovnB9MBpu+wo7xkg5Yvk329o0TgA1Ay6pLQ08B7AGk4+U4iXVGAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T13:11:56.260013Z","bundle_sha256":"630dac26707dc103987c86e10e5ecc48d01be99a119a3cd0c8ca0dafebaf7148"}}