{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:B6CNVIYSE3QQ5WK4ETCLD6JPXU","short_pith_number":"pith:B6CNVIYS","canonical_record":{"source":{"id":"2412.05783","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-08T02:28:58Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"948fae4a058ac7bdd40bf1287fe9aedc324bd5d0bfe952db31a5a0d972f8f8e3","abstract_canon_sha256":"40b1f6f56b7d96b15d536d64f6dfd7712a1bd2e17bedb33497c20b9749485a05"},"schema_version":"1.0"},"canonical_sha256":"0f84daa31226e10ed95c24c4b1f92fbd08a863aaa7306f9cb52cacf1721f80e3","source":{"kind":"arxiv","id":"2412.05783","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.05783","created_at":"2026-07-05T09:46:08Z"},{"alias_kind":"arxiv_version","alias_value":"2412.05783v1","created_at":"2026-07-05T09:46:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05783","created_at":"2026-07-05T09:46:08Z"},{"alias_kind":"pith_short_12","alias_value":"B6CNVIYSE3QQ","created_at":"2026-07-05T09:46:08Z"},{"alias_kind":"pith_short_16","alias_value":"B6CNVIYSE3QQ5WK4","created_at":"2026-07-05T09:46:08Z"},{"alias_kind":"pith_short_8","alias_value":"B6CNVIYS","created_at":"2026-07-05T09:46:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:B6CNVIYSE3QQ5WK4ETCLD6JPXU","target":"record","payload":{"canonical_record":{"source":{"id":"2412.05783","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-08T02:28:58Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"948fae4a058ac7bdd40bf1287fe9aedc324bd5d0bfe952db31a5a0d972f8f8e3","abstract_canon_sha256":"40b1f6f56b7d96b15d536d64f6dfd7712a1bd2e17bedb33497c20b9749485a05"},"schema_version":"1.0"},"canonical_sha256":"0f84daa31226e10ed95c24c4b1f92fbd08a863aaa7306f9cb52cacf1721f80e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:08.825214Z","signature_b64":"6+x2vrlLaFrDWEoXk+QPpsk6oiIA7Lv2ic6CBexb5jN4rk4hIb/TjWYwdyXY6sqvA0LWASKlIpTKWJSzytfFCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f84daa31226e10ed95c24c4b1f92fbd08a863aaa7306f9cb52cacf1721f80e3","last_reissued_at":"2026-07-05T09:46:08.824762Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:08.824762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.05783","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":"2026-07-05T09:46:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gro90fhZiF/VWWMGsjZOcGbeJ80EDbUvTFpTNCfhM909BJu2N7+xannUxoZ1iXF0t3vOMSDn9E/EOZZ3zKEGCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T07:57:16.130076Z"},"content_sha256":"5aaf230ed8458dc586f5b36680c5ee7acbc1bcad12191adb92126ce799c8a0f4","schema_version":"1.0","event_id":"sha256:5aaf230ed8458dc586f5b36680c5ee7acbc1bcad12191adb92126ce799c8a0f4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:B6CNVIYSE3QQ5WK4ETCLD6JPXU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Two-way Deconfounder for Off-policy Evaluation in Causal Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chengchun Shi, Fan Zhou, Ruixin Peng, Shuguang Yu, Shuxing Fang, Zhengling Qi","submitted_at":"2024-12-08T02:28:58Z","abstract_excerpt":"This paper studies off-policy evaluation (OPE) in the presence of unmeasured confounders. Inspired by the two-way fixed effects regression model widely used in the panel data literature, we propose a two-way unmeasured confounding assumption to model the system dynamics in causal reinforcement learning and develop a two-way deconfounder algorithm that devises a neural tensor network to simultaneously learn both the unmeasured confounders and the system dynamics, based on which a model-based estimator can be constructed for consistent policy value estimation. We illustrate the effectiveness of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05783","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/2412.05783/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":"2026-07-05T09:46:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iyHoWoPxEQy5RHCK2BWTabOtHWD8obmiKQhhACdlC9Pf6wsX1wPPMGaX7PO9miu8mdiCqBU0xwihIUzVMzdQBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T07:57:16.130571Z"},"content_sha256":"8cfc3c9681c460640459ad4ca048d5ef095f54f8bb7a3008b399832f376be84e","schema_version":"1.0","event_id":"sha256:8cfc3c9681c460640459ad4ca048d5ef095f54f8bb7a3008b399832f376be84e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B6CNVIYSE3QQ5WK4ETCLD6JPXU/bundle.json","state_url":"https://pith.science/pith/B6CNVIYSE3QQ5WK4ETCLD6JPXU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B6CNVIYSE3QQ5WK4ETCLD6JPXU/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":"2026-08-22T07:57:16Z","links":{"resolver":"https://pith.science/pith/B6CNVIYSE3QQ5WK4ETCLD6JPXU","bundle":"https://pith.science/pith/B6CNVIYSE3QQ5WK4ETCLD6JPXU/bundle.json","state":"https://pith.science/pith/B6CNVIYSE3QQ5WK4ETCLD6JPXU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B6CNVIYSE3QQ5WK4ETCLD6JPXU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:B6CNVIYSE3QQ5WK4ETCLD6JPXU","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":"40b1f6f56b7d96b15d536d64f6dfd7712a1bd2e17bedb33497c20b9749485a05","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-08T02:28:58Z","title_canon_sha256":"948fae4a058ac7bdd40bf1287fe9aedc324bd5d0bfe952db31a5a0d972f8f8e3"},"schema_version":"1.0","source":{"id":"2412.05783","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.05783","created_at":"2026-07-05T09:46:08Z"},{"alias_kind":"arxiv_version","alias_value":"2412.05783v1","created_at":"2026-07-05T09:46:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05783","created_at":"2026-07-05T09:46:08Z"},{"alias_kind":"pith_short_12","alias_value":"B6CNVIYSE3QQ","created_at":"2026-07-05T09:46:08Z"},{"alias_kind":"pith_short_16","alias_value":"B6CNVIYSE3QQ5WK4","created_at":"2026-07-05T09:46:08Z"},{"alias_kind":"pith_short_8","alias_value":"B6CNVIYS","created_at":"2026-07-05T09:46:08Z"}],"graph_snapshots":[{"event_id":"sha256:8cfc3c9681c460640459ad4ca048d5ef095f54f8bb7a3008b399832f376be84e","target":"graph","created_at":"2026-07-05T09:46:08Z","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/2412.05783/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper studies off-policy evaluation (OPE) in the presence of unmeasured confounders. Inspired by the two-way fixed effects regression model widely used in the panel data literature, we propose a two-way unmeasured confounding assumption to model the system dynamics in causal reinforcement learning and develop a two-way deconfounder algorithm that devises a neural tensor network to simultaneously learn both the unmeasured confounders and the system dynamics, based on which a model-based estimator can be constructed for consistent policy value estimation. We illustrate the effectiveness of ","authors_text":"Chengchun Shi, Fan Zhou, Ruixin Peng, Shuguang Yu, Shuxing Fang, Zhengling Qi","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-08T02:28:58Z","title":"Two-way Deconfounder for Off-policy Evaluation in Causal Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05783","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":"sha256:5aaf230ed8458dc586f5b36680c5ee7acbc1bcad12191adb92126ce799c8a0f4","target":"record","created_at":"2026-07-05T09:46:08Z","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":"40b1f6f56b7d96b15d536d64f6dfd7712a1bd2e17bedb33497c20b9749485a05","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-08T02:28:58Z","title_canon_sha256":"948fae4a058ac7bdd40bf1287fe9aedc324bd5d0bfe952db31a5a0d972f8f8e3"},"schema_version":"1.0","source":{"id":"2412.05783","kind":"arxiv","version":1}},"canonical_sha256":"0f84daa31226e10ed95c24c4b1f92fbd08a863aaa7306f9cb52cacf1721f80e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f84daa31226e10ed95c24c4b1f92fbd08a863aaa7306f9cb52cacf1721f80e3","first_computed_at":"2026-07-05T09:46:08.824762Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:46:08.824762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6+x2vrlLaFrDWEoXk+QPpsk6oiIA7Lv2ic6CBexb5jN4rk4hIb/TjWYwdyXY6sqvA0LWASKlIpTKWJSzytfFCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:46:08.825214Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.05783","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5aaf230ed8458dc586f5b36680c5ee7acbc1bcad12191adb92126ce799c8a0f4","sha256:8cfc3c9681c460640459ad4ca048d5ef095f54f8bb7a3008b399832f376be84e"],"state_sha256":"379b9f3553c974ce2707f0572748f2f3ae791fe41366a59001374670fe99ac50"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aueXdtBnxlUhZVFwnfH9/mlcz97xZVOSJdDFMEqteAvX6/6xfrfNN5hu9h0tGcZELbL4oyiArNKIJUN7a2yxCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T07:57:16.135009Z","bundle_sha256":"2565db439db238dc03a644767006bb060ec5f1ae48dbd449d9daaed48bcc6ef3"}}