{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:UPL6VNVYNM5ODRN3XJYVLAVJ2Y","short_pith_number":"pith:UPL6VNVY","canonical_record":{"source":{"id":"2302.11725","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-23T01:17:21Z","cross_cats_sorted":[],"title_canon_sha256":"ca6597944bb5b33bc8af59a58683ffa7333797367fb9067181d63f081aa38ea3","abstract_canon_sha256":"10546e323035e520a20dc44ea8d9ac81964863fbd76a78d94234be19b13df585"},"schema_version":"1.0"},"canonical_sha256":"a3d7eab6b86b3ae1c5bbba715582a9d625b52b621d9c736f5d6c89d22196a708","source":{"kind":"arxiv","id":"2302.11725","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.11725","created_at":"2026-07-05T05:44:55Z"},{"alias_kind":"arxiv_version","alias_value":"2302.11725v1","created_at":"2026-07-05T05:44:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.11725","created_at":"2026-07-05T05:44:55Z"},{"alias_kind":"pith_short_12","alias_value":"UPL6VNVYNM5O","created_at":"2026-07-05T05:44:55Z"},{"alias_kind":"pith_short_16","alias_value":"UPL6VNVYNM5ODRN3","created_at":"2026-07-05T05:44:55Z"},{"alias_kind":"pith_short_8","alias_value":"UPL6VNVY","created_at":"2026-07-05T05:44:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:UPL6VNVYNM5ODRN3XJYVLAVJ2Y","target":"record","payload":{"canonical_record":{"source":{"id":"2302.11725","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-23T01:17:21Z","cross_cats_sorted":[],"title_canon_sha256":"ca6597944bb5b33bc8af59a58683ffa7333797367fb9067181d63f081aa38ea3","abstract_canon_sha256":"10546e323035e520a20dc44ea8d9ac81964863fbd76a78d94234be19b13df585"},"schema_version":"1.0"},"canonical_sha256":"a3d7eab6b86b3ae1c5bbba715582a9d625b52b621d9c736f5d6c89d22196a708","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:44:55.366352Z","signature_b64":"0eCT83T3UrM7YwBOg463bYzTHRVLG5H+/xH1pGj+PWQit99gT4QhrHKa9pexlSjdWiN05iZl29N80+gKU23hDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3d7eab6b86b3ae1c5bbba715582a9d625b52b621d9c736f5d6c89d22196a708","last_reissued_at":"2026-07-05T05:44:55.365939Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:44:55.365939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.11725","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":"2026-07-05T05:44:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ptHSkUd1Kr1oegE4pp4PQLoGVaVJm+NphF3/dJtnkpeMwMvObHCkkPzEmZGssz4xk9gnexTmSBleGxjbN1LbAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T03:37:45.514091Z"},"content_sha256":"696aedff253c9edaafb1e6b2751141f5100a94e8cafcbef3b3e2381f81ab9335","schema_version":"1.0","event_id":"sha256:696aedff253c9edaafb1e6b2751141f5100a94e8cafcbef3b3e2381f81ab9335"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:UPL6VNVYNM5ODRN3XJYVLAVJ2Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Asymptotically Unbiased Off-Policy Policy Evaluation when Reusing Old Data in Nonstationary Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Martha White, Philip Thomas, Vincent Liu, Yash Chandak","submitted_at":"2023-02-23T01:17:21Z","abstract_excerpt":"In this work, we consider the off-policy policy evaluation problem for contextual bandits and finite horizon reinforcement learning in the nonstationary setting. Reusing old data is critical for policy evaluation, but existing estimators that reuse old data introduce large bias such that we can not obtain a valid confidence interval. Inspired from a related field called survey sampling, we introduce a variant of the doubly robust (DR) estimator, called the regression-assisted DR estimator, that can incorporate the past data without introducing a large bias. The estimator unifies several existi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.11725","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/2302.11725/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":"2026-07-05T05:44:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ExPh0Uznp6Iv/bkNhJKmDWA0HAPCQK5JiC41AUWgtvfb5fFBJ02NXcq92Hm9b3UAYTZoju57+M+hfudGXqexDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T03:37:45.514674Z"},"content_sha256":"19911f241111a09283293ed95431cfb26aa85d85a0e994bc06abd1720454b242","schema_version":"1.0","event_id":"sha256:19911f241111a09283293ed95431cfb26aa85d85a0e994bc06abd1720454b242"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UPL6VNVYNM5ODRN3XJYVLAVJ2Y/bundle.json","state_url":"https://pith.science/pith/UPL6VNVYNM5ODRN3XJYVLAVJ2Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UPL6VNVYNM5ODRN3XJYVLAVJ2Y/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":"2026-08-07T03:37:45Z","links":{"resolver":"https://pith.science/pith/UPL6VNVYNM5ODRN3XJYVLAVJ2Y","bundle":"https://pith.science/pith/UPL6VNVYNM5ODRN3XJYVLAVJ2Y/bundle.json","state":"https://pith.science/pith/UPL6VNVYNM5ODRN3XJYVLAVJ2Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UPL6VNVYNM5ODRN3XJYVLAVJ2Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UPL6VNVYNM5ODRN3XJYVLAVJ2Y","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":"10546e323035e520a20dc44ea8d9ac81964863fbd76a78d94234be19b13df585","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-23T01:17:21Z","title_canon_sha256":"ca6597944bb5b33bc8af59a58683ffa7333797367fb9067181d63f081aa38ea3"},"schema_version":"1.0","source":{"id":"2302.11725","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.11725","created_at":"2026-07-05T05:44:55Z"},{"alias_kind":"arxiv_version","alias_value":"2302.11725v1","created_at":"2026-07-05T05:44:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.11725","created_at":"2026-07-05T05:44:55Z"},{"alias_kind":"pith_short_12","alias_value":"UPL6VNVYNM5O","created_at":"2026-07-05T05:44:55Z"},{"alias_kind":"pith_short_16","alias_value":"UPL6VNVYNM5ODRN3","created_at":"2026-07-05T05:44:55Z"},{"alias_kind":"pith_short_8","alias_value":"UPL6VNVY","created_at":"2026-07-05T05:44:55Z"}],"graph_snapshots":[{"event_id":"sha256:19911f241111a09283293ed95431cfb26aa85d85a0e994bc06abd1720454b242","target":"graph","created_at":"2026-07-05T05:44:55Z","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/2302.11725/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we consider the off-policy policy evaluation problem for contextual bandits and finite horizon reinforcement learning in the nonstationary setting. Reusing old data is critical for policy evaluation, but existing estimators that reuse old data introduce large bias such that we can not obtain a valid confidence interval. Inspired from a related field called survey sampling, we introduce a variant of the doubly robust (DR) estimator, called the regression-assisted DR estimator, that can incorporate the past data without introducing a large bias. The estimator unifies several existi","authors_text":"Martha White, Philip Thomas, Vincent Liu, Yash Chandak","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-23T01:17:21Z","title":"Asymptotically Unbiased Off-Policy Policy Evaluation when Reusing Old Data in Nonstationary Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.11725","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":"sha256:696aedff253c9edaafb1e6b2751141f5100a94e8cafcbef3b3e2381f81ab9335","target":"record","created_at":"2026-07-05T05:44:55Z","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":"10546e323035e520a20dc44ea8d9ac81964863fbd76a78d94234be19b13df585","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-23T01:17:21Z","title_canon_sha256":"ca6597944bb5b33bc8af59a58683ffa7333797367fb9067181d63f081aa38ea3"},"schema_version":"1.0","source":{"id":"2302.11725","kind":"arxiv","version":1}},"canonical_sha256":"a3d7eab6b86b3ae1c5bbba715582a9d625b52b621d9c736f5d6c89d22196a708","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3d7eab6b86b3ae1c5bbba715582a9d625b52b621d9c736f5d6c89d22196a708","first_computed_at":"2026-07-05T05:44:55.365939Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:44:55.365939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0eCT83T3UrM7YwBOg463bYzTHRVLG5H+/xH1pGj+PWQit99gT4QhrHKa9pexlSjdWiN05iZl29N80+gKU23hDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:44:55.366352Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.11725","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:696aedff253c9edaafb1e6b2751141f5100a94e8cafcbef3b3e2381f81ab9335","sha256:19911f241111a09283293ed95431cfb26aa85d85a0e994bc06abd1720454b242"],"state_sha256":"cc557768f238a55970b448eb3680ccc1700405850633fb2901b0d3b672d1164d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W2n5OgHjGPcT6+Av/VyQK8/8N+gzxcUqO/f7J3AoJCQ0JK7aNf7E83HfFmkQj+mWT3lKGYLd777ks3uE42zOAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T03:37:45.519957Z","bundle_sha256":"ad1ec78ee77a3143cdeb032ce4ba772355e878712525a899de1dc8a6dfb869df"}}