{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:XSOUAHQVO5GP5A4KUYHZJCC4L4","short_pith_number":"pith:XSOUAHQV","canonical_record":{"source":{"id":"2212.03932","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-07T19:56:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a1171b16179218c4bb1961b3fb3ebe8e95caaaa7f4576ddcba0015d187024a66","abstract_canon_sha256":"9c7f19d44296b263f79a047f53d998097e6126c342b72ab1e778d5c12f649c65"},"schema_version":"1.0"},"canonical_sha256":"bc9d401e15774cfe838aa60f94885c5f317eabaac63f35dbf40e1864ec1caee6","source":{"kind":"arxiv","id":"2212.03932","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.03932","created_at":"2026-07-05T08:15:34Z"},{"alias_kind":"arxiv_version","alias_value":"2212.03932v5","created_at":"2026-07-05T08:15:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.03932","created_at":"2026-07-05T08:15:34Z"},{"alias_kind":"pith_short_12","alias_value":"XSOUAHQVO5GP","created_at":"2026-07-05T08:15:34Z"},{"alias_kind":"pith_short_16","alias_value":"XSOUAHQVO5GP5A4K","created_at":"2026-07-05T08:15:34Z"},{"alias_kind":"pith_short_8","alias_value":"XSOUAHQV","created_at":"2026-07-05T08:15:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:XSOUAHQVO5GP5A4KUYHZJCC4L4","target":"record","payload":{"canonical_record":{"source":{"id":"2212.03932","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-07T19:56:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a1171b16179218c4bb1961b3fb3ebe8e95caaaa7f4576ddcba0015d187024a66","abstract_canon_sha256":"9c7f19d44296b263f79a047f53d998097e6126c342b72ab1e778d5c12f649c65"},"schema_version":"1.0"},"canonical_sha256":"bc9d401e15774cfe838aa60f94885c5f317eabaac63f35dbf40e1864ec1caee6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:15:34.541292Z","signature_b64":"qNpktc8BnVaPq05pUuq/s5XvPOSR6C+lvs4wxvUu7ZHXbWbj3gHkFSMCZAMM7yzGVxnG4MYK7VrazasM7po5DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc9d401e15774cfe838aa60f94885c5f317eabaac63f35dbf40e1864ec1caee6","last_reissued_at":"2026-07-05T08:15:34.540746Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:15:34.540746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.03932","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:15:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6f0e+6Us3hrBy+3qHgWOB8PwfEOWxHiLL1Up6rPk6rZTISTT1zj0oq8DIyymBYvfTWvLZXw0UzZ6ZcVXlREiBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T01:32:25.426712Z"},"content_sha256":"eeff4baecff5863cbdba8760dc64b279e61b5439e6d6d270f5496c357dcf1eb9","schema_version":"1.0","event_id":"sha256:eeff4baecff5863cbdba8760dc64b279e61b5439e6d6d270f5496c357dcf1eb9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:XSOUAHQVO5GP5A4KUYHZJCC4L4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Low Variance Off-policy Evaluation with State-based Importance Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David M. Bossens, Philip S. Thomas","submitted_at":"2022-12-07T19:56:11Z","abstract_excerpt":"In many domains, the exploration process of reinforcement learning will be too costly as it requires trying out suboptimal policies, resulting in a need for off-policy evaluation, in which a target policy is evaluated based on data collected from a known behaviour policy. In this context, importance sampling estimators provide estimates for the expected return by weighting the trajectory based on the probability ratio of the target policy and the behaviour policy. Unfortunately, such estimators have a high variance and therefore a large mean squared error. This paper proposes state-based impor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.03932","kind":"arxiv","version":5},"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/2212.03932/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":"2026-07-05T08:15:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"43YRCEmZ359yvnhplmmDuFIhcM7hlojEM4Q1883NtuyrVgM1kOLD2/fX58UXr9oH2BxK7d0h7oSWJ6rJ4+KnBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T01:32:25.427657Z"},"content_sha256":"e00d5bbc7bdb688f8d0e3710b9b35f59b696b1cdf027daf335292a0164269972","schema_version":"1.0","event_id":"sha256:e00d5bbc7bdb688f8d0e3710b9b35f59b696b1cdf027daf335292a0164269972"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XSOUAHQVO5GP5A4KUYHZJCC4L4/bundle.json","state_url":"https://pith.science/pith/XSOUAHQVO5GP5A4KUYHZJCC4L4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XSOUAHQVO5GP5A4KUYHZJCC4L4/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":"2026-08-18T01:32:25Z","links":{"resolver":"https://pith.science/pith/XSOUAHQVO5GP5A4KUYHZJCC4L4","bundle":"https://pith.science/pith/XSOUAHQVO5GP5A4KUYHZJCC4L4/bundle.json","state":"https://pith.science/pith/XSOUAHQVO5GP5A4KUYHZJCC4L4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XSOUAHQVO5GP5A4KUYHZJCC4L4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:XSOUAHQVO5GP5A4KUYHZJCC4L4","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":"9c7f19d44296b263f79a047f53d998097e6126c342b72ab1e778d5c12f649c65","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-07T19:56:11Z","title_canon_sha256":"a1171b16179218c4bb1961b3fb3ebe8e95caaaa7f4576ddcba0015d187024a66"},"schema_version":"1.0","source":{"id":"2212.03932","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.03932","created_at":"2026-07-05T08:15:34Z"},{"alias_kind":"arxiv_version","alias_value":"2212.03932v5","created_at":"2026-07-05T08:15:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.03932","created_at":"2026-07-05T08:15:34Z"},{"alias_kind":"pith_short_12","alias_value":"XSOUAHQVO5GP","created_at":"2026-07-05T08:15:34Z"},{"alias_kind":"pith_short_16","alias_value":"XSOUAHQVO5GP5A4K","created_at":"2026-07-05T08:15:34Z"},{"alias_kind":"pith_short_8","alias_value":"XSOUAHQV","created_at":"2026-07-05T08:15:34Z"}],"graph_snapshots":[{"event_id":"sha256:e00d5bbc7bdb688f8d0e3710b9b35f59b696b1cdf027daf335292a0164269972","target":"graph","created_at":"2026-07-05T08:15:34Z","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/2212.03932/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In many domains, the exploration process of reinforcement learning will be too costly as it requires trying out suboptimal policies, resulting in a need for off-policy evaluation, in which a target policy is evaluated based on data collected from a known behaviour policy. In this context, importance sampling estimators provide estimates for the expected return by weighting the trajectory based on the probability ratio of the target policy and the behaviour policy. Unfortunately, such estimators have a high variance and therefore a large mean squared error. This paper proposes state-based impor","authors_text":"David M. Bossens, Philip S. Thomas","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-07T19:56:11Z","title":"Low Variance Off-policy Evaluation with State-based Importance Sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.03932","kind":"arxiv","version":5},"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:eeff4baecff5863cbdba8760dc64b279e61b5439e6d6d270f5496c357dcf1eb9","target":"record","created_at":"2026-07-05T08:15:34Z","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":"9c7f19d44296b263f79a047f53d998097e6126c342b72ab1e778d5c12f649c65","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-07T19:56:11Z","title_canon_sha256":"a1171b16179218c4bb1961b3fb3ebe8e95caaaa7f4576ddcba0015d187024a66"},"schema_version":"1.0","source":{"id":"2212.03932","kind":"arxiv","version":5}},"canonical_sha256":"bc9d401e15774cfe838aa60f94885c5f317eabaac63f35dbf40e1864ec1caee6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc9d401e15774cfe838aa60f94885c5f317eabaac63f35dbf40e1864ec1caee6","first_computed_at":"2026-07-05T08:15:34.540746Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:15:34.540746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qNpktc8BnVaPq05pUuq/s5XvPOSR6C+lvs4wxvUu7ZHXbWbj3gHkFSMCZAMM7yzGVxnG4MYK7VrazasM7po5DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:15:34.541292Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.03932","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eeff4baecff5863cbdba8760dc64b279e61b5439e6d6d270f5496c357dcf1eb9","sha256:e00d5bbc7bdb688f8d0e3710b9b35f59b696b1cdf027daf335292a0164269972"],"state_sha256":"21de4bed784f1166291554d134ee005e3318488c0183f1a57348e61e29a03644"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LgUwL1W8o82JEXRBvJC3W9PNc7DtYO9Mn3XoMbOUy/4qAmSIGg+GarJX+0eHdGE6MCqxUTZ5OQYArltPqEGbDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T01:32:25.435212Z","bundle_sha256":"36ab9e1c42a6c5553269e04caea7d5b9b5ca2817eeaaa4ea610a498bc2e00861"}}