{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:LWORRY3PZ6JPJHRD76N7O6MJDU","short_pith_number":"pith:LWORRY3P","canonical_record":{"source":{"id":"1807.01066","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-03T10:20:22Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4281d9b28b1109e4f09957f47cdb89aa5a8ffe1d98f75d8da798ad24d45f1f51","abstract_canon_sha256":"903ec605818b206981d372095bcde710b88d061335110856d2743d2ba75ad60a"},"schema_version":"1.0"},"canonical_sha256":"5d9d18e36fcf92f49e23ff9bf779891d2414981d2d7cbef05f3843a8705610f9","source":{"kind":"arxiv","id":"1807.01066","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.01066","created_at":"2026-05-18T00:11:10Z"},{"alias_kind":"arxiv_version","alias_value":"1807.01066v2","created_at":"2026-05-18T00:11:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01066","created_at":"2026-05-18T00:11:10Z"},{"alias_kind":"pith_short_12","alias_value":"LWORRY3PZ6JP","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LWORRY3PZ6JPJHRD","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LWORRY3P","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:LWORRY3PZ6JPJHRD76N7O6MJDU","target":"record","payload":{"canonical_record":{"source":{"id":"1807.01066","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-03T10:20:22Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4281d9b28b1109e4f09957f47cdb89aa5a8ffe1d98f75d8da798ad24d45f1f51","abstract_canon_sha256":"903ec605818b206981d372095bcde710b88d061335110856d2743d2ba75ad60a"},"schema_version":"1.0"},"canonical_sha256":"5d9d18e36fcf92f49e23ff9bf779891d2414981d2d7cbef05f3843a8705610f9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:10.940652Z","signature_b64":"Ix6StcNP0FaQuS+pOe16H5i8jVO+AxyebWOs8vt88eH2ZxltyF8qBv6C36gaZdH9z4Wr4P/j7zecw9SU2U5vBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d9d18e36fcf92f49e23ff9bf779891d2414981d2d7cbef05f3843a8705610f9","last_reissued_at":"2026-05-18T00:11:10.939895Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:10.939895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.01066","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:11:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BqnbRlA24XMudsjI1+yne5sNtWt0s4CuP5RhDYwLIV+zjL+1jvcxKJqDCVbksWyVTwbcyot2apJR5Dn5xgSxBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:37:18.903843Z"},"content_sha256":"1c658798a821d97cf67c6532b09ee53d3ce32f45e92543e256be5c2c937a2fb4","schema_version":"1.0","event_id":"sha256:1c658798a821d97cf67c6532b09ee53d3ce32f45e92543e256be5c2c937a2fb4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:LWORRY3PZ6JPJHRD76N7O6MJDU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Behaviour Policy Estimation in Off-Policy Policy Evaluation: Calibration Matters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aldo Faisal, Aniruddh Raghu, Emma Brunskill, Finale Doshi-Velez, Matthieu Komorowski, Omer Gottesman, Yao Liu","submitted_at":"2018-07-03T10:20:22Z","abstract_excerpt":"In this work, we consider the problem of estimating a behaviour policy for use in Off-Policy Policy Evaluation (OPE) when the true behaviour policy is unknown. Via a series of empirical studies, we demonstrate how accurate OPE is strongly dependent on the calibration of estimated behaviour policy models: how precisely the behaviour policy is estimated from data. We show how powerful parametric models such as neural networks can result in highly uncalibrated behaviour policy models on a real-world medical dataset, and illustrate how a simple, non-parametric, k-nearest neighbours model produces "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.01066","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T00:11:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HcyQZSqj3IeqPI/oUj/iTtfZnHpSU48PstCl2DSQ2LQW2a+Yr3RM4dlOe2e1dEtLUD9a40UtfjWK+/h+vXpBAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:37:18.904576Z"},"content_sha256":"9d1a7177a6c419a5bbac21f790f667b882c061ff320148156b709256cbb844e2","schema_version":"1.0","event_id":"sha256:9d1a7177a6c419a5bbac21f790f667b882c061ff320148156b709256cbb844e2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LWORRY3PZ6JPJHRD76N7O6MJDU/bundle.json","state_url":"https://pith.science/pith/LWORRY3PZ6JPJHRD76N7O6MJDU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LWORRY3PZ6JPJHRD76N7O6MJDU/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":"2026-05-25T16:37:18Z","links":{"resolver":"https://pith.science/pith/LWORRY3PZ6JPJHRD76N7O6MJDU","bundle":"https://pith.science/pith/LWORRY3PZ6JPJHRD76N7O6MJDU/bundle.json","state":"https://pith.science/pith/LWORRY3PZ6JPJHRD76N7O6MJDU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LWORRY3PZ6JPJHRD76N7O6MJDU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:LWORRY3PZ6JPJHRD76N7O6MJDU","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":"903ec605818b206981d372095bcde710b88d061335110856d2743d2ba75ad60a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-03T10:20:22Z","title_canon_sha256":"4281d9b28b1109e4f09957f47cdb89aa5a8ffe1d98f75d8da798ad24d45f1f51"},"schema_version":"1.0","source":{"id":"1807.01066","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.01066","created_at":"2026-05-18T00:11:10Z"},{"alias_kind":"arxiv_version","alias_value":"1807.01066v2","created_at":"2026-05-18T00:11:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01066","created_at":"2026-05-18T00:11:10Z"},{"alias_kind":"pith_short_12","alias_value":"LWORRY3PZ6JP","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LWORRY3PZ6JPJHRD","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LWORRY3P","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:9d1a7177a6c419a5bbac21f790f667b882c061ff320148156b709256cbb844e2","target":"graph","created_at":"2026-05-18T00:11:10Z","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"},"paper":{"abstract_excerpt":"In this work, we consider the problem of estimating a behaviour policy for use in Off-Policy Policy Evaluation (OPE) when the true behaviour policy is unknown. Via a series of empirical studies, we demonstrate how accurate OPE is strongly dependent on the calibration of estimated behaviour policy models: how precisely the behaviour policy is estimated from data. We show how powerful parametric models such as neural networks can result in highly uncalibrated behaviour policy models on a real-world medical dataset, and illustrate how a simple, non-parametric, k-nearest neighbours model produces ","authors_text":"Aldo Faisal, Aniruddh Raghu, Emma Brunskill, Finale Doshi-Velez, Matthieu Komorowski, Omer Gottesman, Yao Liu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-03T10:20:22Z","title":"Behaviour Policy Estimation in Off-Policy Policy Evaluation: Calibration Matters"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.01066","kind":"arxiv","version":2},"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":"sha256:1c658798a821d97cf67c6532b09ee53d3ce32f45e92543e256be5c2c937a2fb4","target":"record","created_at":"2026-05-18T00:11:10Z","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":"903ec605818b206981d372095bcde710b88d061335110856d2743d2ba75ad60a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-03T10:20:22Z","title_canon_sha256":"4281d9b28b1109e4f09957f47cdb89aa5a8ffe1d98f75d8da798ad24d45f1f51"},"schema_version":"1.0","source":{"id":"1807.01066","kind":"arxiv","version":2}},"canonical_sha256":"5d9d18e36fcf92f49e23ff9bf779891d2414981d2d7cbef05f3843a8705610f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d9d18e36fcf92f49e23ff9bf779891d2414981d2d7cbef05f3843a8705610f9","first_computed_at":"2026-05-18T00:11:10.939895Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:11:10.939895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ix6StcNP0FaQuS+pOe16H5i8jVO+AxyebWOs8vt88eH2ZxltyF8qBv6C36gaZdH9z4Wr4P/j7zecw9SU2U5vBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:11:10.940652Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.01066","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c658798a821d97cf67c6532b09ee53d3ce32f45e92543e256be5c2c937a2fb4","sha256:9d1a7177a6c419a5bbac21f790f667b882c061ff320148156b709256cbb844e2"],"state_sha256":"ac6563b9b05971c76e3a5f0c0417eea7e2a0d51972ff59e82a6fffc24f77d37f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hmYA+IVqzt1jeiK5gIkAEiiNPvg4p1lFziCnyLXBiopYZlkgTXNqmVjTo/c5JLJKeF8DZNTb18Zk2+UeDly/AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T16:37:18.909224Z","bundle_sha256":"735c7e76c39dc2333afe14761a5c3629737f3e4a58d453899f1f8d5c16eb5c34"}}