{"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"}