{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:V2TRBCZY4MTUAPZAD54NBKPC5R","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":"cfbac66950568c46e4a12425bd3a531d74d613f7c7361e192fa821434b3dd259","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-14T20:18:31Z","title_canon_sha256":"dd5a0821e3adc4c33f39e03e9168a71ba114944fa61829d2259651ec61f3efe8"},"schema_version":"1.0","source":{"id":"1905.05824","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.05824","created_at":"2026-07-05T02:19:53Z"},{"alias_kind":"arxiv_version","alias_value":"1905.05824v3","created_at":"2026-07-05T02:19:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.05824","created_at":"2026-07-05T02:19:53Z"},{"alias_kind":"pith_short_12","alias_value":"V2TRBCZY4MTU","created_at":"2026-07-05T02:19:53Z"},{"alias_kind":"pith_short_16","alias_value":"V2TRBCZY4MTUAPZA","created_at":"2026-07-05T02:19:53Z"},{"alias_kind":"pith_short_8","alias_value":"V2TRBCZY","created_at":"2026-07-05T02:19:53Z"}],"graph_snapshots":[{"event_id":"sha256:9a4b711b1d0f59b42fa2b5990fc914ee694b3c3ddfffb1e361385c6f61f5d298","target":"graph","created_at":"2026-07-05T02:19:53Z","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/1905.05824/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce an off-policy evaluation procedure for highlighting episodes where applying a reinforcement learned (RL) policy is likely to have produced a substantially different outcome than the observed policy. In particular, we introduce a class of structural causal models (SCMs) for generating counterfactual trajectories in finite partially observable Markov Decision Processes (POMDPs). We see this as a useful procedure for off-policy \"debugging\" in high-risk settings (e.g., healthcare); by decomposing the expected difference in reward between the RL and observed policy into specific episod","authors_text":"David Sontag, Michael Oberst","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-14T20:18:31Z","title":"Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.05824","kind":"arxiv","version":3},"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:a5c6052bc7504a1b065cbbf429577d71e4b8aba36e4a1b538453be21d8c91125","target":"record","created_at":"2026-07-05T02:19:53Z","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":"cfbac66950568c46e4a12425bd3a531d74d613f7c7361e192fa821434b3dd259","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-14T20:18:31Z","title_canon_sha256":"dd5a0821e3adc4c33f39e03e9168a71ba114944fa61829d2259651ec61f3efe8"},"schema_version":"1.0","source":{"id":"1905.05824","kind":"arxiv","version":3}},"canonical_sha256":"aea7108b38e327403f201f78d0a9e2ec57d96f3fd0b5a00c9151879a04bd42ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aea7108b38e327403f201f78d0a9e2ec57d96f3fd0b5a00c9151879a04bd42ab","first_computed_at":"2026-07-05T02:19:53.001570Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:19:53.001570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fX6GjR5BOTRPQezG2bT2fPkW0dLtf2oUjZFoGtTbI9UPTx5CkqvO6Qxw6AsUsMNX0DgbQBXlJLmeuquIjMlKAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:19:53.001974Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.05824","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5c6052bc7504a1b065cbbf429577d71e4b8aba36e4a1b538453be21d8c91125","sha256:9a4b711b1d0f59b42fa2b5990fc914ee694b3c3ddfffb1e361385c6f61f5d298"],"state_sha256":"8dec5d5c226c6036ea1e28eefa93ac24afa5bd5e0ca263366b9b1a7d1c501573"}