{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FW26DEYLFLLOPPCZASAIXBNM65","short_pith_number":"pith:FW26DEYL","canonical_record":{"source":{"id":"2302.09456","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-19T02:11:22Z","cross_cats_sorted":[],"title_canon_sha256":"38169aa7978e03d698433527dbc944027e044bf3fc885d79e55b83aa4de401fe","abstract_canon_sha256":"e404c47db68bba7f4bf75a471d4cb1a9a64c53139fb27110fd621e470c32a8dc"},"schema_version":"1.0"},"canonical_sha256":"2db5e1930b2ad6e7bc5904808b85acf745b7e77cfc8d4e2c0390e80e3efb5383","source":{"kind":"arxiv","id":"2302.09456","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.09456","created_at":"2026-07-05T07:28:43Z"},{"alias_kind":"arxiv_version","alias_value":"2302.09456v3","created_at":"2026-07-05T07:28:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.09456","created_at":"2026-07-05T07:28:43Z"},{"alias_kind":"pith_short_12","alias_value":"FW26DEYLFLLO","created_at":"2026-07-05T07:28:43Z"},{"alias_kind":"pith_short_16","alias_value":"FW26DEYLFLLOPPCZ","created_at":"2026-07-05T07:28:43Z"},{"alias_kind":"pith_short_8","alias_value":"FW26DEYL","created_at":"2026-07-05T07:28:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FW26DEYLFLLOPPCZASAIXBNM65","target":"record","payload":{"canonical_record":{"source":{"id":"2302.09456","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-19T02:11:22Z","cross_cats_sorted":[],"title_canon_sha256":"38169aa7978e03d698433527dbc944027e044bf3fc885d79e55b83aa4de401fe","abstract_canon_sha256":"e404c47db68bba7f4bf75a471d4cb1a9a64c53139fb27110fd621e470c32a8dc"},"schema_version":"1.0"},"canonical_sha256":"2db5e1930b2ad6e7bc5904808b85acf745b7e77cfc8d4e2c0390e80e3efb5383","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:43.920914Z","signature_b64":"DjkNoh0Gp29OcYKHSYiolKB+EhV2DjmOY/iw2uHwIYU0PNPlNZJNdoKuKQ/3oupapsuVjxuJ5ZUV7K9RjHMaBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2db5e1930b2ad6e7bc5904808b85acf745b7e77cfc8d4e2c0390e80e3efb5383","last_reissued_at":"2026-07-05T07:28:43.920440Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:43.920440Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.09456","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:28:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ICoz1gtaG/9o59EdNA53YWmV3rN/09pI7l3PmwV7buIq8o20qGpmjTpoIsqMP219jpm8Bg/1yTPjoRKwklnwDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T13:08:39.082570Z"},"content_sha256":"edd424ab01191beb64bf847746ea774cd3d3f5caa07731b9f2ca12019a6b14ad","schema_version":"1.0","event_id":"sha256:edd424ab01191beb64bf847746ea774cd3d3f5caa07731b9f2ca12019a6b14ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FW26DEYLFLLOPPCZASAIXBNM65","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distributional Offline Policy Evaluation with Predictive Error Guarantees","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Masatoshi Uehara, Runzhe Wu, Wen Sun","submitted_at":"2023-02-19T02:11:22Z","abstract_excerpt":"We study the problem of estimating the distribution of the return of a policy using an offline dataset that is not generated from the policy, i.e., distributional offline policy evaluation (OPE). We propose an algorithm called Fitted Likelihood Estimation (FLE), which conducts a sequence of Maximum Likelihood Estimation (MLE) and has the flexibility of integrating any state-of-the-art probabilistic generative models as long as it can be trained via MLE. FLE can be used for both finite-horizon and infinite-horizon discounted settings where rewards can be multi-dimensional vectors. Our theoretic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.09456","kind":"arxiv","version":3},"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/2302.09456/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":"2026-07-05T07:28:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SYeEGrdVrywBsdnCoDlEfZ2LmaNMO1Ll0bOrx6Yt90bC9PGM6wAhgqVP3ljTH4Ixcgk5aMtySm6rKGS1MpiUDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T13:08:39.082956Z"},"content_sha256":"8fb5dd421ad007bf74af5c1eb82caf13cfc9b3766a68ecc2ab9f742de847b10c","schema_version":"1.0","event_id":"sha256:8fb5dd421ad007bf74af5c1eb82caf13cfc9b3766a68ecc2ab9f742de847b10c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FW26DEYLFLLOPPCZASAIXBNM65/bundle.json","state_url":"https://pith.science/pith/FW26DEYLFLLOPPCZASAIXBNM65/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FW26DEYLFLLOPPCZASAIXBNM65/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":"2026-07-05T13:08:39Z","links":{"resolver":"https://pith.science/pith/FW26DEYLFLLOPPCZASAIXBNM65","bundle":"https://pith.science/pith/FW26DEYLFLLOPPCZASAIXBNM65/bundle.json","state":"https://pith.science/pith/FW26DEYLFLLOPPCZASAIXBNM65/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FW26DEYLFLLOPPCZASAIXBNM65/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FW26DEYLFLLOPPCZASAIXBNM65","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":"e404c47db68bba7f4bf75a471d4cb1a9a64c53139fb27110fd621e470c32a8dc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-19T02:11:22Z","title_canon_sha256":"38169aa7978e03d698433527dbc944027e044bf3fc885d79e55b83aa4de401fe"},"schema_version":"1.0","source":{"id":"2302.09456","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.09456","created_at":"2026-07-05T07:28:43Z"},{"alias_kind":"arxiv_version","alias_value":"2302.09456v3","created_at":"2026-07-05T07:28:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.09456","created_at":"2026-07-05T07:28:43Z"},{"alias_kind":"pith_short_12","alias_value":"FW26DEYLFLLO","created_at":"2026-07-05T07:28:43Z"},{"alias_kind":"pith_short_16","alias_value":"FW26DEYLFLLOPPCZ","created_at":"2026-07-05T07:28:43Z"},{"alias_kind":"pith_short_8","alias_value":"FW26DEYL","created_at":"2026-07-05T07:28:43Z"}],"graph_snapshots":[{"event_id":"sha256:8fb5dd421ad007bf74af5c1eb82caf13cfc9b3766a68ecc2ab9f742de847b10c","target":"graph","created_at":"2026-07-05T07:28:43Z","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/2302.09456/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the problem of estimating the distribution of the return of a policy using an offline dataset that is not generated from the policy, i.e., distributional offline policy evaluation (OPE). We propose an algorithm called Fitted Likelihood Estimation (FLE), which conducts a sequence of Maximum Likelihood Estimation (MLE) and has the flexibility of integrating any state-of-the-art probabilistic generative models as long as it can be trained via MLE. FLE can be used for both finite-horizon and infinite-horizon discounted settings where rewards can be multi-dimensional vectors. Our theoretic","authors_text":"Masatoshi Uehara, Runzhe Wu, Wen Sun","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-19T02:11:22Z","title":"Distributional Offline Policy Evaluation with Predictive Error Guarantees"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.09456","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:edd424ab01191beb64bf847746ea774cd3d3f5caa07731b9f2ca12019a6b14ad","target":"record","created_at":"2026-07-05T07:28:43Z","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":"e404c47db68bba7f4bf75a471d4cb1a9a64c53139fb27110fd621e470c32a8dc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-19T02:11:22Z","title_canon_sha256":"38169aa7978e03d698433527dbc944027e044bf3fc885d79e55b83aa4de401fe"},"schema_version":"1.0","source":{"id":"2302.09456","kind":"arxiv","version":3}},"canonical_sha256":"2db5e1930b2ad6e7bc5904808b85acf745b7e77cfc8d4e2c0390e80e3efb5383","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2db5e1930b2ad6e7bc5904808b85acf745b7e77cfc8d4e2c0390e80e3efb5383","first_computed_at":"2026-07-05T07:28:43.920440Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:28:43.920440Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DjkNoh0Gp29OcYKHSYiolKB+EhV2DjmOY/iw2uHwIYU0PNPlNZJNdoKuKQ/3oupapsuVjxuJ5ZUV7K9RjHMaBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:28:43.920914Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.09456","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:edd424ab01191beb64bf847746ea774cd3d3f5caa07731b9f2ca12019a6b14ad","sha256:8fb5dd421ad007bf74af5c1eb82caf13cfc9b3766a68ecc2ab9f742de847b10c"],"state_sha256":"cb5feb1da32de4e77b578e9ef71ba6d6cd61971619067096d6e2ed1ce831c856"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bzxjrvnzvqyg3kvCNkP+u2OgsCLzSqacdDgUIAqUhdF3KoLyjTpWt4YOKnxiYy+FJhLexpxRU1zfNgUN2OljDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T13:08:39.085384Z","bundle_sha256":"4a01e8765c646515f5f69411f8fbf8ff5d1a0d61ef886f789948e7ecf46f1ad6"}}