{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:CTD5G5XE7AZ5SKU77LDPUPPVBV","short_pith_number":"pith:CTD5G5XE","canonical_record":{"source":{"id":"2002.09072","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-02-21T00:27:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"88e540f8c03f075fd9c002fdb5ef7eadd5e93b09909b6aa74d2098d0edcbcd46","abstract_canon_sha256":"598ca9cc4472c1b8a0a546bda3cc39c7e476527e010ecb1a6376214c2053d3bd"},"schema_version":"1.0"},"canonical_sha256":"14c7d376e4f833d92a9ffac6fa3df50d4b18c40636569eb20fb01441c28323dd","source":{"kind":"arxiv","id":"2002.09072","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.09072","created_at":"2026-07-05T00:42:45Z"},{"alias_kind":"arxiv_version","alias_value":"2002.09072v1","created_at":"2026-07-05T00:42:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.09072","created_at":"2026-07-05T00:42:45Z"},{"alias_kind":"pith_short_12","alias_value":"CTD5G5XE7AZ5","created_at":"2026-07-05T00:42:45Z"},{"alias_kind":"pith_short_16","alias_value":"CTD5G5XE7AZ5SKU7","created_at":"2026-07-05T00:42:45Z"},{"alias_kind":"pith_short_8","alias_value":"CTD5G5XE","created_at":"2026-07-05T00:42:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:CTD5G5XE7AZ5SKU77LDPUPPVBV","target":"record","payload":{"canonical_record":{"source":{"id":"2002.09072","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-02-21T00:27:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"88e540f8c03f075fd9c002fdb5ef7eadd5e93b09909b6aa74d2098d0edcbcd46","abstract_canon_sha256":"598ca9cc4472c1b8a0a546bda3cc39c7e476527e010ecb1a6376214c2053d3bd"},"schema_version":"1.0"},"canonical_sha256":"14c7d376e4f833d92a9ffac6fa3df50d4b18c40636569eb20fb01441c28323dd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:42:45.195415Z","signature_b64":"BMKfiAt6Z6bo1hnur4i+MipZtWEITaceqvGKmcsVfJ55GB/iV0EQOSxPh8okUISP/78lH/JvEPRnHdw7wv0zBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14c7d376e4f833d92a9ffac6fa3df50d4b18c40636569eb20fb01441c28323dd","last_reissued_at":"2026-07-05T00:42:45.194943Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:42:45.194943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.09072","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:42:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3hORF93s93Cs9tjBfC4L/RGiU7LgE3s9zZ3HoufiPBbXckyeTEhifG5gdsGSABirEFcOwLn/rfHySzIMZr+yBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:23:22.028502Z"},"content_sha256":"09208f515c5fb3e8cd9cc21febceaba2a97bce874a87f51ed57cf0f80708e42c","schema_version":"1.0","event_id":"sha256:09208f515c5fb3e8cd9cc21febceaba2a97bce874a87f51ed57cf0f80708e42c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:CTD5G5XE7AZ5SKU77LDPUPPVBV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GenDICE: Generalized Offline Estimation of Stationary Values","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Bo Dai, Dale Schuurmans, Lihong Li, Ruiyi Zhang","submitted_at":"2020-02-21T00:27:52Z","abstract_excerpt":"An important problem that arises in reinforcement learning and Monte Carlo methods is estimating quantities defined by the stationary distribution of a Markov chain. In many real-world applications, access to the underlying transition operator is limited to a fixed set of data that has already been collected, without additional interaction with the environment being available. We show that consistent estimation remains possible in this challenging scenario, and that effective estimation can still be achieved in important applications. Our approach is based on estimating a ratio that corrects f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.09072","kind":"arxiv","version":1},"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/2002.09072/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":"2026-07-05T00:42:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bbwI0xhQLWyvD3RHlVE+LZgWXo1fLZIQcaMAN+2pCOG74VjgMmMkH1sZQgxiJ+PwEIYa8MamjToTIHLstFybBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:23:22.028969Z"},"content_sha256":"c178ad6fbba0b2165080d4c3f44bd7abd5bd8d70af50b65138aad8b750e97f06","schema_version":"1.0","event_id":"sha256:c178ad6fbba0b2165080d4c3f44bd7abd5bd8d70af50b65138aad8b750e97f06"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CTD5G5XE7AZ5SKU77LDPUPPVBV/bundle.json","state_url":"https://pith.science/pith/CTD5G5XE7AZ5SKU77LDPUPPVBV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CTD5G5XE7AZ5SKU77LDPUPPVBV/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":"2026-08-03T21:23:22Z","links":{"resolver":"https://pith.science/pith/CTD5G5XE7AZ5SKU77LDPUPPVBV","bundle":"https://pith.science/pith/CTD5G5XE7AZ5SKU77LDPUPPVBV/bundle.json","state":"https://pith.science/pith/CTD5G5XE7AZ5SKU77LDPUPPVBV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CTD5G5XE7AZ5SKU77LDPUPPVBV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:CTD5G5XE7AZ5SKU77LDPUPPVBV","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":"598ca9cc4472c1b8a0a546bda3cc39c7e476527e010ecb1a6376214c2053d3bd","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-02-21T00:27:52Z","title_canon_sha256":"88e540f8c03f075fd9c002fdb5ef7eadd5e93b09909b6aa74d2098d0edcbcd46"},"schema_version":"1.0","source":{"id":"2002.09072","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.09072","created_at":"2026-07-05T00:42:45Z"},{"alias_kind":"arxiv_version","alias_value":"2002.09072v1","created_at":"2026-07-05T00:42:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.09072","created_at":"2026-07-05T00:42:45Z"},{"alias_kind":"pith_short_12","alias_value":"CTD5G5XE7AZ5","created_at":"2026-07-05T00:42:45Z"},{"alias_kind":"pith_short_16","alias_value":"CTD5G5XE7AZ5SKU7","created_at":"2026-07-05T00:42:45Z"},{"alias_kind":"pith_short_8","alias_value":"CTD5G5XE","created_at":"2026-07-05T00:42:45Z"}],"graph_snapshots":[{"event_id":"sha256:c178ad6fbba0b2165080d4c3f44bd7abd5bd8d70af50b65138aad8b750e97f06","target":"graph","created_at":"2026-07-05T00:42:45Z","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/2002.09072/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"An important problem that arises in reinforcement learning and Monte Carlo methods is estimating quantities defined by the stationary distribution of a Markov chain. In many real-world applications, access to the underlying transition operator is limited to a fixed set of data that has already been collected, without additional interaction with the environment being available. We show that consistent estimation remains possible in this challenging scenario, and that effective estimation can still be achieved in important applications. Our approach is based on estimating a ratio that corrects f","authors_text":"Bo Dai, Dale Schuurmans, Lihong Li, Ruiyi Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-02-21T00:27:52Z","title":"GenDICE: Generalized Offline Estimation of Stationary Values"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.09072","kind":"arxiv","version":1},"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":"sha256:09208f515c5fb3e8cd9cc21febceaba2a97bce874a87f51ed57cf0f80708e42c","target":"record","created_at":"2026-07-05T00:42:45Z","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":"598ca9cc4472c1b8a0a546bda3cc39c7e476527e010ecb1a6376214c2053d3bd","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-02-21T00:27:52Z","title_canon_sha256":"88e540f8c03f075fd9c002fdb5ef7eadd5e93b09909b6aa74d2098d0edcbcd46"},"schema_version":"1.0","source":{"id":"2002.09072","kind":"arxiv","version":1}},"canonical_sha256":"14c7d376e4f833d92a9ffac6fa3df50d4b18c40636569eb20fb01441c28323dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"14c7d376e4f833d92a9ffac6fa3df50d4b18c40636569eb20fb01441c28323dd","first_computed_at":"2026-07-05T00:42:45.194943Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:42:45.194943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BMKfiAt6Z6bo1hnur4i+MipZtWEITaceqvGKmcsVfJ55GB/iV0EQOSxPh8okUISP/78lH/JvEPRnHdw7wv0zBg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:42:45.195415Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.09072","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09208f515c5fb3e8cd9cc21febceaba2a97bce874a87f51ed57cf0f80708e42c","sha256:c178ad6fbba0b2165080d4c3f44bd7abd5bd8d70af50b65138aad8b750e97f06"],"state_sha256":"8ff4ccbfbf7b481922ba23b19e5ccf5bd624cd851f0c318441de1e0e843d9113"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d3nDm8GHiiqc2PhE8aPItxXtlpdKW24q2Z/D2Q1FmoZ0d7IsIQNkHrEG0wCzlaYi22MUc2pN2XVkwLZ7yiFqBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T21:23:22.033924Z","bundle_sha256":"d315c926a4a580ec50216bfec5dc7d0bde6aa1598e5047a835a498bbfc7b2751"}}