{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:CYPQI57A5NAI75PFQ5ZQUCTBSF","short_pith_number":"pith:CYPQI57A","canonical_record":{"source":{"id":"2204.08957","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-19T15:55:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c95a5ffd03cc5455054578c7f2fbca50b0bcf40a3b70c1b7f252918672472b1f","abstract_canon_sha256":"b365cfaa9f3945a8c8f294741211d97ac5124664c624c1698bce9b386d8f0299"},"schema_version":"1.0"},"canonical_sha256":"161f0477e0eb408ff5e587730a0a619175f216669b75c2f7c291673efa0749ce","source":{"kind":"arxiv","id":"2204.08957","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.08957","created_at":"2026-07-05T04:16:09Z"},{"alias_kind":"arxiv_version","alias_value":"2204.08957v1","created_at":"2026-07-05T04:16:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.08957","created_at":"2026-07-05T04:16:09Z"},{"alias_kind":"pith_short_12","alias_value":"CYPQI57A5NAI","created_at":"2026-07-05T04:16:09Z"},{"alias_kind":"pith_short_16","alias_value":"CYPQI57A5NAI75PF","created_at":"2026-07-05T04:16:09Z"},{"alias_kind":"pith_short_8","alias_value":"CYPQI57A","created_at":"2026-07-05T04:16:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:CYPQI57A5NAI75PFQ5ZQUCTBSF","target":"record","payload":{"canonical_record":{"source":{"id":"2204.08957","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-19T15:55:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c95a5ffd03cc5455054578c7f2fbca50b0bcf40a3b70c1b7f252918672472b1f","abstract_canon_sha256":"b365cfaa9f3945a8c8f294741211d97ac5124664c624c1698bce9b386d8f0299"},"schema_version":"1.0"},"canonical_sha256":"161f0477e0eb408ff5e587730a0a619175f216669b75c2f7c291673efa0749ce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:16:09.385616Z","signature_b64":"o60UyKljIGC44Qd2xsMW005XYDynKjgZlkl3tJmAlZMJQgR/eyUWv8HliUXVPOdiBL3yd9Nrkv7faZwMZlPVBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"161f0477e0eb408ff5e587730a0a619175f216669b75c2f7c291673efa0749ce","last_reissued_at":"2026-07-05T04:16:09.385109Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:16:09.385109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.08957","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":"2026-07-05T04:16:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AqzI7KYf0QV5W+7UbLqe3011d9K7ZUFtUJg7rBB3tQSVO2tF+52jMtvAlRe8kJeqy1rwdTEsstVzjPQjGQROBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T10:33:26.301445Z"},"content_sha256":"207cdd4d18f5a5904650e4235bbb966d387efaae9b57e7bca1ead234cb280fdc","schema_version":"1.0","event_id":"sha256:207cdd4d18f5a5904650e4235bbb966d387efaae9b57e7bca1ead234cb280fdc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:CYPQI57A5NAI75PFQ5ZQUCTBSF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Arthur Guez, Cosmin Paduraru, Daniel J. Mankowitz, Doina Precup, Jongmin Lee, Kee-Eung Kim, Nicolas Heess","submitted_at":"2022-04-19T15:55:47Z","abstract_excerpt":"We consider the offline constrained reinforcement learning (RL) problem, in which the agent aims to compute a policy that maximizes expected return while satisfying given cost constraints, learning only from a pre-collected dataset. This problem setting is appealing in many real-world scenarios, where direct interaction with the environment is costly or risky, and where the resulting policy should comply with safety constraints. However, it is challenging to compute a policy that guarantees satisfying the cost constraints in the offline RL setting, since the off-policy evaluation inherently ha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.08957","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/2204.08957/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":"2026-07-05T04:16:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m/xBNcaeKJaJoxBUp4vZ+HjuW7bcujbQuMM2fmjAf6Gs6QJI0WtRg7RWLsOZTB1MNSS1Lw84hHpMM/B5LPAlCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T10:33:26.302213Z"},"content_sha256":"65576f91a333e9e5d67c3ace52ba56f4eb88d4ee727a91d2501cfe437054c61c","schema_version":"1.0","event_id":"sha256:65576f91a333e9e5d67c3ace52ba56f4eb88d4ee727a91d2501cfe437054c61c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CYPQI57A5NAI75PFQ5ZQUCTBSF/bundle.json","state_url":"https://pith.science/pith/CYPQI57A5NAI75PFQ5ZQUCTBSF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CYPQI57A5NAI75PFQ5ZQUCTBSF/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":"2026-08-18T10:33:26Z","links":{"resolver":"https://pith.science/pith/CYPQI57A5NAI75PFQ5ZQUCTBSF","bundle":"https://pith.science/pith/CYPQI57A5NAI75PFQ5ZQUCTBSF/bundle.json","state":"https://pith.science/pith/CYPQI57A5NAI75PFQ5ZQUCTBSF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CYPQI57A5NAI75PFQ5ZQUCTBSF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CYPQI57A5NAI75PFQ5ZQUCTBSF","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":"b365cfaa9f3945a8c8f294741211d97ac5124664c624c1698bce9b386d8f0299","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-19T15:55:47Z","title_canon_sha256":"c95a5ffd03cc5455054578c7f2fbca50b0bcf40a3b70c1b7f252918672472b1f"},"schema_version":"1.0","source":{"id":"2204.08957","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.08957","created_at":"2026-07-05T04:16:09Z"},{"alias_kind":"arxiv_version","alias_value":"2204.08957v1","created_at":"2026-07-05T04:16:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.08957","created_at":"2026-07-05T04:16:09Z"},{"alias_kind":"pith_short_12","alias_value":"CYPQI57A5NAI","created_at":"2026-07-05T04:16:09Z"},{"alias_kind":"pith_short_16","alias_value":"CYPQI57A5NAI75PF","created_at":"2026-07-05T04:16:09Z"},{"alias_kind":"pith_short_8","alias_value":"CYPQI57A","created_at":"2026-07-05T04:16:09Z"}],"graph_snapshots":[{"event_id":"sha256:65576f91a333e9e5d67c3ace52ba56f4eb88d4ee727a91d2501cfe437054c61c","target":"graph","created_at":"2026-07-05T04:16:09Z","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/2204.08957/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the offline constrained reinforcement learning (RL) problem, in which the agent aims to compute a policy that maximizes expected return while satisfying given cost constraints, learning only from a pre-collected dataset. This problem setting is appealing in many real-world scenarios, where direct interaction with the environment is costly or risky, and where the resulting policy should comply with safety constraints. However, it is challenging to compute a policy that guarantees satisfying the cost constraints in the offline RL setting, since the off-policy evaluation inherently ha","authors_text":"Arthur Guez, Cosmin Paduraru, Daniel J. Mankowitz, Doina Precup, Jongmin Lee, Kee-Eung Kim, Nicolas Heess","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-19T15:55:47Z","title":"COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.08957","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":"sha256:207cdd4d18f5a5904650e4235bbb966d387efaae9b57e7bca1ead234cb280fdc","target":"record","created_at":"2026-07-05T04:16:09Z","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":"b365cfaa9f3945a8c8f294741211d97ac5124664c624c1698bce9b386d8f0299","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-19T15:55:47Z","title_canon_sha256":"c95a5ffd03cc5455054578c7f2fbca50b0bcf40a3b70c1b7f252918672472b1f"},"schema_version":"1.0","source":{"id":"2204.08957","kind":"arxiv","version":1}},"canonical_sha256":"161f0477e0eb408ff5e587730a0a619175f216669b75c2f7c291673efa0749ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"161f0477e0eb408ff5e587730a0a619175f216669b75c2f7c291673efa0749ce","first_computed_at":"2026-07-05T04:16:09.385109Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:16:09.385109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o60UyKljIGC44Qd2xsMW005XYDynKjgZlkl3tJmAlZMJQgR/eyUWv8HliUXVPOdiBL3yd9Nrkv7faZwMZlPVBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:16:09.385616Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.08957","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:207cdd4d18f5a5904650e4235bbb966d387efaae9b57e7bca1ead234cb280fdc","sha256:65576f91a333e9e5d67c3ace52ba56f4eb88d4ee727a91d2501cfe437054c61c"],"state_sha256":"29a3bbdba29eac96dc8ec12e7b8d2c05b1b13fe53868af0c6dfb06c702f0bf8b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t5ef1HASsqvfF574PETOVo5hV3KRa8eumLwChQdoo1BeEk0PdKaSLZKp8S3V9jKY5ixsumnAOC57nQQahs36Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T10:33:26.309628Z","bundle_sha256":"64f1b57bb29ea280020bcc79e2d4f5ed6df250e83f217708a9e861570f60762e"}}