{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:75DQNYG5ASGEEEOYKK7JHY4EFN","short_pith_number":"pith:75DQNYG5","canonical_record":{"source":{"id":"2207.06147","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-13T12:13:38Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"682211d1db1fd72557f2eb36c7039587ab6f9058d025b64b2626d13dff91ed48","abstract_canon_sha256":"21ac3244f2f9af4aa20fc610f2ed75fb28cfdd2a9d897793ff4070dbbd1dec31"},"schema_version":"1.0"},"canonical_sha256":"ff4706e0dd048c4211d852be93e3842b672868b950604690aa036e3cbb1eb7ab","source":{"kind":"arxiv","id":"2207.06147","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.06147","created_at":"2026-07-05T04:40:02Z"},{"alias_kind":"arxiv_version","alias_value":"2207.06147v1","created_at":"2026-07-05T04:40:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.06147","created_at":"2026-07-05T04:40:02Z"},{"alias_kind":"pith_short_12","alias_value":"75DQNYG5ASGE","created_at":"2026-07-05T04:40:02Z"},{"alias_kind":"pith_short_16","alias_value":"75DQNYG5ASGEEEOY","created_at":"2026-07-05T04:40:02Z"},{"alias_kind":"pith_short_8","alias_value":"75DQNYG5","created_at":"2026-07-05T04:40:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:75DQNYG5ASGEEEOYKK7JHY4EFN","target":"record","payload":{"canonical_record":{"source":{"id":"2207.06147","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-13T12:13:38Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"682211d1db1fd72557f2eb36c7039587ab6f9058d025b64b2626d13dff91ed48","abstract_canon_sha256":"21ac3244f2f9af4aa20fc610f2ed75fb28cfdd2a9d897793ff4070dbbd1dec31"},"schema_version":"1.0"},"canonical_sha256":"ff4706e0dd048c4211d852be93e3842b672868b950604690aa036e3cbb1eb7ab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:40:02.202835Z","signature_b64":"iCbxq3vYqdxqM9uk0n9sxzNIk4MtRvpLxrXp7L4IzTJF1Ea2DGSbybmsfygBQ3XJw6dnlKAAdKw+FLeFnFbpCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff4706e0dd048c4211d852be93e3842b672868b950604690aa036e3cbb1eb7ab","last_reissued_at":"2026-07-05T04:40:02.202394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:40:02.202394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.06147","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":"2026-07-05T04:40:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YXLRUbYrYJWtue8gQnIfkC+/11L/5UqbzAlYiFLv9qO+8qo6uEUuocgrpYe8Oz/i2JbB/5Qw+nWaYZ5m4BD+AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T22:51:14.293764Z"},"content_sha256":"7a25419852154ab86df55f532d76cf55eb9966205fc1c7058fa53f5227cc907e","schema_version":"1.0","event_id":"sha256:7a25419852154ab86df55f532d76cf55eb9966205fc1c7058fa53f5227cc907e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:75DQNYG5ASGEEEOYKK7JHY4EFN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Near-Optimal Primal-Dual Method for Off-Policy Learning in CMDP","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fan Chen, Junyu Zhang, Zaiwen Wen","submitted_at":"2022-07-13T12:13:38Z","abstract_excerpt":"As an important framework for safe Reinforcement Learning, the Constrained Markov Decision Process (CMDP) has been extensively studied in the recent literature. However, despite the rich results under various on-policy learning settings, there still lacks some essential understanding of the offline CMDP problems, in terms of both the algorithm design and the information theoretic sample complexity lower bound. In this paper, we focus on solving the CMDP problems where only offline data are available. By adopting the concept of the single-policy concentrability coefficient $C^*$, we establish a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.06147","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/2207.06147/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":"2026-07-05T04:40:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fCBC6az7wnuOeIFObcHXz2ZhMEnYmap79GeCihVKp7GSkWvdqC1+JTTPcNaq1sMcUGMEhkxPSFdqacTBl4WXAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T22:51:14.294570Z"},"content_sha256":"58d142b287f545769bf131de938585b3acbfafc1720a509f970ee63fba4576d1","schema_version":"1.0","event_id":"sha256:58d142b287f545769bf131de938585b3acbfafc1720a509f970ee63fba4576d1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/75DQNYG5ASGEEEOYKK7JHY4EFN/bundle.json","state_url":"https://pith.science/pith/75DQNYG5ASGEEEOYKK7JHY4EFN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/75DQNYG5ASGEEEOYKK7JHY4EFN/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":"2026-08-19T22:51:14Z","links":{"resolver":"https://pith.science/pith/75DQNYG5ASGEEEOYKK7JHY4EFN","bundle":"https://pith.science/pith/75DQNYG5ASGEEEOYKK7JHY4EFN/bundle.json","state":"https://pith.science/pith/75DQNYG5ASGEEEOYKK7JHY4EFN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/75DQNYG5ASGEEEOYKK7JHY4EFN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:75DQNYG5ASGEEEOYKK7JHY4EFN","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":"21ac3244f2f9af4aa20fc610f2ed75fb28cfdd2a9d897793ff4070dbbd1dec31","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-13T12:13:38Z","title_canon_sha256":"682211d1db1fd72557f2eb36c7039587ab6f9058d025b64b2626d13dff91ed48"},"schema_version":"1.0","source":{"id":"2207.06147","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.06147","created_at":"2026-07-05T04:40:02Z"},{"alias_kind":"arxiv_version","alias_value":"2207.06147v1","created_at":"2026-07-05T04:40:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.06147","created_at":"2026-07-05T04:40:02Z"},{"alias_kind":"pith_short_12","alias_value":"75DQNYG5ASGE","created_at":"2026-07-05T04:40:02Z"},{"alias_kind":"pith_short_16","alias_value":"75DQNYG5ASGEEEOY","created_at":"2026-07-05T04:40:02Z"},{"alias_kind":"pith_short_8","alias_value":"75DQNYG5","created_at":"2026-07-05T04:40:02Z"}],"graph_snapshots":[{"event_id":"sha256:58d142b287f545769bf131de938585b3acbfafc1720a509f970ee63fba4576d1","target":"graph","created_at":"2026-07-05T04:40:02Z","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/2207.06147/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As an important framework for safe Reinforcement Learning, the Constrained Markov Decision Process (CMDP) has been extensively studied in the recent literature. However, despite the rich results under various on-policy learning settings, there still lacks some essential understanding of the offline CMDP problems, in terms of both the algorithm design and the information theoretic sample complexity lower bound. In this paper, we focus on solving the CMDP problems where only offline data are available. By adopting the concept of the single-policy concentrability coefficient $C^*$, we establish a","authors_text":"Fan Chen, Junyu Zhang, Zaiwen Wen","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-13T12:13:38Z","title":"A Near-Optimal Primal-Dual Method for Off-Policy Learning in CMDP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.06147","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":"sha256:7a25419852154ab86df55f532d76cf55eb9966205fc1c7058fa53f5227cc907e","target":"record","created_at":"2026-07-05T04:40:02Z","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":"21ac3244f2f9af4aa20fc610f2ed75fb28cfdd2a9d897793ff4070dbbd1dec31","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-13T12:13:38Z","title_canon_sha256":"682211d1db1fd72557f2eb36c7039587ab6f9058d025b64b2626d13dff91ed48"},"schema_version":"1.0","source":{"id":"2207.06147","kind":"arxiv","version":1}},"canonical_sha256":"ff4706e0dd048c4211d852be93e3842b672868b950604690aa036e3cbb1eb7ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff4706e0dd048c4211d852be93e3842b672868b950604690aa036e3cbb1eb7ab","first_computed_at":"2026-07-05T04:40:02.202394Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:40:02.202394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iCbxq3vYqdxqM9uk0n9sxzNIk4MtRvpLxrXp7L4IzTJF1Ea2DGSbybmsfygBQ3XJw6dnlKAAdKw+FLeFnFbpCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:40:02.202835Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.06147","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a25419852154ab86df55f532d76cf55eb9966205fc1c7058fa53f5227cc907e","sha256:58d142b287f545769bf131de938585b3acbfafc1720a509f970ee63fba4576d1"],"state_sha256":"936ee953f22b307e0b7b51d06b34a448754746d674c19931601d994a2075c94e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dqB0g/GKqz++SIt20DA5zyAQ+lPzHXkBw1XtdMrSxXQM4P88IRCSOQnfYTtX0G2OKGpGW7Q+0yfwKS2c8dHECQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T22:51:14.300817Z","bundle_sha256":"6458347a871931dfcbbcb802660006704e2dc98c2dcbf38b6875c51ebacf654d"}}