{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:DIOR6XV4RKBHDTKFB4T6CAQHYT","short_pith_number":"pith:DIOR6XV4","canonical_record":{"source":{"id":"2504.05405","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-07T18:19:56Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"caad5bb620c2cd4635d57f4a05769e5857cc427db73a6b7d0b51ecbc3673cd42","abstract_canon_sha256":"be88433ef5c997eb1231ab0c051d6f7bb49e5181e5b5d1e2e3db524b5434026b"},"schema_version":"1.0"},"canonical_sha256":"1a1d1f5ebc8a8271cd450f27e10207c4df27fbc3a8e0b777ba9da3f916121b17","source":{"kind":"arxiv","id":"2504.05405","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.05405","created_at":"2026-07-05T10:45:41Z"},{"alias_kind":"arxiv_version","alias_value":"2504.05405v1","created_at":"2026-07-05T10:45:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.05405","created_at":"2026-07-05T10:45:41Z"},{"alias_kind":"pith_short_12","alias_value":"DIOR6XV4RKBH","created_at":"2026-07-05T10:45:41Z"},{"alias_kind":"pith_short_16","alias_value":"DIOR6XV4RKBHDTKF","created_at":"2026-07-05T10:45:41Z"},{"alias_kind":"pith_short_8","alias_value":"DIOR6XV4","created_at":"2026-07-05T10:45:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:DIOR6XV4RKBHDTKFB4T6CAQHYT","target":"record","payload":{"canonical_record":{"source":{"id":"2504.05405","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-07T18:19:56Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"caad5bb620c2cd4635d57f4a05769e5857cc427db73a6b7d0b51ecbc3673cd42","abstract_canon_sha256":"be88433ef5c997eb1231ab0c051d6f7bb49e5181e5b5d1e2e3db524b5434026b"},"schema_version":"1.0"},"canonical_sha256":"1a1d1f5ebc8a8271cd450f27e10207c4df27fbc3a8e0b777ba9da3f916121b17","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:41.718441Z","signature_b64":"eVcV7zP2LXXezLYfCJTJNqDRddEZMpAYtpB3t67jDtI0YDAxy27/aQ9VX+YFvvcTVovlf2ckMhaNbLX9e6d9Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a1d1f5ebc8a8271cd450f27e10207c4df27fbc3a8e0b777ba9da3f916121b17","last_reissued_at":"2026-07-05T10:45:41.717910Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:41.717910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.05405","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":"2026-07-05T10:45:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/LHkKW9gKi9mkHNw2bWVOZ6YdfjETFDWdS+rinLNqlHKt654BjoPjctNkjV/FNvP+SWl3p4w0SnN7Q8Rtba4Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T10:48:10.903364Z"},"content_sha256":"6fe64f9cd779c3ca822f1b4e9a6a0d31ea5f426ae92f54a5489a6aac54558950","schema_version":"1.0","event_id":"sha256:6fe64f9cd779c3ca822f1b4e9a6a0d31ea5f426ae92f54a5489a6aac54558950"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:DIOR6XV4RKBHDTKFB4T6CAQHYT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Role of Environment Access in Agnostic Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Akshay Krishnamurthy, Ayush Sekhari, Gene Li","submitted_at":"2025-04-07T18:19:56Z","abstract_excerpt":"We study Reinforcement Learning (RL) in environments with large state spaces, where function approximation is required for sample-efficient learning. Departing from a long history of prior work, we consider the weakest possible form of function approximation, called agnostic policy learning, where the learner seeks to find the best policy in a given class $\\Pi$, with no guarantee that $\\Pi$ contains an optimal policy for the underlying task. Although it is known that sample-efficient agnostic policy learning is not possible in the standard online RL setting without further assumptions, we inve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.05405","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/2504.05405/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":"2026-07-05T10:45:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xo04O8U8dJrY89rNM9+vF7nU4gnWF4nhQevJAYgZ+Yxpn5Hd4qUZl1KdL1Fc8PQ9SzlVhYQdNp9OmF9+xWGkCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T10:48:10.905557Z"},"content_sha256":"810884003bce8f8b851876a94dfd8081ceb33de5c676abedfee1ecb4ff5adc9f","schema_version":"1.0","event_id":"sha256:810884003bce8f8b851876a94dfd8081ceb33de5c676abedfee1ecb4ff5adc9f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DIOR6XV4RKBHDTKFB4T6CAQHYT/bundle.json","state_url":"https://pith.science/pith/DIOR6XV4RKBHDTKFB4T6CAQHYT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DIOR6XV4RKBHDTKFB4T6CAQHYT/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":"2026-08-11T10:48:10Z","links":{"resolver":"https://pith.science/pith/DIOR6XV4RKBHDTKFB4T6CAQHYT","bundle":"https://pith.science/pith/DIOR6XV4RKBHDTKFB4T6CAQHYT/bundle.json","state":"https://pith.science/pith/DIOR6XV4RKBHDTKFB4T6CAQHYT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DIOR6XV4RKBHDTKFB4T6CAQHYT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DIOR6XV4RKBHDTKFB4T6CAQHYT","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":"be88433ef5c997eb1231ab0c051d6f7bb49e5181e5b5d1e2e3db524b5434026b","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-07T18:19:56Z","title_canon_sha256":"caad5bb620c2cd4635d57f4a05769e5857cc427db73a6b7d0b51ecbc3673cd42"},"schema_version":"1.0","source":{"id":"2504.05405","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.05405","created_at":"2026-07-05T10:45:41Z"},{"alias_kind":"arxiv_version","alias_value":"2504.05405v1","created_at":"2026-07-05T10:45:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.05405","created_at":"2026-07-05T10:45:41Z"},{"alias_kind":"pith_short_12","alias_value":"DIOR6XV4RKBH","created_at":"2026-07-05T10:45:41Z"},{"alias_kind":"pith_short_16","alias_value":"DIOR6XV4RKBHDTKF","created_at":"2026-07-05T10:45:41Z"},{"alias_kind":"pith_short_8","alias_value":"DIOR6XV4","created_at":"2026-07-05T10:45:41Z"}],"graph_snapshots":[{"event_id":"sha256:810884003bce8f8b851876a94dfd8081ceb33de5c676abedfee1ecb4ff5adc9f","target":"graph","created_at":"2026-07-05T10:45:41Z","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/2504.05405/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study Reinforcement Learning (RL) in environments with large state spaces, where function approximation is required for sample-efficient learning. Departing from a long history of prior work, we consider the weakest possible form of function approximation, called agnostic policy learning, where the learner seeks to find the best policy in a given class $\\Pi$, with no guarantee that $\\Pi$ contains an optimal policy for the underlying task. Although it is known that sample-efficient agnostic policy learning is not possible in the standard online RL setting without further assumptions, we inve","authors_text":"Akshay Krishnamurthy, Ayush Sekhari, Gene Li","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-07T18:19:56Z","title":"The Role of Environment Access in Agnostic Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.05405","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":"sha256:6fe64f9cd779c3ca822f1b4e9a6a0d31ea5f426ae92f54a5489a6aac54558950","target":"record","created_at":"2026-07-05T10:45:41Z","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":"be88433ef5c997eb1231ab0c051d6f7bb49e5181e5b5d1e2e3db524b5434026b","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-07T18:19:56Z","title_canon_sha256":"caad5bb620c2cd4635d57f4a05769e5857cc427db73a6b7d0b51ecbc3673cd42"},"schema_version":"1.0","source":{"id":"2504.05405","kind":"arxiv","version":1}},"canonical_sha256":"1a1d1f5ebc8a8271cd450f27e10207c4df27fbc3a8e0b777ba9da3f916121b17","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a1d1f5ebc8a8271cd450f27e10207c4df27fbc3a8e0b777ba9da3f916121b17","first_computed_at":"2026-07-05T10:45:41.717910Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:45:41.717910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eVcV7zP2LXXezLYfCJTJNqDRddEZMpAYtpB3t67jDtI0YDAxy27/aQ9VX+YFvvcTVovlf2ckMhaNbLX9e6d9Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:45:41.718441Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.05405","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6fe64f9cd779c3ca822f1b4e9a6a0d31ea5f426ae92f54a5489a6aac54558950","sha256:810884003bce8f8b851876a94dfd8081ceb33de5c676abedfee1ecb4ff5adc9f"],"state_sha256":"3d7755ed78e377c2b8c69eceba5530f779acd2c2aa0f0d5d4934ef1e6ad352f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oJhkQYGth47P3CRryRHZ5Ka6GcfO8djBSDNf2aC2wrmyEs7aJTutgrOif6EK5ROaJfNcqEUzHbtyWfTjeuHBAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T10:48:10.922448Z","bundle_sha256":"315173029e58445d2371548695ce0207a48a74182a1cfd2d7240a0b3bafe31ac"}}