{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GJSI57FHVPFCEI4RU7CQCU5SNS","short_pith_number":"pith:GJSI57FH","canonical_record":{"source":{"id":"2506.01884","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T17:12:24Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"080e976aa11d24596252db01cd9ab9260b1d9f7e9f6c98b4ff8651aa0e219e01","abstract_canon_sha256":"15b69076edc57f2f9175b29ccd80b10c3df0b12704058d782588ccbf36a82608"},"schema_version":"1.0"},"canonical_sha256":"32648efca7abca222391a7c50153b26cb54aee747f4c771989d0b67fc98fecef","source":{"kind":"arxiv","id":"2506.01884","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01884","created_at":"2026-07-05T11:14:20Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01884v1","created_at":"2026-07-05T11:14:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01884","created_at":"2026-07-05T11:14:20Z"},{"alias_kind":"pith_short_12","alias_value":"GJSI57FHVPFC","created_at":"2026-07-05T11:14:20Z"},{"alias_kind":"pith_short_16","alias_value":"GJSI57FHVPFCEI4R","created_at":"2026-07-05T11:14:20Z"},{"alias_kind":"pith_short_8","alias_value":"GJSI57FH","created_at":"2026-07-05T11:14:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GJSI57FHVPFCEI4RU7CQCU5SNS","target":"record","payload":{"canonical_record":{"source":{"id":"2506.01884","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T17:12:24Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"080e976aa11d24596252db01cd9ab9260b1d9f7e9f6c98b4ff8651aa0e219e01","abstract_canon_sha256":"15b69076edc57f2f9175b29ccd80b10c3df0b12704058d782588ccbf36a82608"},"schema_version":"1.0"},"canonical_sha256":"32648efca7abca222391a7c50153b26cb54aee747f4c771989d0b67fc98fecef","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:20.843098Z","signature_b64":"Dn7P3dYqVE0wWqWhBVDGNeBw4Rxkg0QQA33H4OmBJKzyQwDMoWqVZxe6u6oK9JM+AUyqkzifrZFczsyr5Lg6Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32648efca7abca222391a7c50153b26cb54aee747f4c771989d0b67fc98fecef","last_reissued_at":"2026-07-05T11:14:20.842629Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:20.842629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.01884","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":"2026-07-05T11:14:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+ExkxCxKAZFn4TZK9FjRx74V9w+ToIVeHKJuFap3nVu9Eyq335OpFo+CJptRW6C5lwhGA0Qu0339164xpYyBDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T06:30:47.211474Z"},"content_sha256":"ce5bb56a0ddc05aa303342b4f1e556e03fcbd29508a4bd6a567bc029918dfc4f","schema_version":"1.0","event_id":"sha256:ce5bb56a0ddc05aa303342b4f1e556e03fcbd29508a4bd6a567bc029918dfc4f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GJSI57FHVPFCEI4RU7CQCU5SNS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Agnostic Reinforcement Learning: Foundations and Algorithms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gene Li","submitted_at":"2025-06-02T17:12:24Z","abstract_excerpt":"Reinforcement Learning (RL) has demonstrated tremendous empirical success across numerous challenging domains. However, we lack a strong theoretical understanding of the statistical complexity of RL in environments with large state spaces, where function approximation is required for sample-efficient learning. This thesis addresses this gap by rigorously examining the statistical complexity of RL with function approximation from a learning theoretic perspective. Departing from a long history of prior work, we consider the weakest form of function approximation, called agnostic policy learning,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01884","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/2506.01884/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":"2026-07-05T11:14:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AmnyOo2ZgEw34eziQWif8AL+KYAdL4r7EcqWpjvbp/6K9N42COrRwLm5z6cN83LUwmls7u3hKBY+JWkgWzXrAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T06:30:47.211990Z"},"content_sha256":"1c60a9bad1807dd1cb7c9b0f92bd9b1be659de0f9f3d60db7fbaa94f15322424","schema_version":"1.0","event_id":"sha256:1c60a9bad1807dd1cb7c9b0f92bd9b1be659de0f9f3d60db7fbaa94f15322424"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GJSI57FHVPFCEI4RU7CQCU5SNS/bundle.json","state_url":"https://pith.science/pith/GJSI57FHVPFCEI4RU7CQCU5SNS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GJSI57FHVPFCEI4RU7CQCU5SNS/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":"2026-08-23T06:30:47Z","links":{"resolver":"https://pith.science/pith/GJSI57FHVPFCEI4RU7CQCU5SNS","bundle":"https://pith.science/pith/GJSI57FHVPFCEI4RU7CQCU5SNS/bundle.json","state":"https://pith.science/pith/GJSI57FHVPFCEI4RU7CQCU5SNS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GJSI57FHVPFCEI4RU7CQCU5SNS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GJSI57FHVPFCEI4RU7CQCU5SNS","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":"15b69076edc57f2f9175b29ccd80b10c3df0b12704058d782588ccbf36a82608","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T17:12:24Z","title_canon_sha256":"080e976aa11d24596252db01cd9ab9260b1d9f7e9f6c98b4ff8651aa0e219e01"},"schema_version":"1.0","source":{"id":"2506.01884","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01884","created_at":"2026-07-05T11:14:20Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01884v1","created_at":"2026-07-05T11:14:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01884","created_at":"2026-07-05T11:14:20Z"},{"alias_kind":"pith_short_12","alias_value":"GJSI57FHVPFC","created_at":"2026-07-05T11:14:20Z"},{"alias_kind":"pith_short_16","alias_value":"GJSI57FHVPFCEI4R","created_at":"2026-07-05T11:14:20Z"},{"alias_kind":"pith_short_8","alias_value":"GJSI57FH","created_at":"2026-07-05T11:14:20Z"}],"graph_snapshots":[{"event_id":"sha256:1c60a9bad1807dd1cb7c9b0f92bd9b1be659de0f9f3d60db7fbaa94f15322424","target":"graph","created_at":"2026-07-05T11:14:20Z","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/2506.01884/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) has demonstrated tremendous empirical success across numerous challenging domains. However, we lack a strong theoretical understanding of the statistical complexity of RL in environments with large state spaces, where function approximation is required for sample-efficient learning. This thesis addresses this gap by rigorously examining the statistical complexity of RL with function approximation from a learning theoretic perspective. Departing from a long history of prior work, we consider the weakest form of function approximation, called agnostic policy learning,","authors_text":"Gene Li","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T17:12:24Z","title":"Agnostic Reinforcement Learning: Foundations and Algorithms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01884","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:ce5bb56a0ddc05aa303342b4f1e556e03fcbd29508a4bd6a567bc029918dfc4f","target":"record","created_at":"2026-07-05T11:14:20Z","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":"15b69076edc57f2f9175b29ccd80b10c3df0b12704058d782588ccbf36a82608","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T17:12:24Z","title_canon_sha256":"080e976aa11d24596252db01cd9ab9260b1d9f7e9f6c98b4ff8651aa0e219e01"},"schema_version":"1.0","source":{"id":"2506.01884","kind":"arxiv","version":1}},"canonical_sha256":"32648efca7abca222391a7c50153b26cb54aee747f4c771989d0b67fc98fecef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32648efca7abca222391a7c50153b26cb54aee747f4c771989d0b67fc98fecef","first_computed_at":"2026-07-05T11:14:20.842629Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:20.842629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Dn7P3dYqVE0wWqWhBVDGNeBw4Rxkg0QQA33H4OmBJKzyQwDMoWqVZxe6u6oK9JM+AUyqkzifrZFczsyr5Lg6Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:20.843098Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.01884","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce5bb56a0ddc05aa303342b4f1e556e03fcbd29508a4bd6a567bc029918dfc4f","sha256:1c60a9bad1807dd1cb7c9b0f92bd9b1be659de0f9f3d60db7fbaa94f15322424"],"state_sha256":"98d0ebbcc8bfa5736881d91f7cb864e89049225a004b8dcb5aeb67520a4288fd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WvQ08lNrbJtbCtZm+iWYXafq6tyJgk9+8XBxOGdKw8vfDK1tOCLAyRcUGSLHnZdZBovl+qg8d5r492WrcTlBAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T06:30:47.216444Z","bundle_sha256":"4ad892d8c031036f0e7bc1979faeb695dbfae10948e91d4d67eac84864b623cd"}}