{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VF5TYRKLDYFMBI5VB2NYTVS47N","short_pith_number":"pith:VF5TYRKL","canonical_record":{"source":{"id":"2311.08384","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-14T18:45:56Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"a05e3bfa5c4fa897edbbd66e7aaabbef2bfa769d345659e98a0308e5e5bacdc5","abstract_canon_sha256":"262a35e5be7518e8f9c98d02f875c7967acb7277bc346b9ea5594763a3646f22"},"schema_version":"1.0"},"canonical_sha256":"a97b3c454b1e0ac0a3b50e9b89d65cfb427831c8a93836362f572e3a18e19ee9","source":{"kind":"arxiv","id":"2311.08384","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.08384","created_at":"2026-07-05T07:12:44Z"},{"alias_kind":"arxiv_version","alias_value":"2311.08384v1","created_at":"2026-07-05T07:12:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08384","created_at":"2026-07-05T07:12:44Z"},{"alias_kind":"pith_short_12","alias_value":"VF5TYRKLDYFM","created_at":"2026-07-05T07:12:44Z"},{"alias_kind":"pith_short_16","alias_value":"VF5TYRKLDYFMBI5V","created_at":"2026-07-05T07:12:44Z"},{"alias_kind":"pith_short_8","alias_value":"VF5TYRKL","created_at":"2026-07-05T07:12:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VF5TYRKLDYFMBI5VB2NYTVS47N","target":"record","payload":{"canonical_record":{"source":{"id":"2311.08384","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-14T18:45:56Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"a05e3bfa5c4fa897edbbd66e7aaabbef2bfa769d345659e98a0308e5e5bacdc5","abstract_canon_sha256":"262a35e5be7518e8f9c98d02f875c7967acb7277bc346b9ea5594763a3646f22"},"schema_version":"1.0"},"canonical_sha256":"a97b3c454b1e0ac0a3b50e9b89d65cfb427831c8a93836362f572e3a18e19ee9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:44.444047Z","signature_b64":"Gt2f1Bo7/D0a74ip2VNATjICkj+LRI4A5tEnukZcdFddzqCYqzCVSzHNjYDeKeeQhBAcXzp9MznzHkQw6KlACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a97b3c454b1e0ac0a3b50e9b89d65cfb427831c8a93836362f572e3a18e19ee9","last_reissued_at":"2026-07-05T07:12:44.443557Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:44.443557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.08384","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":"2026-07-05T07:12:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"La07q2DAerW9X3P4GozMT3GNfNK9mYq6XwRNjlxqwfklPwKORkg1kh1EDUeNDiVLhG68XjnjnNQIkcyCthTNAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T05:49:31.424598Z"},"content_sha256":"d94067c02a107ed05b65199eff448ca24f6dfc89ee97e052ca09e60dbab706f3","schema_version":"1.0","event_id":"sha256:d94067c02a107ed05b65199eff448ca24f6dfc89ee97e052ca09e60dbab706f3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VF5TYRKLDYFMBI5VB2NYTVS47N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ayush Sekhari, Wen Sun, Yifei Zhou, Yuda Song","submitted_at":"2023-11-14T18:45:56Z","abstract_excerpt":"Hybrid RL is the setting where an RL agent has access to both offline data and online data by interacting with the real-world environment. In this work, we propose a new hybrid RL algorithm that combines an on-policy actor-critic method with offline data. On-policy methods such as policy gradient and natural policy gradient (NPG) have shown to be more robust to model misspecification, though sometimes it may not be as sample efficient as methods that rely on off-policy learning. On the other hand, offline methods that depend on off-policy training often require strong assumptions in theory and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08384","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/2311.08384/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":"2026-07-05T07:12:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uFjN+a/5sTBhI13t3CRgxZNyfOoElh3V4GlddPM9lSezvWooTus8CvniAwHBCcUUe5hI/YPUpmWRML05tz1SDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T05:49:31.424976Z"},"content_sha256":"f50bea93cecb8c6b8fe7f7eca4ff9c9dea8c9d39c29bd36844eeb34c1c4e7316","schema_version":"1.0","event_id":"sha256:f50bea93cecb8c6b8fe7f7eca4ff9c9dea8c9d39c29bd36844eeb34c1c4e7316"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VF5TYRKLDYFMBI5VB2NYTVS47N/bundle.json","state_url":"https://pith.science/pith/VF5TYRKLDYFMBI5VB2NYTVS47N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VF5TYRKLDYFMBI5VB2NYTVS47N/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":"2026-07-27T05:49:31Z","links":{"resolver":"https://pith.science/pith/VF5TYRKLDYFMBI5VB2NYTVS47N","bundle":"https://pith.science/pith/VF5TYRKLDYFMBI5VB2NYTVS47N/bundle.json","state":"https://pith.science/pith/VF5TYRKLDYFMBI5VB2NYTVS47N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VF5TYRKLDYFMBI5VB2NYTVS47N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VF5TYRKLDYFMBI5VB2NYTVS47N","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":"262a35e5be7518e8f9c98d02f875c7967acb7277bc346b9ea5594763a3646f22","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-14T18:45:56Z","title_canon_sha256":"a05e3bfa5c4fa897edbbd66e7aaabbef2bfa769d345659e98a0308e5e5bacdc5"},"schema_version":"1.0","source":{"id":"2311.08384","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.08384","created_at":"2026-07-05T07:12:44Z"},{"alias_kind":"arxiv_version","alias_value":"2311.08384v1","created_at":"2026-07-05T07:12:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08384","created_at":"2026-07-05T07:12:44Z"},{"alias_kind":"pith_short_12","alias_value":"VF5TYRKLDYFM","created_at":"2026-07-05T07:12:44Z"},{"alias_kind":"pith_short_16","alias_value":"VF5TYRKLDYFMBI5V","created_at":"2026-07-05T07:12:44Z"},{"alias_kind":"pith_short_8","alias_value":"VF5TYRKL","created_at":"2026-07-05T07:12:44Z"}],"graph_snapshots":[{"event_id":"sha256:f50bea93cecb8c6b8fe7f7eca4ff9c9dea8c9d39c29bd36844eeb34c1c4e7316","target":"graph","created_at":"2026-07-05T07:12:44Z","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/2311.08384/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hybrid RL is the setting where an RL agent has access to both offline data and online data by interacting with the real-world environment. In this work, we propose a new hybrid RL algorithm that combines an on-policy actor-critic method with offline data. On-policy methods such as policy gradient and natural policy gradient (NPG) have shown to be more robust to model misspecification, though sometimes it may not be as sample efficient as methods that rely on off-policy learning. On the other hand, offline methods that depend on off-policy training often require strong assumptions in theory and","authors_text":"Ayush Sekhari, Wen Sun, Yifei Zhou, Yuda Song","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-14T18:45:56Z","title":"Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08384","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:d94067c02a107ed05b65199eff448ca24f6dfc89ee97e052ca09e60dbab706f3","target":"record","created_at":"2026-07-05T07:12:44Z","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":"262a35e5be7518e8f9c98d02f875c7967acb7277bc346b9ea5594763a3646f22","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-14T18:45:56Z","title_canon_sha256":"a05e3bfa5c4fa897edbbd66e7aaabbef2bfa769d345659e98a0308e5e5bacdc5"},"schema_version":"1.0","source":{"id":"2311.08384","kind":"arxiv","version":1}},"canonical_sha256":"a97b3c454b1e0ac0a3b50e9b89d65cfb427831c8a93836362f572e3a18e19ee9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a97b3c454b1e0ac0a3b50e9b89d65cfb427831c8a93836362f572e3a18e19ee9","first_computed_at":"2026-07-05T07:12:44.443557Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:12:44.443557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gt2f1Bo7/D0a74ip2VNATjICkj+LRI4A5tEnukZcdFddzqCYqzCVSzHNjYDeKeeQhBAcXzp9MznzHkQw6KlACg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:12:44.444047Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.08384","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d94067c02a107ed05b65199eff448ca24f6dfc89ee97e052ca09e60dbab706f3","sha256:f50bea93cecb8c6b8fe7f7eca4ff9c9dea8c9d39c29bd36844eeb34c1c4e7316"],"state_sha256":"c5adf89afadd5934218a7e6aed75923f33820c96fbe210d9539036ce0bf75319"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xiB9ebfVZZWohlHAV9tvQXRKAE2NvK6TEiUHEaN1V4Zi4QTjQoYJd7lUCBO+AA9czS9jCx4gorgPpehx21EUBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-27T05:49:31.427490Z","bundle_sha256":"44ec5eef48c3229fb73440c7c9bf9cc7adc0a1b530880dd24dc72f13b467cb13"}}