{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HEX5BNQ34AYUCXN2R6YE5RVX4J","short_pith_number":"pith:HEX5BNQ3","canonical_record":{"source":{"id":"2403.09701","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-07T19:39:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9f353ec5e73c11e8ed005e6e877283337bf93d8b92307ba92e97b30d2d5d6df1","abstract_canon_sha256":"a149b1d12efe5d0084cc6a3a618cf8960d148d2059f6118842b6620768f90631"},"schema_version":"1.0"},"canonical_sha256":"392fd0b61be031415dba8fb04ec6b7e26640ea6e30c34471a6e5ddb53bc6ecc1","source":{"kind":"arxiv","id":"2403.09701","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.09701","created_at":"2026-07-05T07:57:02Z"},{"alias_kind":"arxiv_version","alias_value":"2403.09701v2","created_at":"2026-07-05T07:57:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09701","created_at":"2026-07-05T07:57:02Z"},{"alias_kind":"pith_short_12","alias_value":"HEX5BNQ34AYU","created_at":"2026-07-05T07:57:02Z"},{"alias_kind":"pith_short_16","alias_value":"HEX5BNQ34AYUCXN2","created_at":"2026-07-05T07:57:02Z"},{"alias_kind":"pith_short_8","alias_value":"HEX5BNQ3","created_at":"2026-07-05T07:57:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HEX5BNQ34AYUCXN2R6YE5RVX4J","target":"record","payload":{"canonical_record":{"source":{"id":"2403.09701","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-07T19:39:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9f353ec5e73c11e8ed005e6e877283337bf93d8b92307ba92e97b30d2d5d6df1","abstract_canon_sha256":"a149b1d12efe5d0084cc6a3a618cf8960d148d2059f6118842b6620768f90631"},"schema_version":"1.0"},"canonical_sha256":"392fd0b61be031415dba8fb04ec6b7e26640ea6e30c34471a6e5ddb53bc6ecc1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:02.470542Z","signature_b64":"Dt6mXKLU4YrLqk6CM7rEiJmsTrX7dV/ug8kJmEO7hs6+FXibVYKHQxLkUW9QJGj0kA3DTY8c10vPwHsGO1vPAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"392fd0b61be031415dba8fb04ec6b7e26640ea6e30c34471a6e5ddb53bc6ecc1","last_reissued_at":"2026-07-05T07:57:02.470064Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:02.470064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.09701","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:57:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I1uhdCesH+jRcOK2EGjdbkk+K9bz0b0njeOt19041VrDiydKqYeHSaRp3OTOFW2zp4XByiI2yh79AC407cx1CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:54:33.441037Z"},"content_sha256":"4fe7800abc5b52bd2b21400ac46430388ef7c00da81674c8060696f073aa328d","schema_version":"1.0","event_id":"sha256:4fe7800abc5b52bd2b21400ac46430388ef7c00da81674c8060696f073aa328d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HEX5BNQ34AYUCXN2R6YE5RVX4J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Natural Extension To Online Algorithms For Hybrid RL With Limited Coverage","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kevin Tan, Ziping Xu","submitted_at":"2024-03-07T19:39:47Z","abstract_excerpt":"Hybrid Reinforcement Learning (RL), leveraging both online and offline data, has garnered recent interest, yet research on its provable benefits remains sparse. Additionally, many existing hybrid RL algorithms (Song et al., 2023; Nakamoto et al., 2023; Amortila et al., 2024) impose coverage assumptions on the offline dataset, but we show that this is unnecessary. A well-designed online algorithm should \"fill in the gaps\" in the offline dataset, exploring states and actions that the behavior policy did not explore. Unlike previous approaches that focus on estimating the offline data distributio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09701","kind":"arxiv","version":2},"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/2403.09701/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":"2026-07-05T07:57:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nf3bjwTD7lh2d0taZopgB9eIWT49570FwOxSy9IPFkxAUcoDQlTaBBOyM/UPmEnUdwFh0FK6pQOB7KnyClCiDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:54:33.441516Z"},"content_sha256":"6c8dee14e1d2057f8bb1954314563a539199f2f366e9f9b357fd2da21c40e77e","schema_version":"1.0","event_id":"sha256:6c8dee14e1d2057f8bb1954314563a539199f2f366e9f9b357fd2da21c40e77e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HEX5BNQ34AYUCXN2R6YE5RVX4J/bundle.json","state_url":"https://pith.science/pith/HEX5BNQ34AYUCXN2R6YE5RVX4J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HEX5BNQ34AYUCXN2R6YE5RVX4J/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":"2026-08-18T18:54:33Z","links":{"resolver":"https://pith.science/pith/HEX5BNQ34AYUCXN2R6YE5RVX4J","bundle":"https://pith.science/pith/HEX5BNQ34AYUCXN2R6YE5RVX4J/bundle.json","state":"https://pith.science/pith/HEX5BNQ34AYUCXN2R6YE5RVX4J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HEX5BNQ34AYUCXN2R6YE5RVX4J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HEX5BNQ34AYUCXN2R6YE5RVX4J","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":"a149b1d12efe5d0084cc6a3a618cf8960d148d2059f6118842b6620768f90631","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-07T19:39:47Z","title_canon_sha256":"9f353ec5e73c11e8ed005e6e877283337bf93d8b92307ba92e97b30d2d5d6df1"},"schema_version":"1.0","source":{"id":"2403.09701","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.09701","created_at":"2026-07-05T07:57:02Z"},{"alias_kind":"arxiv_version","alias_value":"2403.09701v2","created_at":"2026-07-05T07:57:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09701","created_at":"2026-07-05T07:57:02Z"},{"alias_kind":"pith_short_12","alias_value":"HEX5BNQ34AYU","created_at":"2026-07-05T07:57:02Z"},{"alias_kind":"pith_short_16","alias_value":"HEX5BNQ34AYUCXN2","created_at":"2026-07-05T07:57:02Z"},{"alias_kind":"pith_short_8","alias_value":"HEX5BNQ3","created_at":"2026-07-05T07:57:02Z"}],"graph_snapshots":[{"event_id":"sha256:6c8dee14e1d2057f8bb1954314563a539199f2f366e9f9b357fd2da21c40e77e","target":"graph","created_at":"2026-07-05T07:57:02Z","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/2403.09701/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hybrid Reinforcement Learning (RL), leveraging both online and offline data, has garnered recent interest, yet research on its provable benefits remains sparse. Additionally, many existing hybrid RL algorithms (Song et al., 2023; Nakamoto et al., 2023; Amortila et al., 2024) impose coverage assumptions on the offline dataset, but we show that this is unnecessary. A well-designed online algorithm should \"fill in the gaps\" in the offline dataset, exploring states and actions that the behavior policy did not explore. Unlike previous approaches that focus on estimating the offline data distributio","authors_text":"Kevin Tan, Ziping Xu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-07T19:39:47Z","title":"A Natural Extension To Online Algorithms For Hybrid RL With Limited Coverage"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09701","kind":"arxiv","version":2},"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":"sha256:4fe7800abc5b52bd2b21400ac46430388ef7c00da81674c8060696f073aa328d","target":"record","created_at":"2026-07-05T07:57:02Z","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":"a149b1d12efe5d0084cc6a3a618cf8960d148d2059f6118842b6620768f90631","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-07T19:39:47Z","title_canon_sha256":"9f353ec5e73c11e8ed005e6e877283337bf93d8b92307ba92e97b30d2d5d6df1"},"schema_version":"1.0","source":{"id":"2403.09701","kind":"arxiv","version":2}},"canonical_sha256":"392fd0b61be031415dba8fb04ec6b7e26640ea6e30c34471a6e5ddb53bc6ecc1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"392fd0b61be031415dba8fb04ec6b7e26640ea6e30c34471a6e5ddb53bc6ecc1","first_computed_at":"2026-07-05T07:57:02.470064Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:57:02.470064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Dt6mXKLU4YrLqk6CM7rEiJmsTrX7dV/ug8kJmEO7hs6+FXibVYKHQxLkUW9QJGj0kA3DTY8c10vPwHsGO1vPAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:57:02.470542Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.09701","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fe7800abc5b52bd2b21400ac46430388ef7c00da81674c8060696f073aa328d","sha256:6c8dee14e1d2057f8bb1954314563a539199f2f366e9f9b357fd2da21c40e77e"],"state_sha256":"7ad28512c6642f7a231d4708386bc87769ac8326d09f811283e9990267a4aad0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bi0+Si5OHeHykbP4qyfqXU1lXX2GMUAh5m0L1MirI/6ij5XXL1RzooXfwR5/gW6g+SV6VlPEyMRogA8sHHHxBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T18:54:33.445703Z","bundle_sha256":"9b0c17639a2cd5e4c2435078ed96f06475741497a8cb89535172882ebf2d0f56"}}