{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CGGTOGKIQ6HH4WXISFAJRT4L7Q","short_pith_number":"pith:CGGTOGKI","canonical_record":{"source":{"id":"2411.03810","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-06T10:14:46Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5f47af71db257347a4d7050215c9d8e7abe6b6ef7f15968dc308435cb594088b","abstract_canon_sha256":"73c6038dd6e0409d585f098ca3ec7246d920b0b6f7dff1d34f47af85910438d3"},"schema_version":"1.0"},"canonical_sha256":"118d371948878e7e5ae8914098cf8bfc16c43f12396f4b43792758f3a75b638d","source":{"kind":"arxiv","id":"2411.03810","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.03810","created_at":"2026-07-05T09:31:56Z"},{"alias_kind":"arxiv_version","alias_value":"2411.03810v1","created_at":"2026-07-05T09:31:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.03810","created_at":"2026-07-05T09:31:56Z"},{"alias_kind":"pith_short_12","alias_value":"CGGTOGKIQ6HH","created_at":"2026-07-05T09:31:56Z"},{"alias_kind":"pith_short_16","alias_value":"CGGTOGKIQ6HH4WXI","created_at":"2026-07-05T09:31:56Z"},{"alias_kind":"pith_short_8","alias_value":"CGGTOGKI","created_at":"2026-07-05T09:31:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CGGTOGKIQ6HH4WXISFAJRT4L7Q","target":"record","payload":{"canonical_record":{"source":{"id":"2411.03810","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-06T10:14:46Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5f47af71db257347a4d7050215c9d8e7abe6b6ef7f15968dc308435cb594088b","abstract_canon_sha256":"73c6038dd6e0409d585f098ca3ec7246d920b0b6f7dff1d34f47af85910438d3"},"schema_version":"1.0"},"canonical_sha256":"118d371948878e7e5ae8914098cf8bfc16c43f12396f4b43792758f3a75b638d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:56.345858Z","signature_b64":"vF3bIFrfqUsUPCdC3cJO3CV0Bye68CYn9VIPlWS/cTbBmiiWvM3jmhD3DslXKuXRQY1alOd0aOjpnL36EI2pCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"118d371948878e7e5ae8914098cf8bfc16c43f12396f4b43792758f3a75b638d","last_reissued_at":"2026-07-05T09:31:56.345330Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:56.345330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.03810","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":"2026-07-05T09:31:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mf9ltB6ERAlLEWaSVDw1MyAPbXtIZllVKLxVAYT95PCcb6REXjruhzxBa0FL5zgJDYPcKV6w+bW6RvuID8gHCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:11:45.402368Z"},"content_sha256":"3b1291aae3c73270d980c149c78b79b448c6eafea36c5a1a2f209a720fd54869","schema_version":"1.0","event_id":"sha256:3b1291aae3c73270d980c149c78b79b448c6eafea36c5a1a2f209a720fd54869"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CGGTOGKIQ6HH4WXISFAJRT4L7Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hybrid Transfer Reinforcement Learning: Provable Sample Efficiency from Shifted-Dynamics Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Wierman, Chengrui Qu, Kishan Panaganti, Laixi Shi, Pengcheng You","submitted_at":"2024-11-06T10:14:46Z","abstract_excerpt":"Online Reinforcement learning (RL) typically requires high-stakes online interaction data to learn a policy for a target task. This prompts interest in leveraging historical data to improve sample efficiency. The historical data may come from outdated or related source environments with different dynamics. It remains unclear how to effectively use such data in the target task to provably enhance learning and sample efficiency. To address this, we propose a hybrid transfer RL (HTRL) setting, where an agent learns in a target environment while accessing offline data from a source environment wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.03810","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/2411.03810/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":"2026-07-05T09:31:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7wKuv7j7XGfufVVCSJ8knYJ3jhFavpqhJFPA0yYgBwG9R/TAhnhEeq4G37ihCYA3QvPs6WFtvecOquuJhreWCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:11:45.402893Z"},"content_sha256":"747a612c7ba48f05601a05a87de902ddd572534181ad44536a88ba9acd8c14f6","schema_version":"1.0","event_id":"sha256:747a612c7ba48f05601a05a87de902ddd572534181ad44536a88ba9acd8c14f6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CGGTOGKIQ6HH4WXISFAJRT4L7Q/bundle.json","state_url":"https://pith.science/pith/CGGTOGKIQ6HH4WXISFAJRT4L7Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CGGTOGKIQ6HH4WXISFAJRT4L7Q/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":"2026-08-08T16:11:45Z","links":{"resolver":"https://pith.science/pith/CGGTOGKIQ6HH4WXISFAJRT4L7Q","bundle":"https://pith.science/pith/CGGTOGKIQ6HH4WXISFAJRT4L7Q/bundle.json","state":"https://pith.science/pith/CGGTOGKIQ6HH4WXISFAJRT4L7Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CGGTOGKIQ6HH4WXISFAJRT4L7Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CGGTOGKIQ6HH4WXISFAJRT4L7Q","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":"73c6038dd6e0409d585f098ca3ec7246d920b0b6f7dff1d34f47af85910438d3","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-06T10:14:46Z","title_canon_sha256":"5f47af71db257347a4d7050215c9d8e7abe6b6ef7f15968dc308435cb594088b"},"schema_version":"1.0","source":{"id":"2411.03810","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.03810","created_at":"2026-07-05T09:31:56Z"},{"alias_kind":"arxiv_version","alias_value":"2411.03810v1","created_at":"2026-07-05T09:31:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.03810","created_at":"2026-07-05T09:31:56Z"},{"alias_kind":"pith_short_12","alias_value":"CGGTOGKIQ6HH","created_at":"2026-07-05T09:31:56Z"},{"alias_kind":"pith_short_16","alias_value":"CGGTOGKIQ6HH4WXI","created_at":"2026-07-05T09:31:56Z"},{"alias_kind":"pith_short_8","alias_value":"CGGTOGKI","created_at":"2026-07-05T09:31:56Z"}],"graph_snapshots":[{"event_id":"sha256:747a612c7ba48f05601a05a87de902ddd572534181ad44536a88ba9acd8c14f6","target":"graph","created_at":"2026-07-05T09:31:56Z","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/2411.03810/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Online Reinforcement learning (RL) typically requires high-stakes online interaction data to learn a policy for a target task. This prompts interest in leveraging historical data to improve sample efficiency. The historical data may come from outdated or related source environments with different dynamics. It remains unclear how to effectively use such data in the target task to provably enhance learning and sample efficiency. To address this, we propose a hybrid transfer RL (HTRL) setting, where an agent learns in a target environment while accessing offline data from a source environment wit","authors_text":"Adam Wierman, Chengrui Qu, Kishan Panaganti, Laixi Shi, Pengcheng You","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-06T10:14:46Z","title":"Hybrid Transfer Reinforcement Learning: Provable Sample Efficiency from Shifted-Dynamics Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.03810","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":"sha256:3b1291aae3c73270d980c149c78b79b448c6eafea36c5a1a2f209a720fd54869","target":"record","created_at":"2026-07-05T09:31:56Z","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":"73c6038dd6e0409d585f098ca3ec7246d920b0b6f7dff1d34f47af85910438d3","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-06T10:14:46Z","title_canon_sha256":"5f47af71db257347a4d7050215c9d8e7abe6b6ef7f15968dc308435cb594088b"},"schema_version":"1.0","source":{"id":"2411.03810","kind":"arxiv","version":1}},"canonical_sha256":"118d371948878e7e5ae8914098cf8bfc16c43f12396f4b43792758f3a75b638d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"118d371948878e7e5ae8914098cf8bfc16c43f12396f4b43792758f3a75b638d","first_computed_at":"2026-07-05T09:31:56.345330Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:31:56.345330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vF3bIFrfqUsUPCdC3cJO3CV0Bye68CYn9VIPlWS/cTbBmiiWvM3jmhD3DslXKuXRQY1alOd0aOjpnL36EI2pCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:31:56.345858Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.03810","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b1291aae3c73270d980c149c78b79b448c6eafea36c5a1a2f209a720fd54869","sha256:747a612c7ba48f05601a05a87de902ddd572534181ad44536a88ba9acd8c14f6"],"state_sha256":"dfe3fd98eb47e3a17672ab3588a498f81e78cf92cf85bf942898df45a9771e76"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8UbZk7KCpCEug/E31aC7Ad510rhhwnmSa8u97yY7YWTqAsrkxaY09I1jDOnA9BneFx9Jr4wswAwlmi+zOvRhBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T16:11:45.406997Z","bundle_sha256":"4e19880fde6b364ece5c5fd74151fb67f07a610c6ca8716279404011723b6d68"}}