{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VQHMFSFF6TWAUMSK6JHKQMJCAU","short_pith_number":"pith:VQHMFSFF","canonical_record":{"source":{"id":"2601.21924","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T16:16:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4d6317a039840bf50f5dd73588dcb3bbb5f5284eabf4cc3924e3e5f52bd5c19f","abstract_canon_sha256":"5459d5ab71ecd08f465cd563bb394670f4b30e4ced296b1e0f0587b85fa9ff2b"},"schema_version":"1.0"},"canonical_sha256":"ac0ec2c8a5f4ec0a324af24ea8312205229b869e856e33e6c8814d5bc7f2139e","source":{"kind":"arxiv","id":"2601.21924","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.21924","created_at":"2026-05-26T01:03:23Z"},{"alias_kind":"arxiv_version","alias_value":"2601.21924v2","created_at":"2026-05-26T01:03:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21924","created_at":"2026-05-26T01:03:23Z"},{"alias_kind":"pith_short_12","alias_value":"VQHMFSFF6TWA","created_at":"2026-05-26T01:03:23Z"},{"alias_kind":"pith_short_16","alias_value":"VQHMFSFF6TWAUMSK","created_at":"2026-05-26T01:03:23Z"},{"alias_kind":"pith_short_8","alias_value":"VQHMFSFF","created_at":"2026-05-26T01:03:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VQHMFSFF6TWAUMSK6JHKQMJCAU","target":"record","payload":{"canonical_record":{"source":{"id":"2601.21924","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T16:16:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4d6317a039840bf50f5dd73588dcb3bbb5f5284eabf4cc3924e3e5f52bd5c19f","abstract_canon_sha256":"5459d5ab71ecd08f465cd563bb394670f4b30e4ced296b1e0f0587b85fa9ff2b"},"schema_version":"1.0"},"canonical_sha256":"ac0ec2c8a5f4ec0a324af24ea8312205229b869e856e33e6c8814d5bc7f2139e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:23.719481Z","signature_b64":"un9YQn8X0ccbGmT6p+z8nZIGlheqpKj+2yUmXpsf3D9jmJqfw1yieXMa3b/sZR2j2Bq+44tEiR4cm0LQGmNRBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac0ec2c8a5f4ec0a324af24ea8312205229b869e856e33e6c8814d5bc7f2139e","last_reissued_at":"2026-05-26T01:03:23.718522Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:23.718522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2601.21924","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":"2026-05-26T01:03:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WffwQbhADBGlvCmX58XXpOZ+PwgoaeP51r7StIhQyVuHq+u9k2A+iLWJtDCu4oOu4EVct3ySEe1WyI+7vSq6BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T16:13:51.232768Z"},"content_sha256":"2e4b6c73fbbc3d677a6be034d60c5864d69f569e5bbdc9160fc30b962887a42d","schema_version":"1.0","event_id":"sha256:2e4b6c73fbbc3d677a6be034d60c5864d69f569e5bbdc9160fc30b962887a42d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VQHMFSFF6TWAUMSK6JHKQMJCAU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"One-Step Bellman Alignment Enables Provably Efficient Transfer in Online RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Elynn Chen, Enpei Zhang, Jinhang Chai, Yujun Yan","submitted_at":"2026-01-29T16:16:24Z","abstract_excerpt":"We study online transfer reinforcement learning (RL) in episodic Markov decision processes, where experience from related source tasks is available during learning on a target task. A fundamental difficulty is that task similarity is typically defined in terms of rewards or transitions, whereas online RL algorithms operate on Bellman regression targets. As a result, naively reusing source Bellman updates introduces systematic bias and invalidates regret guarantees. We identify one-step Bellman alignment as the correct abstraction for transfer in online RL and propose re-weighted targeting (RWT"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.21924","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/2601.21924/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":"2026-05-26T01:03:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rLvaZGOpf11fm8SuK3ci0aLaYO6D8wlZtCYCLuc+8E4PR6J2KhdeoiGTyPmWKlje8aqvQmARBcoN4oT8AuBfBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T16:13:51.233598Z"},"content_sha256":"47c530dc8c007d600771fe54367620a444eed78d5d2a262a26dc445979879856","schema_version":"1.0","event_id":"sha256:47c530dc8c007d600771fe54367620a444eed78d5d2a262a26dc445979879856"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VQHMFSFF6TWAUMSK6JHKQMJCAU/bundle.json","state_url":"https://pith.science/pith/VQHMFSFF6TWAUMSK6JHKQMJCAU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VQHMFSFF6TWAUMSK6JHKQMJCAU/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":"2026-05-29T16:13:51Z","links":{"resolver":"https://pith.science/pith/VQHMFSFF6TWAUMSK6JHKQMJCAU","bundle":"https://pith.science/pith/VQHMFSFF6TWAUMSK6JHKQMJCAU/bundle.json","state":"https://pith.science/pith/VQHMFSFF6TWAUMSK6JHKQMJCAU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VQHMFSFF6TWAUMSK6JHKQMJCAU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VQHMFSFF6TWAUMSK6JHKQMJCAU","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":"5459d5ab71ecd08f465cd563bb394670f4b30e4ced296b1e0f0587b85fa9ff2b","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T16:16:24Z","title_canon_sha256":"4d6317a039840bf50f5dd73588dcb3bbb5f5284eabf4cc3924e3e5f52bd5c19f"},"schema_version":"1.0","source":{"id":"2601.21924","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.21924","created_at":"2026-05-26T01:03:23Z"},{"alias_kind":"arxiv_version","alias_value":"2601.21924v2","created_at":"2026-05-26T01:03:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21924","created_at":"2026-05-26T01:03:23Z"},{"alias_kind":"pith_short_12","alias_value":"VQHMFSFF6TWA","created_at":"2026-05-26T01:03:23Z"},{"alias_kind":"pith_short_16","alias_value":"VQHMFSFF6TWAUMSK","created_at":"2026-05-26T01:03:23Z"},{"alias_kind":"pith_short_8","alias_value":"VQHMFSFF","created_at":"2026-05-26T01:03:23Z"}],"graph_snapshots":[{"event_id":"sha256:47c530dc8c007d600771fe54367620a444eed78d5d2a262a26dc445979879856","target":"graph","created_at":"2026-05-26T01:03:23Z","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/2601.21924/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study online transfer reinforcement learning (RL) in episodic Markov decision processes, where experience from related source tasks is available during learning on a target task. A fundamental difficulty is that task similarity is typically defined in terms of rewards or transitions, whereas online RL algorithms operate on Bellman regression targets. As a result, naively reusing source Bellman updates introduces systematic bias and invalidates regret guarantees. We identify one-step Bellman alignment as the correct abstraction for transfer in online RL and propose re-weighted targeting (RWT","authors_text":"Elynn Chen, Enpei Zhang, Jinhang Chai, Yujun Yan","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T16:16:24Z","title":"One-Step Bellman Alignment Enables Provably Efficient Transfer in Online RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.21924","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":"sha256:2e4b6c73fbbc3d677a6be034d60c5864d69f569e5bbdc9160fc30b962887a42d","target":"record","created_at":"2026-05-26T01:03:23Z","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":"5459d5ab71ecd08f465cd563bb394670f4b30e4ced296b1e0f0587b85fa9ff2b","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T16:16:24Z","title_canon_sha256":"4d6317a039840bf50f5dd73588dcb3bbb5f5284eabf4cc3924e3e5f52bd5c19f"},"schema_version":"1.0","source":{"id":"2601.21924","kind":"arxiv","version":2}},"canonical_sha256":"ac0ec2c8a5f4ec0a324af24ea8312205229b869e856e33e6c8814d5bc7f2139e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac0ec2c8a5f4ec0a324af24ea8312205229b869e856e33e6c8814d5bc7f2139e","first_computed_at":"2026-05-26T01:03:23.718522Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:23.718522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"un9YQn8X0ccbGmT6p+z8nZIGlheqpKj+2yUmXpsf3D9jmJqfw1yieXMa3b/sZR2j2Bq+44tEiR4cm0LQGmNRBg==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:23.719481Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.21924","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e4b6c73fbbc3d677a6be034d60c5864d69f569e5bbdc9160fc30b962887a42d","sha256:47c530dc8c007d600771fe54367620a444eed78d5d2a262a26dc445979879856"],"state_sha256":"c3f3ab5e361280b89841783bd6ea5786891f583326030f891faada26d7ce8ff3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aI3sHO1/SpqfiGTxIdUzDpGhZAs6bxQ4fojMkf6hhD+266V+WkjGM4ZAYtRFsueYOnrP8nx2Gc2hNKtvkv9ZBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T16:13:51.238022Z","bundle_sha256":"96ea656b20d8df4ec2dd33e61bd3b43af5860832e5ca7ea629788b4897e7782d"}}