{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:2Z4HA2PYVJWBCYBRQ35KIQYBOR","short_pith_number":"pith:2Z4HA2PY","canonical_record":{"source":{"id":"2605.13054","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T06:23:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b017bebe7100461cc0ad9252248770b7a341540de6f88e3814a4b4fbb384a6c1","abstract_canon_sha256":"b8ab930630e8062a1fdfaa0e4ea4433c7441496f9efa1bad71dc9087f16c0120"},"schema_version":"1.0"},"canonical_sha256":"d6787069f8aa6c11603186faa4430174753ef2418b05c77ed39219b988fd0699","source":{"kind":"arxiv","id":"2605.13054","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13054","created_at":"2026-05-18T03:08:59Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13054v1","created_at":"2026-05-18T03:08:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13054","created_at":"2026-05-18T03:08:59Z"},{"alias_kind":"pith_short_12","alias_value":"2Z4HA2PYVJWB","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"2Z4HA2PYVJWBCYBR","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"2Z4HA2PY","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:2Z4HA2PYVJWBCYBRQ35KIQYBOR","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13054","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T06:23:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b017bebe7100461cc0ad9252248770b7a341540de6f88e3814a4b4fbb384a6c1","abstract_canon_sha256":"b8ab930630e8062a1fdfaa0e4ea4433c7441496f9efa1bad71dc9087f16c0120"},"schema_version":"1.0"},"canonical_sha256":"d6787069f8aa6c11603186faa4430174753ef2418b05c77ed39219b988fd0699","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:08:59.244903Z","signature_b64":"+uNLdu1nsmDs/XTJNlQaKJSqB6JKxbf80U0SWkPsuVzRjA1f2w5XhP8/QHms9/6O2vBWMfYnjHBHc3n609WGDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6787069f8aa6c11603186faa4430174753ef2418b05c77ed39219b988fd0699","last_reissued_at":"2026-05-18T03:08:59.244109Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:08:59.244109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13054","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":"2026-05-18T03:08:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JT+pNZJwAeHqHMMvXBeIrjNzBC5RS6ioS1GnLTYixj52vXmEioXpY1Z6K52hg8Z4df/owGQVvzMGeONVqWoOCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T06:06:47.156444Z"},"content_sha256":"34a97629806a693f6e06135d36901895826c89221d508c160354c93b5e45171c","schema_version":"1.0","event_id":"sha256:34a97629806a693f6e06135d36901895826c89221d508c160354c93b5e45171c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:2Z4HA2PYVJWBCYBRQ35KIQYBOR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bridging Domain Gaps with Target-Aligned Generation for Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Target-aligned Coverage Expansion uses dual score-based generation to synthesize consistent transitions across domains in offline RL.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gwanwoo Choi, Jeongmo Kim, Minung Kim, Seungyul Han","submitted_at":"2026-05-13T06:23:51Z","abstract_excerpt":"Cross-domain offline reinforcement learning aims to adapt a policy from a source domain to a target domain using only pre-collected datasets, where environment dynamics may differ. A key challenge is to leverage source data while reducing distributional mismatch, particularly when the target dataset is extremely limited. To address this, we propose Target-aligned Coverage Expansion (TCE), a framework that decides how source data should be used, either by directly incorporating target-near transitions or by expanding state coverage through target-aligned generation, guided by theoretical analys"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"TCE builds on a dual score-based generative model to synthesize target-consistent transitions over an expanded state region. Extensive experiments across diverse cross-domain environments show that TCE consistently outperforms state-of-the-art cross-domain offline RL baselines.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The dual score-based generative model can reliably synthesize target-consistent transitions over an expanded state region without introducing harmful distribution shifts.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"TCE bridges domain gaps in offline RL by selectively using source data or generating target-aligned transitions via a dual score-based model, outperforming baselines in experiments.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Target-aligned Coverage Expansion uses dual score-based generation to synthesize consistent transitions across domains in offline RL.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c8d70b2ef93b1affabb15c1fb55965232db91b99c8d33e75689d7a4e8a7023eb"},"source":{"id":"2605.13054","kind":"arxiv","version":1},"verdict":{"id":"84324f6e-93af-4db6-9394-a17840a82f72","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:09:23.535852Z","strongest_claim":"TCE builds on a dual score-based generative model to synthesize target-consistent transitions over an expanded state region. Extensive experiments across diverse cross-domain environments show that TCE consistently outperforms state-of-the-art cross-domain offline RL baselines.","one_line_summary":"TCE bridges domain gaps in offline RL by selectively using source data or generating target-aligned transitions via a dual score-based model, outperforming baselines in experiments.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The dual score-based generative model can reliably synthesize target-consistent transitions over an expanded state region without introducing harmful distribution shifts.","pith_extraction_headline":"Target-aligned Coverage Expansion uses dual score-based generation to synthesize consistent transitions across domains in offline RL."},"references":{"count":43,"sample":[{"doi":"","year":2018,"title":"arXiv preprint arXiv:1805.12298 , year=","work_id":"74f189b3-0db6-4c8d-85b3-78d3c52e0acc","ref_index":1,"cited_arxiv_id":"1805.12298","is_internal_anchor":true},{"doi":"","year":2020,"title":"A survey of au- tonomous driving: Common practices and emerging technologies.IEEE access, 8:58443–58469, 2020","work_id":"65b34a9c-1054-4051-be1f-225b0123a814","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Off-dynamics reinforcement learning: Training for transfer with domain classifiers","work_id":"94cb89e3-1520-40b5-8696-e21c9c2f3c5e","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Domain adaptive imitation learning","work_id":"229fdb1b-ca1a-4f01-8675-18f50c0ec393","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2005,"title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","work_id":"597b6f46-d60f-451f-8f34-7d32876a9014","ref_index":5,"cited_arxiv_id":"2005.01643","is_internal_anchor":true}],"resolved_work":43,"snapshot_sha256":"0502fe6a9f887af6e225f7d27db62ad807bcd105382fb0ac47d1c3ea946d55b6","internal_anchors":6},"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":"84324f6e-93af-4db6-9394-a17840a82f72"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:08:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dUtUYd6udFxP+44bQB69lFZ5yz6/Kt5dauf8ybf5Io1P8OnXtWUCxMZmD4g3Ifh8XWt24a9MhpD/Xi5JtfOsCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T06:06:47.157092Z"},"content_sha256":"6d308c52c02d99a8bbcb0d88c3ae9a042dc3343dd9d147b98c27d30fb215c3ea","schema_version":"1.0","event_id":"sha256:6d308c52c02d99a8bbcb0d88c3ae9a042dc3343dd9d147b98c27d30fb215c3ea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2Z4HA2PYVJWBCYBRQ35KIQYBOR/bundle.json","state_url":"https://pith.science/pith/2Z4HA2PYVJWBCYBRQ35KIQYBOR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2Z4HA2PYVJWBCYBRQ35KIQYBOR/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":"2026-06-04T06:06:47Z","links":{"resolver":"https://pith.science/pith/2Z4HA2PYVJWBCYBRQ35KIQYBOR","bundle":"https://pith.science/pith/2Z4HA2PYVJWBCYBRQ35KIQYBOR/bundle.json","state":"https://pith.science/pith/2Z4HA2PYVJWBCYBRQ35KIQYBOR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2Z4HA2PYVJWBCYBRQ35KIQYBOR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2Z4HA2PYVJWBCYBRQ35KIQYBOR","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":"b8ab930630e8062a1fdfaa0e4ea4433c7441496f9efa1bad71dc9087f16c0120","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T06:23:51Z","title_canon_sha256":"b017bebe7100461cc0ad9252248770b7a341540de6f88e3814a4b4fbb384a6c1"},"schema_version":"1.0","source":{"id":"2605.13054","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13054","created_at":"2026-05-18T03:08:59Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13054v1","created_at":"2026-05-18T03:08:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13054","created_at":"2026-05-18T03:08:59Z"},{"alias_kind":"pith_short_12","alias_value":"2Z4HA2PYVJWB","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"2Z4HA2PYVJWBCYBR","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"2Z4HA2PY","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:6d308c52c02d99a8bbcb0d88c3ae9a042dc3343dd9d147b98c27d30fb215c3ea","target":"graph","created_at":"2026-05-18T03:08:59Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"TCE builds on a dual score-based generative model to synthesize target-consistent transitions over an expanded state region. Extensive experiments across diverse cross-domain environments show that TCE consistently outperforms state-of-the-art cross-domain offline RL baselines."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The dual score-based generative model can reliably synthesize target-consistent transitions over an expanded state region without introducing harmful distribution shifts."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"TCE bridges domain gaps in offline RL by selectively using source data or generating target-aligned transitions via a dual score-based model, outperforming baselines in experiments."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Target-aligned Coverage Expansion uses dual score-based generation to synthesize consistent transitions across domains in offline RL."}],"snapshot_sha256":"c8d70b2ef93b1affabb15c1fb55965232db91b99c8d33e75689d7a4e8a7023eb"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Cross-domain offline reinforcement learning aims to adapt a policy from a source domain to a target domain using only pre-collected datasets, where environment dynamics may differ. A key challenge is to leverage source data while reducing distributional mismatch, particularly when the target dataset is extremely limited. To address this, we propose Target-aligned Coverage Expansion (TCE), a framework that decides how source data should be used, either by directly incorporating target-near transitions or by expanding state coverage through target-aligned generation, guided by theoretical analys","authors_text":"Gwanwoo Choi, Jeongmo Kim, Minung Kim, Seungyul Han","cross_cats":["cs.AI"],"headline":"Target-aligned Coverage Expansion uses dual score-based generation to synthesize consistent transitions across domains in offline RL.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T06:23:51Z","title":"Bridging Domain Gaps with Target-Aligned Generation for Offline Reinforcement Learning"},"references":{"count":43,"internal_anchors":6,"resolved_work":43,"sample":[{"cited_arxiv_id":"1805.12298","doi":"","is_internal_anchor":true,"ref_index":1,"title":"arXiv preprint arXiv:1805.12298 , year=","work_id":"74f189b3-0db6-4c8d-85b3-78d3c52e0acc","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"A survey of au- tonomous driving: Common practices and emerging technologies.IEEE access, 8:58443–58469, 2020","work_id":"65b34a9c-1054-4051-be1f-225b0123a814","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Off-dynamics reinforcement learning: Training for transfer with domain classifiers","work_id":"94cb89e3-1520-40b5-8696-e21c9c2f3c5e","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Domain adaptive imitation learning","work_id":"229fdb1b-ca1a-4f01-8675-18f50c0ec393","year":2020},{"cited_arxiv_id":"2005.01643","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","work_id":"597b6f46-d60f-451f-8f34-7d32876a9014","year":2005}],"snapshot_sha256":"0502fe6a9f887af6e225f7d27db62ad807bcd105382fb0ac47d1c3ea946d55b6"},"source":{"id":"2605.13054","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T20:09:23.535852Z","id":"84324f6e-93af-4db6-9394-a17840a82f72","model_set":{"reader":"grok-4.3"},"one_line_summary":"TCE bridges domain gaps in offline RL by selectively using source data or generating target-aligned transitions via a dual score-based model, outperforming baselines in experiments.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Target-aligned Coverage Expansion uses dual score-based generation to synthesize consistent transitions across domains in offline RL.","strongest_claim":"TCE builds on a dual score-based generative model to synthesize target-consistent transitions over an expanded state region. Extensive experiments across diverse cross-domain environments show that TCE consistently outperforms state-of-the-art cross-domain offline RL baselines.","weakest_assumption":"The dual score-based generative model can reliably synthesize target-consistent transitions over an expanded state region without introducing harmful distribution shifts."}},"verdict_id":"84324f6e-93af-4db6-9394-a17840a82f72"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:34a97629806a693f6e06135d36901895826c89221d508c160354c93b5e45171c","target":"record","created_at":"2026-05-18T03:08:59Z","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":"b8ab930630e8062a1fdfaa0e4ea4433c7441496f9efa1bad71dc9087f16c0120","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T06:23:51Z","title_canon_sha256":"b017bebe7100461cc0ad9252248770b7a341540de6f88e3814a4b4fbb384a6c1"},"schema_version":"1.0","source":{"id":"2605.13054","kind":"arxiv","version":1}},"canonical_sha256":"d6787069f8aa6c11603186faa4430174753ef2418b05c77ed39219b988fd0699","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6787069f8aa6c11603186faa4430174753ef2418b05c77ed39219b988fd0699","first_computed_at":"2026-05-18T03:08:59.244109Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:08:59.244109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+uNLdu1nsmDs/XTJNlQaKJSqB6JKxbf80U0SWkPsuVzRjA1f2w5XhP8/QHms9/6O2vBWMfYnjHBHc3n609WGDg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:08:59.244903Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13054","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34a97629806a693f6e06135d36901895826c89221d508c160354c93b5e45171c","sha256:6d308c52c02d99a8bbcb0d88c3ae9a042dc3343dd9d147b98c27d30fb215c3ea"],"state_sha256":"3fc04a589dbc5061b7ab27f262721338580d32b984defc72eb49e7cc0c67cedf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wVoICFiWHaIgPSXr+r8jKHS3kN0F0spnq5Hlh2gyPcj/5sYVGToGV52iyy8es203q1j/J6RsdaIJhI2prj/pDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T06:06:47.159731Z","bundle_sha256":"964bca6b611491d5f276a9c88159f011e2d8788542d6d2dd4664079aafa82703"}}