{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WJKWEEPM2BOZ3AL6R2JIW63GUQ","short_pith_number":"pith:WJKWEEPM","schema_version":"1.0","canonical_sha256":"b2556211ecd05d9d817e8e928b7b66a43271d93c54d8f73b8088e2621824611d","source":{"kind":"arxiv","id":"2605.24810","version":1},"attestation_state":"computed","paper":{"title":"Cross-Domain Energy-Guided Diffusion Generation for Off-Dynamics Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.AP"],"primary_cat":"cs.LG","authors_text":"Anqi Liu, Pan Xu, Yihong Guo, Yu Yang","submitted_at":"2026-05-24T01:44:57Z","abstract_excerpt":"Off-dynamics offline reinforcement learning seeks to learn a target-domain policy from a large source dataset and a limited target dataset under mismatched transition dynamics. Existing approaches such as reward augmentation and data filtering are constrained to the source dataset and cannot synthesize new target behavior to improve coverage beyond the collected source trajectories. While recent model-based methods attempt to address this by learning target-aware dynamics, the generated experience is constructed only at the transition level, which leads to accumulated errors over long horizons"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.24810","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-24T01:44:57Z","cross_cats_sorted":["cs.AI","cs.RO","stat.AP"],"title_canon_sha256":"fc72464404ccb932896c1fa785a6e30b9248efd93341a26d3eaad83f9889c004","abstract_canon_sha256":"ecc1be2831ae6b5eef6d1f9af7d773f2810ed75936bf34b2fd7802f42b35e068"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:59.404493Z","signature_b64":"X3J4EbMhPnBacUSnWmCybixbdO3v4d1x3w76vZC4lAacH/Nh3Pt8yvHciiSbn8uUtJMYq9dCXQPg8NZZTRD7Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2556211ecd05d9d817e8e928b7b66a43271d93c54d8f73b8088e2621824611d","last_reissued_at":"2026-05-26T01:03:59.403925Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:59.403925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Domain Energy-Guided Diffusion Generation for Off-Dynamics Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.AP"],"primary_cat":"cs.LG","authors_text":"Anqi Liu, Pan Xu, Yihong Guo, Yu Yang","submitted_at":"2026-05-24T01:44:57Z","abstract_excerpt":"Off-dynamics offline reinforcement learning seeks to learn a target-domain policy from a large source dataset and a limited target dataset under mismatched transition dynamics. Existing approaches such as reward augmentation and data filtering are constrained to the source dataset and cannot synthesize new target behavior to improve coverage beyond the collected source trajectories. While recent model-based methods attempt to address this by learning target-aware dynamics, the generated experience is constructed only at the transition level, which leads to accumulated errors over long horizons"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24810","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/2605.24810/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.24810","created_at":"2026-05-26T01:03:59.404012+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24810v1","created_at":"2026-05-26T01:03:59.404012+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24810","created_at":"2026-05-26T01:03:59.404012+00:00"},{"alias_kind":"pith_short_12","alias_value":"WJKWEEPM2BOZ","created_at":"2026-05-26T01:03:59.404012+00:00"},{"alias_kind":"pith_short_16","alias_value":"WJKWEEPM2BOZ3AL6","created_at":"2026-05-26T01:03:59.404012+00:00"},{"alias_kind":"pith_short_8","alias_value":"WJKWEEPM","created_at":"2026-05-26T01:03:59.404012+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WJKWEEPM2BOZ3AL6R2JIW63GUQ","json":"https://pith.science/pith/WJKWEEPM2BOZ3AL6R2JIW63GUQ.json","graph_json":"https://pith.science/api/pith-number/WJKWEEPM2BOZ3AL6R2JIW63GUQ/graph.json","events_json":"https://pith.science/api/pith-number/WJKWEEPM2BOZ3AL6R2JIW63GUQ/events.json","paper":"https://pith.science/paper/WJKWEEPM"},"agent_actions":{"view_html":"https://pith.science/pith/WJKWEEPM2BOZ3AL6R2JIW63GUQ","download_json":"https://pith.science/pith/WJKWEEPM2BOZ3AL6R2JIW63GUQ.json","view_paper":"https://pith.science/paper/WJKWEEPM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24810&json=true","fetch_graph":"https://pith.science/api/pith-number/WJKWEEPM2BOZ3AL6R2JIW63GUQ/graph.json","fetch_events":"https://pith.science/api/pith-number/WJKWEEPM2BOZ3AL6R2JIW63GUQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WJKWEEPM2BOZ3AL6R2JIW63GUQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WJKWEEPM2BOZ3AL6R2JIW63GUQ/action/storage_attestation","attest_author":"https://pith.science/pith/WJKWEEPM2BOZ3AL6R2JIW63GUQ/action/author_attestation","sign_citation":"https://pith.science/pith/WJKWEEPM2BOZ3AL6R2JIW63GUQ/action/citation_signature","submit_replication":"https://pith.science/pith/WJKWEEPM2BOZ3AL6R2JIW63GUQ/action/replication_record"}},"created_at":"2026-05-26T01:03:59.404012+00:00","updated_at":"2026-05-26T01:03:59.404012+00:00"}