{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JKGV543RQY334QRBGDEDTYWS6K","short_pith_number":"pith:JKGV543R","canonical_record":{"source":{"id":"2605.24862","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-24T04:44:44Z","cross_cats_sorted":[],"title_canon_sha256":"54f0e1d77ab02e83c575aaf2121feee775c464ffa0a176b03aa156a6d3a3d31c","abstract_canon_sha256":"e97103fcb4334b87f6d34763196387035eac0a9e6da8515d4d1907c2b82cfc38"},"schema_version":"1.0"},"canonical_sha256":"4a8d5ef3718637be422130c839e2d2f2a592df82b5c3b03aae6a803e6b4457b2","source":{"kind":"arxiv","id":"2605.24862","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24862","created_at":"2026-05-26T01:04:02Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24862v1","created_at":"2026-05-26T01:04:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24862","created_at":"2026-05-26T01:04:02Z"},{"alias_kind":"pith_short_12","alias_value":"JKGV543RQY33","created_at":"2026-05-26T01:04:02Z"},{"alias_kind":"pith_short_16","alias_value":"JKGV543RQY334QRB","created_at":"2026-05-26T01:04:02Z"},{"alias_kind":"pith_short_8","alias_value":"JKGV543R","created_at":"2026-05-26T01:04:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JKGV543RQY334QRBGDEDTYWS6K","target":"record","payload":{"canonical_record":{"source":{"id":"2605.24862","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-24T04:44:44Z","cross_cats_sorted":[],"title_canon_sha256":"54f0e1d77ab02e83c575aaf2121feee775c464ffa0a176b03aa156a6d3a3d31c","abstract_canon_sha256":"e97103fcb4334b87f6d34763196387035eac0a9e6da8515d4d1907c2b82cfc38"},"schema_version":"1.0"},"canonical_sha256":"4a8d5ef3718637be422130c839e2d2f2a592df82b5c3b03aae6a803e6b4457b2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:04:02.231357Z","signature_b64":"N6xLmRqyK7r7w5+BwJv/Mls3zquXsQa1ktwSIpz2wmyWkRBmfwcPPc5kz9RFUql76P5L3e3VmQs/iW1U63xeAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a8d5ef3718637be422130c839e2d2f2a592df82b5c3b03aae6a803e6b4457b2","last_reissued_at":"2026-05-26T01:04:02.230536Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:04:02.230536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.24862","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":"2026-05-26T01:04:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XWXDw4zGsuj5LBw2vMPMghLnaS0dkYWdRqnkWPmpiDu2BwrwRj1ylAOUTtDN+G1afzkA87tzjmRPObQ1CNzLBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T02:01:54.578091Z"},"content_sha256":"75a7a058e4eb35481ec3535437438a9626eb45c6e4deecf949f4a7e8afd49227","schema_version":"1.0","event_id":"sha256:75a7a058e4eb35481ec3535437438a9626eb45c6e4deecf949f4a7e8afd49227"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JKGV543RQY334QRBGDEDTYWS6K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unifying Value Alignment and Assignment in Cross-Domain Offline Reinforcement Learning with Heterogeneous Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenjia Bai, Jiafei Lyu, Peisong Wang, Shuang Qiu, Siyang Gao, Zhongjian Qiao","submitted_at":"2026-05-24T04:44:44Z","abstract_excerpt":"Cross-domain offline reinforcement learning (RL) aims to learn a policy in the target domain with a limited target domain dataset and a source domain dataset that exhibits a dynamics shift. Training directly on the original source dataset typically leads to performance collapse. Recent studies perform data filtering from the perspective of dynamics alignment or value alignment to enable efficient policy transfer. However, these studies are typically validated on single-domain or single-behavior-policy source datasets. In this work, we explore a more general heterogeneous cross-domain offline R"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24862","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/2605.24862/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":"2026-05-26T01:04:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b97q+SHgOZUGFOo61WgdrmaQqqdSOwjbKrcVytpr+PbN5TgZHpTsIfBSIWMqK/tNaH8LDx5FT8EyC3uqhmBKAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T02:01:54.578824Z"},"content_sha256":"3212f30c7f0d7382ace7365f8e5d7cba66667b2068323e87b73d465a078b6800","schema_version":"1.0","event_id":"sha256:3212f30c7f0d7382ace7365f8e5d7cba66667b2068323e87b73d465a078b6800"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JKGV543RQY334QRBGDEDTYWS6K/bundle.json","state_url":"https://pith.science/pith/JKGV543RQY334QRBGDEDTYWS6K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JKGV543RQY334QRBGDEDTYWS6K/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":"2026-06-01T02:01:54Z","links":{"resolver":"https://pith.science/pith/JKGV543RQY334QRBGDEDTYWS6K","bundle":"https://pith.science/pith/JKGV543RQY334QRBGDEDTYWS6K/bundle.json","state":"https://pith.science/pith/JKGV543RQY334QRBGDEDTYWS6K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JKGV543RQY334QRBGDEDTYWS6K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JKGV543RQY334QRBGDEDTYWS6K","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":"e97103fcb4334b87f6d34763196387035eac0a9e6da8515d4d1907c2b82cfc38","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-24T04:44:44Z","title_canon_sha256":"54f0e1d77ab02e83c575aaf2121feee775c464ffa0a176b03aa156a6d3a3d31c"},"schema_version":"1.0","source":{"id":"2605.24862","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24862","created_at":"2026-05-26T01:04:02Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24862v1","created_at":"2026-05-26T01:04:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24862","created_at":"2026-05-26T01:04:02Z"},{"alias_kind":"pith_short_12","alias_value":"JKGV543RQY33","created_at":"2026-05-26T01:04:02Z"},{"alias_kind":"pith_short_16","alias_value":"JKGV543RQY334QRB","created_at":"2026-05-26T01:04:02Z"},{"alias_kind":"pith_short_8","alias_value":"JKGV543R","created_at":"2026-05-26T01:04:02Z"}],"graph_snapshots":[{"event_id":"sha256:3212f30c7f0d7382ace7365f8e5d7cba66667b2068323e87b73d465a078b6800","target":"graph","created_at":"2026-05-26T01:04:02Z","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/2605.24862/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cross-domain offline reinforcement learning (RL) aims to learn a policy in the target domain with a limited target domain dataset and a source domain dataset that exhibits a dynamics shift. Training directly on the original source dataset typically leads to performance collapse. Recent studies perform data filtering from the perspective of dynamics alignment or value alignment to enable efficient policy transfer. However, these studies are typically validated on single-domain or single-behavior-policy source datasets. In this work, we explore a more general heterogeneous cross-domain offline R","authors_text":"Chenjia Bai, Jiafei Lyu, Peisong Wang, Shuang Qiu, Siyang Gao, Zhongjian Qiao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-24T04:44:44Z","title":"Unifying Value Alignment and Assignment in Cross-Domain Offline Reinforcement Learning with Heterogeneous Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24862","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":"sha256:75a7a058e4eb35481ec3535437438a9626eb45c6e4deecf949f4a7e8afd49227","target":"record","created_at":"2026-05-26T01:04:02Z","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":"e97103fcb4334b87f6d34763196387035eac0a9e6da8515d4d1907c2b82cfc38","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-24T04:44:44Z","title_canon_sha256":"54f0e1d77ab02e83c575aaf2121feee775c464ffa0a176b03aa156a6d3a3d31c"},"schema_version":"1.0","source":{"id":"2605.24862","kind":"arxiv","version":1}},"canonical_sha256":"4a8d5ef3718637be422130c839e2d2f2a592df82b5c3b03aae6a803e6b4457b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a8d5ef3718637be422130c839e2d2f2a592df82b5c3b03aae6a803e6b4457b2","first_computed_at":"2026-05-26T01:04:02.230536Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:04:02.230536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N6xLmRqyK7r7w5+BwJv/Mls3zquXsQa1ktwSIpz2wmyWkRBmfwcPPc5kz9RFUql76P5L3e3VmQs/iW1U63xeAw==","signature_status":"signed_v1","signed_at":"2026-05-26T01:04:02.231357Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.24862","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75a7a058e4eb35481ec3535437438a9626eb45c6e4deecf949f4a7e8afd49227","sha256:3212f30c7f0d7382ace7365f8e5d7cba66667b2068323e87b73d465a078b6800"],"state_sha256":"71ad28152e642aff1f1c7b25f8a692490a8cfdaa9cbccfc064844a6882b2efa8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HGQzc0a0aSRytx4LBH9PHMUVjsHV3T/m7mFCk6DKXRMELhrOiVTIAW0x37n/nNA0bsj0OHSHO1QugHk2fAiVAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T02:01:54.583098Z","bundle_sha256":"cc79c89075913acaa6309327b6ea964b9822f8f5b735bf4cd042ac6111e2c24d"}}