{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CY2767GPCLAANXJI6YVRGDY3NN","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":"9c7b5484020be0b97bfee687b81e4ccfb7bed764471d4b3657cd885b45aa7015","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-14T22:28:36Z","title_canon_sha256":"6a5865b66ab3c292d236d8a2a6b67207727b44209d79f64e2627c4f618d219f3"},"schema_version":"1.0","source":{"id":"2507.10843","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.10843","created_at":"2026-07-05T11:37:00Z"},{"alias_kind":"arxiv_version","alias_value":"2507.10843v1","created_at":"2026-07-05T11:37:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10843","created_at":"2026-07-05T11:37:00Z"},{"alias_kind":"pith_short_12","alias_value":"CY2767GPCLAA","created_at":"2026-07-05T11:37:00Z"},{"alias_kind":"pith_short_16","alias_value":"CY2767GPCLAANXJI","created_at":"2026-07-05T11:37:00Z"},{"alias_kind":"pith_short_8","alias_value":"CY2767GP","created_at":"2026-07-05T11:37:00Z"}],"graph_snapshots":[{"event_id":"sha256:c7f15d13ca56fd082672dab44d6151093fd99ac17098fd7abb8d5a8c0d4b83d1","target":"graph","created_at":"2026-07-05T11:37:00Z","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/2507.10843/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) aims to learn an optimal policy from a static dataset, making it particularly valuable in scenarios where data collection is costly, such as robotics. A major challenge in offline RL is distributional shift, where the learned policy deviates from the dataset distribution, potentially leading to unreliable out-of-distribution actions. To mitigate this issue, regularization techniques have been employed. While many existing methods utilize density ratio-based measures, such as the $f$-divergence, for regularization, we propose an approach that utilizes the Was","authors_text":"Kazuki Ota, Motoki Omura, Takayuki Osa, Tatsuya Harada, Yusuke Mukuta","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-14T22:28:36Z","title":"Offline Reinforcement Learning with Wasserstein Regularization via Optimal Transport Maps"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10843","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":"sha256:80dff217f3f8c5a421d42723b6de570e8b1500d777b08fb4e0933b2ec4601ccd","target":"record","created_at":"2026-07-05T11:37:00Z","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":"9c7b5484020be0b97bfee687b81e4ccfb7bed764471d4b3657cd885b45aa7015","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-14T22:28:36Z","title_canon_sha256":"6a5865b66ab3c292d236d8a2a6b67207727b44209d79f64e2627c4f618d219f3"},"schema_version":"1.0","source":{"id":"2507.10843","kind":"arxiv","version":1}},"canonical_sha256":"1635ff7ccf12c006dd28f62b130f1b6b7922e532e63fcf46b76478678d7534a9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1635ff7ccf12c006dd28f62b130f1b6b7922e532e63fcf46b76478678d7534a9","first_computed_at":"2026-07-05T11:37:00.666135Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:37:00.666135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tKiWQll8G10ctV1nX3PL/RWLE39J5piDNfY0dQAFCtQAeqz7cTaiM5C7LmW7WYJVEKFRzlOvvh1gvmhhjJRaAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:37:00.666696Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.10843","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80dff217f3f8c5a421d42723b6de570e8b1500d777b08fb4e0933b2ec4601ccd","sha256:c7f15d13ca56fd082672dab44d6151093fd99ac17098fd7abb8d5a8c0d4b83d1"],"state_sha256":"0dfbbbfef611f5a193e66da0fa9000e6b64de7c73a4c1f2b3222f15eb2fd0387"}