{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JRGUNHQLRXQYKIMUE24FGIYKCF","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":"6270df7e1ee4875d28ab06e30accc45438e11a50ed5a9719056700b539622a5e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T07:11:03Z","title_canon_sha256":"bd422883dcb258b484d42d7e834494a09657f19a1ca75f574b08a1b3181cb007"},"schema_version":"1.0","source":{"id":"2606.09115","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09115","created_at":"2026-06-09T02:08:00Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09115v1","created_at":"2026-06-09T02:08:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09115","created_at":"2026-06-09T02:08:00Z"},{"alias_kind":"pith_short_12","alias_value":"JRGUNHQLRXQY","created_at":"2026-06-09T02:08:00Z"},{"alias_kind":"pith_short_16","alias_value":"JRGUNHQLRXQYKIMU","created_at":"2026-06-09T02:08:00Z"},{"alias_kind":"pith_short_8","alias_value":"JRGUNHQL","created_at":"2026-06-09T02:08:00Z"}],"graph_snapshots":[{"event_id":"sha256:3f65b0fbef645fe324d9c1e7e66ae5031e8e88ad67fd31966f6364e8471f7423","target":"graph","created_at":"2026-06-09T02:08:00Z","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/2606.09115/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) offers a path to policy improvement from logged data alone, using historical returns or other measurable outcomes as world feedback. A key difficulty is improving observed behavior without extrapolating beyond what the offline data supports. We propose \\emph{counterfactual transport flows}, a source-conditioned trajectory refinement framework for offline decision-making guided by world feedback. Given a low-feedback candidate trajectory, we construct local preference pairs from offline data by retrieving nearby trajectories in latent trajectory space with hi","authors_text":"Hanno Scharr, Ira Assent, Lena Krieger, Qin Wang, Xuan Zhao, Zhuo Cao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T07:11:03Z","title":"Counterfactual Transport Flows for Offline Conservative Trajectory Refinement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09115","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:d6323e9b6d1a051e8cf954b7a00e17982972f736c9e4c2b422f3880c59c2c55b","target":"record","created_at":"2026-06-09T02:08:00Z","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":"6270df7e1ee4875d28ab06e30accc45438e11a50ed5a9719056700b539622a5e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T07:11:03Z","title_canon_sha256":"bd422883dcb258b484d42d7e834494a09657f19a1ca75f574b08a1b3181cb007"},"schema_version":"1.0","source":{"id":"2606.09115","kind":"arxiv","version":1}},"canonical_sha256":"4c4d469e0b8de185219426b853230a116d2bdb3825018f6b97d480e4c6383289","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c4d469e0b8de185219426b853230a116d2bdb3825018f6b97d480e4c6383289","first_computed_at":"2026-06-09T02:08:00.070056Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:08:00.070056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A2P+hDqd0SEf2xVNzzuabUon4K+jIJ2Vtz8DEMhQJ5iCC0UL8+Mcd92M4ziMlbtue7LfAo2bBSpaXhxpa+/PCA==","signature_status":"signed_v1","signed_at":"2026-06-09T02:08:00.070929Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.09115","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6323e9b6d1a051e8cf954b7a00e17982972f736c9e4c2b422f3880c59c2c55b","sha256:3f65b0fbef645fe324d9c1e7e66ae5031e8e88ad67fd31966f6364e8471f7423"],"state_sha256":"34e7b25da0d9e92062f18925ec29b6b8807fef9b4e7cc5abf2b5b6ec90768319"}