{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JRGUNHQLRXQYKIMUE24FGIYKCF","short_pith_number":"pith:JRGUNHQL","schema_version":"1.0","canonical_sha256":"4c4d469e0b8de185219426b853230a116d2bdb3825018f6b97d480e4c6383289","source":{"kind":"arxiv","id":"2606.09115","version":1},"attestation_state":"computed","paper":{"title":"Counterfactual Transport Flows for Offline Conservative Trajectory Refinement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hanno Scharr, Ira Assent, Lena Krieger, Qin Wang, Xuan Zhao, Zhuo Cao","submitted_at":"2026-06-08T07:11:03Z","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"},"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":"2606.09115","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T07:11:03Z","cross_cats_sorted":[],"title_canon_sha256":"bd422883dcb258b484d42d7e834494a09657f19a1ca75f574b08a1b3181cb007","abstract_canon_sha256":"6270df7e1ee4875d28ab06e30accc45438e11a50ed5a9719056700b539622a5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:08:00.070929Z","signature_b64":"A2P+hDqd0SEf2xVNzzuabUon4K+jIJ2Vtz8DEMhQJ5iCC0UL8+Mcd92M4ziMlbtue7LfAo2bBSpaXhxpa+/PCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c4d469e0b8de185219426b853230a116d2bdb3825018f6b97d480e4c6383289","last_reissued_at":"2026-06-09T02:08:00.070056Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:08:00.070056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Counterfactual Transport Flows for Offline Conservative Trajectory Refinement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hanno Scharr, Ira Assent, Lena Krieger, Qin Wang, Xuan Zhao, Zhuo Cao","submitted_at":"2026-06-08T07:11:03Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09115","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/2606.09115/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":"2606.09115","created_at":"2026-06-09T02:08:00.070206+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09115v1","created_at":"2026-06-09T02:08:00.070206+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09115","created_at":"2026-06-09T02:08:00.070206+00:00"},{"alias_kind":"pith_short_12","alias_value":"JRGUNHQLRXQY","created_at":"2026-06-09T02:08:00.070206+00:00"},{"alias_kind":"pith_short_16","alias_value":"JRGUNHQLRXQYKIMU","created_at":"2026-06-09T02:08:00.070206+00:00"},{"alias_kind":"pith_short_8","alias_value":"JRGUNHQL","created_at":"2026-06-09T02:08:00.070206+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/JRGUNHQLRXQYKIMUE24FGIYKCF","json":"https://pith.science/pith/JRGUNHQLRXQYKIMUE24FGIYKCF.json","graph_json":"https://pith.science/api/pith-number/JRGUNHQLRXQYKIMUE24FGIYKCF/graph.json","events_json":"https://pith.science/api/pith-number/JRGUNHQLRXQYKIMUE24FGIYKCF/events.json","paper":"https://pith.science/paper/JRGUNHQL"},"agent_actions":{"view_html":"https://pith.science/pith/JRGUNHQLRXQYKIMUE24FGIYKCF","download_json":"https://pith.science/pith/JRGUNHQLRXQYKIMUE24FGIYKCF.json","view_paper":"https://pith.science/paper/JRGUNHQL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09115&json=true","fetch_graph":"https://pith.science/api/pith-number/JRGUNHQLRXQYKIMUE24FGIYKCF/graph.json","fetch_events":"https://pith.science/api/pith-number/JRGUNHQLRXQYKIMUE24FGIYKCF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JRGUNHQLRXQYKIMUE24FGIYKCF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JRGUNHQLRXQYKIMUE24FGIYKCF/action/storage_attestation","attest_author":"https://pith.science/pith/JRGUNHQLRXQYKIMUE24FGIYKCF/action/author_attestation","sign_citation":"https://pith.science/pith/JRGUNHQLRXQYKIMUE24FGIYKCF/action/citation_signature","submit_replication":"https://pith.science/pith/JRGUNHQLRXQYKIMUE24FGIYKCF/action/replication_record"}},"created_at":"2026-06-09T02:08:00.070206+00:00","updated_at":"2026-06-09T02:08:00.070206+00:00"}