{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SDP4NSHPM277V2IU7I5KKGFCS5","short_pith_number":"pith:SDP4NSHP","schema_version":"1.0","canonical_sha256":"90dfc6c8ef66bffae914fa3aa518a2977f79fddbca7943160841755d3ba4b91a","source":{"kind":"arxiv","id":"2606.20084","version":1},"attestation_state":"computed","paper":{"title":"Residual-Space Evolutionary Optimization via Flow-based Generative Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fernanda Nader, Hanno Scharr, Ira Assent, Lena Krieger, Xuan Zhao, Zhuo Cao","submitted_at":"2026-06-18T11:02:11Z","abstract_excerpt":"Data editing with generative methods typically requires differentiable objectives and gradient-based search. However, these assumptions break down in flow-based settings, where edits are performed through forward and backward integration and often involve non-differentiable or black-box objectives. We introduce residual-space evolutionary optimization, a model-agnostic framework that addresses this gap by combining flow-based generative editing with evolutionary algorithms. Building on the observation that conditional flow matching (CFM) can disentangle condition-controlled factors from instan"},"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":"2606.20084","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-18T11:02:11Z","cross_cats_sorted":[],"title_canon_sha256":"4b30c281f2288d8e6f2de7a71ac7c02606da1f15a9bd49f7ac2b21752730b0dd","abstract_canon_sha256":"594a20c85ebec5c8d0259ac4b017a6f00ff772ab69274da9d6cfbabc36ea584c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:13:02.441041Z","signature_b64":"6zDpYA5LmrYEMO652v1TMynjCe2T28ZBNBn9h7UwKoH34T9mIzMi1GGwoTOxnutKYnMHHxX12Tvc349Dq6u3BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90dfc6c8ef66bffae914fa3aa518a2977f79fddbca7943160841755d3ba4b91a","last_reissued_at":"2026-06-19T16:13:02.440625Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:13:02.440625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Residual-Space Evolutionary Optimization via Flow-based Generative Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fernanda Nader, Hanno Scharr, Ira Assent, Lena Krieger, Xuan Zhao, Zhuo Cao","submitted_at":"2026-06-18T11:02:11Z","abstract_excerpt":"Data editing with generative methods typically requires differentiable objectives and gradient-based search. However, these assumptions break down in flow-based settings, where edits are performed through forward and backward integration and often involve non-differentiable or black-box objectives. We introduce residual-space evolutionary optimization, a model-agnostic framework that addresses this gap by combining flow-based generative editing with evolutionary algorithms. Building on the observation that conditional flow matching (CFM) can disentangle condition-controlled factors from instan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20084","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/2606.20084/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":"2606.20084","created_at":"2026-06-19T16:13:02.440690+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20084v1","created_at":"2026-06-19T16:13:02.440690+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20084","created_at":"2026-06-19T16:13:02.440690+00:00"},{"alias_kind":"pith_short_12","alias_value":"SDP4NSHPM277","created_at":"2026-06-19T16:13:02.440690+00:00"},{"alias_kind":"pith_short_16","alias_value":"SDP4NSHPM277V2IU","created_at":"2026-06-19T16:13:02.440690+00:00"},{"alias_kind":"pith_short_8","alias_value":"SDP4NSHP","created_at":"2026-06-19T16:13:02.440690+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/SDP4NSHPM277V2IU7I5KKGFCS5","json":"https://pith.science/pith/SDP4NSHPM277V2IU7I5KKGFCS5.json","graph_json":"https://pith.science/api/pith-number/SDP4NSHPM277V2IU7I5KKGFCS5/graph.json","events_json":"https://pith.science/api/pith-number/SDP4NSHPM277V2IU7I5KKGFCS5/events.json","paper":"https://pith.science/paper/SDP4NSHP"},"agent_actions":{"view_html":"https://pith.science/pith/SDP4NSHPM277V2IU7I5KKGFCS5","download_json":"https://pith.science/pith/SDP4NSHPM277V2IU7I5KKGFCS5.json","view_paper":"https://pith.science/paper/SDP4NSHP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20084&json=true","fetch_graph":"https://pith.science/api/pith-number/SDP4NSHPM277V2IU7I5KKGFCS5/graph.json","fetch_events":"https://pith.science/api/pith-number/SDP4NSHPM277V2IU7I5KKGFCS5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SDP4NSHPM277V2IU7I5KKGFCS5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SDP4NSHPM277V2IU7I5KKGFCS5/action/storage_attestation","attest_author":"https://pith.science/pith/SDP4NSHPM277V2IU7I5KKGFCS5/action/author_attestation","sign_citation":"https://pith.science/pith/SDP4NSHPM277V2IU7I5KKGFCS5/action/citation_signature","submit_replication":"https://pith.science/pith/SDP4NSHPM277V2IU7I5KKGFCS5/action/replication_record"}},"created_at":"2026-06-19T16:13:02.440690+00:00","updated_at":"2026-06-19T16:13:02.440690+00:00"}