{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:43K5LMY3ARM55JOIZSZVI32VBG","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":"39a3186d10f89a34782264ad47c6426083715d68a82e5707dcd6a286f119c9d6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-04-16T08:50:57Z","title_canon_sha256":"a7049d81fc3c4bd69f939cc597b54bb421e6d637376bddc3124276692479db96"},"schema_version":"1.0","source":{"id":"2604.14790","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.14790","created_at":"2026-07-01T01:17:50Z"},{"alias_kind":"arxiv_version","alias_value":"2604.14790v2","created_at":"2026-07-01T01:17:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.14790","created_at":"2026-07-01T01:17:50Z"},{"alias_kind":"pith_short_12","alias_value":"43K5LMY3ARM5","created_at":"2026-07-01T01:17:50Z"},{"alias_kind":"pith_short_16","alias_value":"43K5LMY3ARM55JOI","created_at":"2026-07-01T01:17:50Z"},{"alias_kind":"pith_short_8","alias_value":"43K5LMY3","created_at":"2026-07-01T01:17:50Z"}],"graph_snapshots":[{"event_id":"sha256:c2c04a4f267c37dbd83502a9604c296261b5c0a42942c269323c84333f997dd1","target":"graph","created_at":"2026-07-01T01:17:50Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"By applying spherical linear interpolation (Slerp) to the noise sequences associated with selected parent images, the proposed method generates offspring that inherit characteristics from both parents while preserving the geometric structure of the diffusion process."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That step-wise interpolation of noise sequences in the DDPM reverse process produces offspring images that are semantically meaningful and useful for evolutionary recombination, rather than arbitrary blends that fail to preserve parental traits in a controllable way."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Diffusion crossover formulates evolutionary recombination as step-wise spherical linear interpolation of noise sequences in the DDPM reverse process to generate semantically consistent offspring from parent images."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Diffusion models support evolutionary crossover by applying spherical interpolation to parent noise sequences in the reverse process."}],"snapshot_sha256":"6fbbbb5dc09016546465549dc76a484e14dd2156c2dbed8f9776a8f8d7e495de"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.14790/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Interactive Evolutionary Computation (IEC) provides a powerful framework for optimizing subjective criteria such as human preferences and aesthetics, yet it suffers from a fundamental limitation: in high-dimensional generative representations, defining crossover in a semantically consistent manner is difficult, often leading to a mutation-dominated search. In this work, we explicitly define crossover in diffusion models. We propose Diffusion crossover, which formulates evolutionary recombination as step-wise interpolation of noise sequences in the reverse process of Denoising Diffusion Probabi","authors_text":"Chisato Kumada, Satoru Hiwa, Tomoyuki Hiroyasu","cross_cats":[],"headline":"Diffusion models support evolutionary crossover by applying spherical interpolation to parent noise sequences in the reverse process.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-04-16T08:50:57Z","title":"Diffusion Crossover: Defining Evolutionary Recombination in Diffusion Models via Noise Sequence Interpolation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.14790","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T10:33:59.033897Z","id":"816d096c-d4b6-4d0a-abf7-870a7eeaae7b","model_set":{"reader":"grok-4.3"},"one_line_summary":"Diffusion crossover formulates evolutionary recombination as step-wise spherical linear interpolation of noise sequences in the DDPM reverse process to generate semantically consistent offspring from parent images.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Diffusion models support evolutionary crossover by applying spherical interpolation to parent noise sequences in the reverse process.","strongest_claim":"By applying spherical linear interpolation (Slerp) to the noise sequences associated with selected parent images, the proposed method generates offspring that inherit characteristics from both parents while preserving the geometric structure of the diffusion process.","weakest_assumption":"That step-wise interpolation of noise sequences in the DDPM reverse process produces offspring images that are semantically meaningful and useful for evolutionary recombination, rather than arbitrary blends that fail to preserve parental traits in a controllable way."}},"verdict_id":"816d096c-d4b6-4d0a-abf7-870a7eeaae7b"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:eb1f648e8801c09582435040224372087f61e09c97ee92de499a709612b05ccd","target":"record","created_at":"2026-07-01T01:17:50Z","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":"39a3186d10f89a34782264ad47c6426083715d68a82e5707dcd6a286f119c9d6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-04-16T08:50:57Z","title_canon_sha256":"a7049d81fc3c4bd69f939cc597b54bb421e6d637376bddc3124276692479db96"},"schema_version":"1.0","source":{"id":"2604.14790","kind":"arxiv","version":2}},"canonical_sha256":"e6d5d5b31b0459dea5c8ccb3546f55099d5e90920e28eef1bc7662e912d4deeb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6d5d5b31b0459dea5c8ccb3546f55099d5e90920e28eef1bc7662e912d4deeb","first_computed_at":"2026-07-01T01:17:50.536027Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T01:17:50.536027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ww9NZythnJ7vyPUDy4gykkPr3zsRSgZeLLQs4mkNiPKE9FpfueHnv2TZ+YxYRRXPJSxv5BSTa7f+TxkTSMU1BQ==","signature_status":"signed_v1","signed_at":"2026-07-01T01:17:50.536476Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.14790","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb1f648e8801c09582435040224372087f61e09c97ee92de499a709612b05ccd","sha256:c2c04a4f267c37dbd83502a9604c296261b5c0a42942c269323c84333f997dd1"],"state_sha256":"3aa83b21c2804bda5dad0cb324f26083a94a4e1b33d2df2af6bf27659f46950e"}