{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UWZMYPV6QK3K2JMMU3JLICNWY2","short_pith_number":"pith:UWZMYPV6","schema_version":"1.0","canonical_sha256":"a5b2cc3ebe82b6ad258ca6d2b409b6c69097db3e0d6b6c0170bc06b80867c06f","source":{"kind":"arxiv","id":"2506.13834","version":1},"attestation_state":"computed","paper":{"title":"Evolvable Conditional Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Chin Chun Ooi, Jian Cheng Wong, Pao-Hsiung Chiu, Sheares Xue Wen Toh, Yew-Soon Ong, Zhao Wei","submitted_at":"2025-06-16T07:11:32Z","abstract_excerpt":"This paper presents an evolvable conditional diffusion method such that black-box, non-differentiable multi-physics models, as are common in domains like computational fluid dynamics and electromagnetics, can be effectively used for guiding the generative process to facilitate autonomous scientific discovery. We formulate the guidance as an optimization problem where one optimizes for a desired fitness function through updates to the descriptive statistic for the denoising distribution, and derive an evolution-guided approach from first principles through the lens of probabilistic evolution. I"},"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":"2506.13834","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-16T07:11:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6a84b9b15e98f27d1ccf0c9bf984dbe2e0bfc7254d0492e6cb029457f4821148","abstract_canon_sha256":"bee723221c9761b086203eea8923a0d10aac5db505d96af4eb1984f016f274c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:44.550391Z","signature_b64":"Td682+aPkrb0UrUPTlNyXum5/VHe9M/sOVycowbbsZVeyNBA0YG9500+MC8p7VxWoeDBybF9WOLZXQTSQdeJCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5b2cc3ebe82b6ad258ca6d2b409b6c69097db3e0d6b6c0170bc06b80867c06f","last_reissued_at":"2026-07-05T11:22:44.549868Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:44.549868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evolvable Conditional Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Chin Chun Ooi, Jian Cheng Wong, Pao-Hsiung Chiu, Sheares Xue Wen Toh, Yew-Soon Ong, Zhao Wei","submitted_at":"2025-06-16T07:11:32Z","abstract_excerpt":"This paper presents an evolvable conditional diffusion method such that black-box, non-differentiable multi-physics models, as are common in domains like computational fluid dynamics and electromagnetics, can be effectively used for guiding the generative process to facilitate autonomous scientific discovery. We formulate the guidance as an optimization problem where one optimizes for a desired fitness function through updates to the descriptive statistic for the denoising distribution, and derive an evolution-guided approach from first principles through the lens of probabilistic evolution. I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13834","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/2506.13834/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":"2506.13834","created_at":"2026-07-05T11:22:44.549936+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.13834v1","created_at":"2026-07-05T11:22:44.549936+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13834","created_at":"2026-07-05T11:22:44.549936+00:00"},{"alias_kind":"pith_short_12","alias_value":"UWZMYPV6QK3K","created_at":"2026-07-05T11:22:44.549936+00:00"},{"alias_kind":"pith_short_16","alias_value":"UWZMYPV6QK3K2JMM","created_at":"2026-07-05T11:22:44.549936+00:00"},{"alias_kind":"pith_short_8","alias_value":"UWZMYPV6","created_at":"2026-07-05T11:22:44.549936+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16348","citing_title":"Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07950","citing_title":"Slowly Annealed Langevin Dynamics: Theory and Applications to Training-Free Guided Generation","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UWZMYPV6QK3K2JMMU3JLICNWY2","json":"https://pith.science/pith/UWZMYPV6QK3K2JMMU3JLICNWY2.json","graph_json":"https://pith.science/api/pith-number/UWZMYPV6QK3K2JMMU3JLICNWY2/graph.json","events_json":"https://pith.science/api/pith-number/UWZMYPV6QK3K2JMMU3JLICNWY2/events.json","paper":"https://pith.science/paper/UWZMYPV6"},"agent_actions":{"view_html":"https://pith.science/pith/UWZMYPV6QK3K2JMMU3JLICNWY2","download_json":"https://pith.science/pith/UWZMYPV6QK3K2JMMU3JLICNWY2.json","view_paper":"https://pith.science/paper/UWZMYPV6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.13834&json=true","fetch_graph":"https://pith.science/api/pith-number/UWZMYPV6QK3K2JMMU3JLICNWY2/graph.json","fetch_events":"https://pith.science/api/pith-number/UWZMYPV6QK3K2JMMU3JLICNWY2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UWZMYPV6QK3K2JMMU3JLICNWY2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UWZMYPV6QK3K2JMMU3JLICNWY2/action/storage_attestation","attest_author":"https://pith.science/pith/UWZMYPV6QK3K2JMMU3JLICNWY2/action/author_attestation","sign_citation":"https://pith.science/pith/UWZMYPV6QK3K2JMMU3JLICNWY2/action/citation_signature","submit_replication":"https://pith.science/pith/UWZMYPV6QK3K2JMMU3JLICNWY2/action/replication_record"}},"created_at":"2026-07-05T11:22:44.549936+00:00","updated_at":"2026-07-05T11:22:44.549936+00:00"}