{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CMN26SHAH5CZ7T2PUYOOASOBAR","short_pith_number":"pith:CMN26SHA","schema_version":"1.0","canonical_sha256":"131baf48e03f459fcf4fa61ce049c1045b199602a962cdb313816cb0fe87f35f","source":{"kind":"arxiv","id":"2406.00812","version":2},"attestation_state":"computed","paper":{"title":"Covariance-Adaptive Sequential Black-box Optimization for Diffusion Targeted Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Ivor W. Tsang, Kim Yong Tan, Yew Soon Ong, Yueming Lyu","submitted_at":"2024-06-02T17:26:27Z","abstract_excerpt":"Diffusion models have demonstrated great potential in generating high-quality content for images, natural language, protein domains, etc. However, how to perform user-preferred targeted generation via diffusion models with only black-box target scores of users remains challenging. To address this issue, we first formulate the fine-tuning of the targeted reserve-time stochastic differential equation (SDE) associated with a pre-trained diffusion model as a sequential black-box optimization problem. Furthermore, we propose a novel covariance-adaptive sequential optimization algorithm to optimize "},"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":"2406.00812","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2024-06-02T17:26:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ec6dc13b6419ff03749a757c79a288adda7ba686e100c7048324d14ff36f2afb","abstract_canon_sha256":"cb604917ba43824c897c413ac727beeb68b463e6f9062dd591c33c85c7951fa1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:01.191973Z","signature_b64":"emMCL7J8oZ5K185tTlRnbB3eenZ8pNRvRt7CN7Gzent0hWd3blsxtcQ1toglkwXGHHGNNTGucUFcjz5gi7SlCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"131baf48e03f459fcf4fa61ce049c1045b199602a962cdb313816cb0fe87f35f","last_reissued_at":"2026-07-05T08:29:01.191501Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:01.191501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Covariance-Adaptive Sequential Black-box Optimization for Diffusion Targeted Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Ivor W. Tsang, Kim Yong Tan, Yew Soon Ong, Yueming Lyu","submitted_at":"2024-06-02T17:26:27Z","abstract_excerpt":"Diffusion models have demonstrated great potential in generating high-quality content for images, natural language, protein domains, etc. However, how to perform user-preferred targeted generation via diffusion models with only black-box target scores of users remains challenging. To address this issue, we first formulate the fine-tuning of the targeted reserve-time stochastic differential equation (SDE) associated with a pre-trained diffusion model as a sequential black-box optimization problem. Furthermore, we propose a novel covariance-adaptive sequential optimization algorithm to optimize "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00812","kind":"arxiv","version":2},"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/2406.00812/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":"2406.00812","created_at":"2026-07-05T08:29:01.191560+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.00812v2","created_at":"2026-07-05T08:29:01.191560+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00812","created_at":"2026-07-05T08:29:01.191560+00:00"},{"alias_kind":"pith_short_12","alias_value":"CMN26SHAH5CZ","created_at":"2026-07-05T08:29:01.191560+00:00"},{"alias_kind":"pith_short_16","alias_value":"CMN26SHAH5CZ7T2P","created_at":"2026-07-05T08:29:01.191560+00:00"},{"alias_kind":"pith_short_8","alias_value":"CMN26SHA","created_at":"2026-07-05T08:29:01.191560+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07950","citing_title":"Slowly Annealed Langevin Dynamics: Theory and Applications to Training-Free Guided Generation","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CMN26SHAH5CZ7T2PUYOOASOBAR","json":"https://pith.science/pith/CMN26SHAH5CZ7T2PUYOOASOBAR.json","graph_json":"https://pith.science/api/pith-number/CMN26SHAH5CZ7T2PUYOOASOBAR/graph.json","events_json":"https://pith.science/api/pith-number/CMN26SHAH5CZ7T2PUYOOASOBAR/events.json","paper":"https://pith.science/paper/CMN26SHA"},"agent_actions":{"view_html":"https://pith.science/pith/CMN26SHAH5CZ7T2PUYOOASOBAR","download_json":"https://pith.science/pith/CMN26SHAH5CZ7T2PUYOOASOBAR.json","view_paper":"https://pith.science/paper/CMN26SHA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.00812&json=true","fetch_graph":"https://pith.science/api/pith-number/CMN26SHAH5CZ7T2PUYOOASOBAR/graph.json","fetch_events":"https://pith.science/api/pith-number/CMN26SHAH5CZ7T2PUYOOASOBAR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CMN26SHAH5CZ7T2PUYOOASOBAR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CMN26SHAH5CZ7T2PUYOOASOBAR/action/storage_attestation","attest_author":"https://pith.science/pith/CMN26SHAH5CZ7T2PUYOOASOBAR/action/author_attestation","sign_citation":"https://pith.science/pith/CMN26SHAH5CZ7T2PUYOOASOBAR/action/citation_signature","submit_replication":"https://pith.science/pith/CMN26SHAH5CZ7T2PUYOOASOBAR/action/replication_record"}},"created_at":"2026-07-05T08:29:01.191560+00:00","updated_at":"2026-07-05T08:29:01.191560+00:00"}