{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YKQTZ7VZ5DJGL42BT37X2KS5SX","short_pith_number":"pith:YKQTZ7VZ","schema_version":"1.0","canonical_sha256":"c2a13cfeb9e8d265f3419eff7d2a5d95f4f25d395cbbc43ba689f891f5847fa7","source":{"kind":"arxiv","id":"2406.01781","version":5},"attestation_state":"computed","paper":{"title":"DEFT: Efficient Fine-Tuning of Diffusion Models by Learning the Generalised $h$-transform","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Denker, Emile Mathieu, Francisco Vargas, Kieran Didi, Pietro Lio, Riccardo Barbano, Shreyas Padhy, Simon Mathis, Urszula Julia Komorowska, Vincent Dutordoir","submitted_at":"2024-06-03T20:52:34Z","abstract_excerpt":"Generative modelling paradigms based on denoising diffusion processes have emerged as a leading candidate for conditional sampling in inverse problems. In many real-world applications, we often have access to large, expensively trained unconditional diffusion models, which we aim to exploit for improving conditional sampling. Most recent approaches are motivated heuristically and lack a unifying framework, obscuring connections between them. Further, they often suffer from issues such as being very sensitive to hyperparameters, being expensive to train or needing access to weights hidden behin"},"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":"2406.01781","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T20:52:34Z","cross_cats_sorted":[],"title_canon_sha256":"a18d45b709664e09ad4d895c14aaa7cc20413ef616c77e637cdbd62ade2a867e","abstract_canon_sha256":"11db5170fcc790a7491daabb0663efaa1c0d5dd0443afe4d944c7dbdee64fbce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:21.500265Z","signature_b64":"HrCk/alPhfbKvjc0oNBbD++TM+f8kyluoGZVd7AjojueEloF8GZ4nFFu5wswcC7ZE+8F6jMiDdoD2JIvnWXHBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2a13cfeb9e8d265f3419eff7d2a5d95f4f25d395cbbc43ba689f891f5847fa7","last_reissued_at":"2026-07-05T11:06:21.499780Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:21.499780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DEFT: Efficient Fine-Tuning of Diffusion Models by Learning the Generalised $h$-transform","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Denker, Emile Mathieu, Francisco Vargas, Kieran Didi, Pietro Lio, Riccardo Barbano, Shreyas Padhy, Simon Mathis, Urszula Julia Komorowska, Vincent Dutordoir","submitted_at":"2024-06-03T20:52:34Z","abstract_excerpt":"Generative modelling paradigms based on denoising diffusion processes have emerged as a leading candidate for conditional sampling in inverse problems. In many real-world applications, we often have access to large, expensively trained unconditional diffusion models, which we aim to exploit for improving conditional sampling. Most recent approaches are motivated heuristically and lack a unifying framework, obscuring connections between them. Further, they often suffer from issues such as being very sensitive to hyperparameters, being expensive to train or needing access to weights hidden behin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01781","kind":"arxiv","version":5},"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/2406.01781/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":"2406.01781","created_at":"2026-07-05T11:06:21.499833+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01781v5","created_at":"2026-07-05T11:06:21.499833+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01781","created_at":"2026-07-05T11:06:21.499833+00:00"},{"alias_kind":"pith_short_12","alias_value":"YKQTZ7VZ5DJG","created_at":"2026-07-05T11:06:21.499833+00:00"},{"alias_kind":"pith_short_16","alias_value":"YKQTZ7VZ5DJGL42B","created_at":"2026-07-05T11:06:21.499833+00:00"},{"alias_kind":"pith_short_8","alias_value":"YKQTZ7VZ","created_at":"2026-07-05T11:06:21.499833+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06079","citing_title":"Debiasing Guidance for Discrete Diffusion with Sequential Monte Carlo","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YKQTZ7VZ5DJGL42BT37X2KS5SX","json":"https://pith.science/pith/YKQTZ7VZ5DJGL42BT37X2KS5SX.json","graph_json":"https://pith.science/api/pith-number/YKQTZ7VZ5DJGL42BT37X2KS5SX/graph.json","events_json":"https://pith.science/api/pith-number/YKQTZ7VZ5DJGL42BT37X2KS5SX/events.json","paper":"https://pith.science/paper/YKQTZ7VZ"},"agent_actions":{"view_html":"https://pith.science/pith/YKQTZ7VZ5DJGL42BT37X2KS5SX","download_json":"https://pith.science/pith/YKQTZ7VZ5DJGL42BT37X2KS5SX.json","view_paper":"https://pith.science/paper/YKQTZ7VZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01781&json=true","fetch_graph":"https://pith.science/api/pith-number/YKQTZ7VZ5DJGL42BT37X2KS5SX/graph.json","fetch_events":"https://pith.science/api/pith-number/YKQTZ7VZ5DJGL42BT37X2KS5SX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YKQTZ7VZ5DJGL42BT37X2KS5SX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YKQTZ7VZ5DJGL42BT37X2KS5SX/action/storage_attestation","attest_author":"https://pith.science/pith/YKQTZ7VZ5DJGL42BT37X2KS5SX/action/author_attestation","sign_citation":"https://pith.science/pith/YKQTZ7VZ5DJGL42BT37X2KS5SX/action/citation_signature","submit_replication":"https://pith.science/pith/YKQTZ7VZ5DJGL42BT37X2KS5SX/action/replication_record"}},"created_at":"2026-07-05T11:06:21.499833+00:00","updated_at":"2026-07-05T11:06:21.499833+00:00"}