{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ULK6PDFILDN22PREAC3AD7UFV5","short_pith_number":"pith:ULK6PDFI","schema_version":"1.0","canonical_sha256":"a2d5e78ca858dbad3e2400b601fe85af691cda64a419c0f1f8c12b0dcb5babed","source":{"kind":"arxiv","id":"2409.20175","version":2},"attestation_state":"computed","paper":{"title":"Ensemble Kalman Diffusion Guidance: A Derivative-free Method for Inverse Problems","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Austin Wang, Hongkai Zheng, Nikola Kovachki, Ricardo Baptista, Wenda Chu, Yisong Yue","submitted_at":"2024-09-30T10:36:41Z","abstract_excerpt":"When solving inverse problems, one increasingly popular approach is to use pre-trained diffusion models as plug-and-play priors. This framework can accommodate different forward models without re-training while preserving the generative capability of diffusion models. Despite their success in many imaging inverse problems, most existing methods rely on privileged information such as derivative, pseudo-inverse, or full knowledge about the forward model. This reliance poses a substantial limitation that restricts their use in a wide range of problems where such information is unavailable, such a"},"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":"2409.20175","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-30T10:36:41Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f632c9a92cb6a4e960534f706cfeeb1194a601831e2f9490103e4ec7e018f09d","abstract_canon_sha256":"df34e44cff3fef5a8ec3b61c1f69ebb93010217383b040cebab3cefd94732fbe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:24.767277Z","signature_b64":"CgrbbKuAzgMHM7T5aR3SPTKKRUI2+tozE1fWzwagnxaJVB6HvXCV7AOCUZVT1mSFJndeFQdIp185s2+agd2vAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2d5e78ca858dbad3e2400b601fe85af691cda64a419c0f1f8c12b0dcb5babed","last_reissued_at":"2026-07-05T11:14:24.766830Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:24.766830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ensemble Kalman Diffusion Guidance: A Derivative-free Method for Inverse Problems","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Austin Wang, Hongkai Zheng, Nikola Kovachki, Ricardo Baptista, Wenda Chu, Yisong Yue","submitted_at":"2024-09-30T10:36:41Z","abstract_excerpt":"When solving inverse problems, one increasingly popular approach is to use pre-trained diffusion models as plug-and-play priors. This framework can accommodate different forward models without re-training while preserving the generative capability of diffusion models. Despite their success in many imaging inverse problems, most existing methods rely on privileged information such as derivative, pseudo-inverse, or full knowledge about the forward model. This reliance poses a substantial limitation that restricts their use in a wide range of problems where such information is unavailable, such a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.20175","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/2409.20175/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":"2409.20175","created_at":"2026-07-05T11:14:24.766887+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.20175v2","created_at":"2026-07-05T11:14:24.766887+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.20175","created_at":"2026-07-05T11:14:24.766887+00:00"},{"alias_kind":"pith_short_12","alias_value":"ULK6PDFILDN2","created_at":"2026-07-05T11:14:24.766887+00:00"},{"alias_kind":"pith_short_16","alias_value":"ULK6PDFILDN22PRE","created_at":"2026-07-05T11:14:24.766887+00:00"},{"alias_kind":"pith_short_8","alias_value":"ULK6PDFI","created_at":"2026-07-05T11:14:24.766887+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.22597","citing_title":"Energy-Guided Generative Modeling for Low-Energy Molecular Structure Discovery","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21180","citing_title":"Uncertainty-Aware Spatiotemporal Super-Resolution Data Assimilation with Diffusion Models","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ULK6PDFILDN22PREAC3AD7UFV5","json":"https://pith.science/pith/ULK6PDFILDN22PREAC3AD7UFV5.json","graph_json":"https://pith.science/api/pith-number/ULK6PDFILDN22PREAC3AD7UFV5/graph.json","events_json":"https://pith.science/api/pith-number/ULK6PDFILDN22PREAC3AD7UFV5/events.json","paper":"https://pith.science/paper/ULK6PDFI"},"agent_actions":{"view_html":"https://pith.science/pith/ULK6PDFILDN22PREAC3AD7UFV5","download_json":"https://pith.science/pith/ULK6PDFILDN22PREAC3AD7UFV5.json","view_paper":"https://pith.science/paper/ULK6PDFI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.20175&json=true","fetch_graph":"https://pith.science/api/pith-number/ULK6PDFILDN22PREAC3AD7UFV5/graph.json","fetch_events":"https://pith.science/api/pith-number/ULK6PDFILDN22PREAC3AD7UFV5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ULK6PDFILDN22PREAC3AD7UFV5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ULK6PDFILDN22PREAC3AD7UFV5/action/storage_attestation","attest_author":"https://pith.science/pith/ULK6PDFILDN22PREAC3AD7UFV5/action/author_attestation","sign_citation":"https://pith.science/pith/ULK6PDFILDN22PREAC3AD7UFV5/action/citation_signature","submit_replication":"https://pith.science/pith/ULK6PDFILDN22PREAC3AD7UFV5/action/replication_record"}},"created_at":"2026-07-05T11:14:24.766887+00:00","updated_at":"2026-07-05T11:14:24.766887+00:00"}