{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TMPZPBEVKVDYWNMSQ2AAHY4A5W","short_pith_number":"pith:TMPZPBEV","schema_version":"1.0","canonical_sha256":"9b1f97849555478b3592868003e380eda953b1d8bf3925c7adcc6de1f1714380","source":{"kind":"arxiv","id":"2402.06320","version":2},"attestation_state":"computed","paper":{"title":"Particle Denoising Diffusion Sampler","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.CO"],"primary_cat":"stat.ML","authors_text":"Angus Phillips, Arnaud Doucet, George Deligiannidis, Hai-Dang Dau, Michael John Hutchinson, Valentin De Bortoli","submitted_at":"2024-02-09T11:01:35Z","abstract_excerpt":"Denoising diffusion models have become ubiquitous for generative modeling. The core idea is to transport the data distribution to a Gaussian by using a diffusion. Approximate samples from the data distribution are then obtained by estimating the time-reversal of this diffusion using score matching ideas. We follow here a similar strategy to sample from unnormalized probability densities and compute their normalizing constants. However, the time-reversed diffusion is here simulated by using an original iterative particle scheme relying on a novel score matching loss. Contrary to standard denois"},"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":"2402.06320","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-02-09T11:01:35Z","cross_cats_sorted":["cs.LG","stat.CO"],"title_canon_sha256":"3acae431a739c0cd3d46060af5150558e4f14ee2c1d5c1f0f2947a542458faa8","abstract_canon_sha256":"cb72e9a27bd7f5e39c60d71bb10e90432ea9fe535ba625388149a15667c16cef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:11.125046Z","signature_b64":"Wrtd+AJklQscEbP9M/ehK9VqWum5+lEKxdoSHaVm5FCrF+mG09pYnAg/3oxw191EprO+3vXurIQCjnogoQLYBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b1f97849555478b3592868003e380eda953b1d8bf3925c7adcc6de1f1714380","last_reissued_at":"2026-07-05T08:32:11.124548Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:11.124548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Particle Denoising Diffusion Sampler","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.CO"],"primary_cat":"stat.ML","authors_text":"Angus Phillips, Arnaud Doucet, George Deligiannidis, Hai-Dang Dau, Michael John Hutchinson, Valentin De Bortoli","submitted_at":"2024-02-09T11:01:35Z","abstract_excerpt":"Denoising diffusion models have become ubiquitous for generative modeling. The core idea is to transport the data distribution to a Gaussian by using a diffusion. Approximate samples from the data distribution are then obtained by estimating the time-reversal of this diffusion using score matching ideas. We follow here a similar strategy to sample from unnormalized probability densities and compute their normalizing constants. However, the time-reversed diffusion is here simulated by using an original iterative particle scheme relying on a novel score matching loss. Contrary to standard denois"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.06320","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/2402.06320/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":"2402.06320","created_at":"2026-07-05T08:32:11.124602+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.06320v2","created_at":"2026-07-05T08:32:11.124602+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.06320","created_at":"2026-07-05T08:32:11.124602+00:00"},{"alias_kind":"pith_short_12","alias_value":"TMPZPBEVKVDY","created_at":"2026-07-05T08:32:11.124602+00:00"},{"alias_kind":"pith_short_16","alias_value":"TMPZPBEVKVDYWNMS","created_at":"2026-07-05T08:32:11.124602+00:00"},{"alias_kind":"pith_short_8","alias_value":"TMPZPBEV","created_at":"2026-07-05T08:32:11.124602+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25169","citing_title":"Laplace-Fisher Gate Identities for Optimal Matrix-Gated Blended Score Estimation","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01144","citing_title":"Sequentially-Controlled Interactive Multi-Particle Flow-Maps for Online Feedback-Driven Search","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25169","citing_title":"Laplace-Fisher Gate Identities for Optimal Matrix-Gated Blended Score Estimation","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00337","citing_title":"FES-FM: Free Energy Surface Sampling via Reduced Flow Matching","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TMPZPBEVKVDYWNMSQ2AAHY4A5W","json":"https://pith.science/pith/TMPZPBEVKVDYWNMSQ2AAHY4A5W.json","graph_json":"https://pith.science/api/pith-number/TMPZPBEVKVDYWNMSQ2AAHY4A5W/graph.json","events_json":"https://pith.science/api/pith-number/TMPZPBEVKVDYWNMSQ2AAHY4A5W/events.json","paper":"https://pith.science/paper/TMPZPBEV"},"agent_actions":{"view_html":"https://pith.science/pith/TMPZPBEVKVDYWNMSQ2AAHY4A5W","download_json":"https://pith.science/pith/TMPZPBEVKVDYWNMSQ2AAHY4A5W.json","view_paper":"https://pith.science/paper/TMPZPBEV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.06320&json=true","fetch_graph":"https://pith.science/api/pith-number/TMPZPBEVKVDYWNMSQ2AAHY4A5W/graph.json","fetch_events":"https://pith.science/api/pith-number/TMPZPBEVKVDYWNMSQ2AAHY4A5W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TMPZPBEVKVDYWNMSQ2AAHY4A5W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TMPZPBEVKVDYWNMSQ2AAHY4A5W/action/storage_attestation","attest_author":"https://pith.science/pith/TMPZPBEVKVDYWNMSQ2AAHY4A5W/action/author_attestation","sign_citation":"https://pith.science/pith/TMPZPBEVKVDYWNMSQ2AAHY4A5W/action/citation_signature","submit_replication":"https://pith.science/pith/TMPZPBEVKVDYWNMSQ2AAHY4A5W/action/replication_record"}},"created_at":"2026-07-05T08:32:11.124602+00:00","updated_at":"2026-07-05T08:32:11.124602+00:00"}