{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OJVTNUCMHXDS23SB53ZU7W7LZR","short_pith_number":"pith:OJVTNUCM","schema_version":"1.0","canonical_sha256":"726b36d04c3dc72d6e41eef34fdbebcc5085ee550193187671cfd6463761064a","source":{"kind":"arxiv","id":"2402.08667","version":1},"attestation_state":"computed","paper":{"title":"Target Score Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.CO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arnaud Doucet, Michael Hutchinson, Peter Wirnsberger, Valentin De Bortoli","submitted_at":"2024-02-13T18:48:28Z","abstract_excerpt":"Denoising Score Matching estimates the score of a noised version of a target distribution by minimizing a regression loss and is widely used to train the popular class of Denoising Diffusion Models. A well known limitation of Denoising Score Matching, however, is that it yields poor estimates of the score at low noise levels. This issue is particularly unfavourable for problems in the physical sciences and for Monte Carlo sampling tasks for which the score of the clean original target is known. Intuitively, estimating the score of a slightly noised version of the target should be a simple task"},"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":"2402.08667","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-13T18:48:28Z","cross_cats_sorted":["stat.CO","stat.ML"],"title_canon_sha256":"1a63ccb828d1b1c8bfc962869ea2389dabc03928095f2cb068b095113c8fdfb3","abstract_canon_sha256":"9eafac98d2c278bda7e21c6d01625fc601f11ee07273627461be18aaf75a48d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:44:49.382196Z","signature_b64":"dAaDcSMoukOjaMDSts2jz+MNDhF1TeqLbi/92BXdfyhXTEiEa/N5zS+bvxlljAiH00PT4pQUebDQShUUUgzJDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"726b36d04c3dc72d6e41eef34fdbebcc5085ee550193187671cfd6463761064a","last_reissued_at":"2026-07-05T07:44:49.381650Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:44:49.381650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Target Score Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.CO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arnaud Doucet, Michael Hutchinson, Peter Wirnsberger, Valentin De Bortoli","submitted_at":"2024-02-13T18:48:28Z","abstract_excerpt":"Denoising Score Matching estimates the score of a noised version of a target distribution by minimizing a regression loss and is widely used to train the popular class of Denoising Diffusion Models. A well known limitation of Denoising Score Matching, however, is that it yields poor estimates of the score at low noise levels. This issue is particularly unfavourable for problems in the physical sciences and for Monte Carlo sampling tasks for which the score of the clean original target is known. Intuitively, estimating the score of a slightly noised version of the target should be a simple task"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08667","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/2402.08667/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":"2402.08667","created_at":"2026-07-05T07:44:49.381710+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.08667v1","created_at":"2026-07-05T07:44:49.381710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08667","created_at":"2026-07-05T07:44:49.381710+00:00"},{"alias_kind":"pith_short_12","alias_value":"OJVTNUCMHXDS","created_at":"2026-07-05T07:44:49.381710+00:00"},{"alias_kind":"pith_short_16","alias_value":"OJVTNUCMHXDS23SB","created_at":"2026-07-05T07:44:49.381710+00:00"},{"alias_kind":"pith_short_8","alias_value":"OJVTNUCM","created_at":"2026-07-05T07:44:49.381710+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08335","citing_title":"Bayesian Experimental Design via Score Matching","ref_index":115,"is_internal_anchor":true},{"citing_arxiv_id":"2606.25169","citing_title":"Laplace-Fisher Gate Identities for Optimal Matrix-Gated Blended Score Estimation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31498","citing_title":"Scalable Inference-Time Annealing with Surrogate Likelihood Estimators","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25169","citing_title":"Laplace-Fisher Gate Identities for Optimal Matrix-Gated Blended Score Estimation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2603.25980","citing_title":"A Priori Sampling of Transition States with Guided Diffusion","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00337","citing_title":"FES-FM: Free Energy Surface Sampling via Reduced Flow Matching","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21809","citing_title":"Quotient-Space Diffusion Models","ref_index":110,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OJVTNUCMHXDS23SB53ZU7W7LZR","json":"https://pith.science/pith/OJVTNUCMHXDS23SB53ZU7W7LZR.json","graph_json":"https://pith.science/api/pith-number/OJVTNUCMHXDS23SB53ZU7W7LZR/graph.json","events_json":"https://pith.science/api/pith-number/OJVTNUCMHXDS23SB53ZU7W7LZR/events.json","paper":"https://pith.science/paper/OJVTNUCM"},"agent_actions":{"view_html":"https://pith.science/pith/OJVTNUCMHXDS23SB53ZU7W7LZR","download_json":"https://pith.science/pith/OJVTNUCMHXDS23SB53ZU7W7LZR.json","view_paper":"https://pith.science/paper/OJVTNUCM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.08667&json=true","fetch_graph":"https://pith.science/api/pith-number/OJVTNUCMHXDS23SB53ZU7W7LZR/graph.json","fetch_events":"https://pith.science/api/pith-number/OJVTNUCMHXDS23SB53ZU7W7LZR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OJVTNUCMHXDS23SB53ZU7W7LZR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OJVTNUCMHXDS23SB53ZU7W7LZR/action/storage_attestation","attest_author":"https://pith.science/pith/OJVTNUCMHXDS23SB53ZU7W7LZR/action/author_attestation","sign_citation":"https://pith.science/pith/OJVTNUCMHXDS23SB53ZU7W7LZR/action/citation_signature","submit_replication":"https://pith.science/pith/OJVTNUCMHXDS23SB53ZU7W7LZR/action/replication_record"}},"created_at":"2026-07-05T07:44:49.381710+00:00","updated_at":"2026-07-05T07:44:49.381710+00:00"}