{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4F7B2N6YTTERIFJOBHLILHMPXE","short_pith_number":"pith:4F7B2N6Y","schema_version":"1.0","canonical_sha256":"e17e1d37d89cc914152e09d6859d8fb90af7c8a69fdb7b413890eb46eaff89d4","source":{"kind":"arxiv","id":"2407.07998","version":1},"attestation_state":"computed","paper":{"title":"What's the score? Automated Denoising Score Matching for Nonlinear Diffusions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mark Goldstein, Raghav Singhal, Rajesh Ranganath","submitted_at":"2024-07-10T19:02:19Z","abstract_excerpt":"Reversing a diffusion process by learning its score forms the heart of diffusion-based generative modeling and for estimating properties of scientific systems. The diffusion processes that are tractable center on linear processes with a Gaussian stationary distribution. This limits the kinds of models that can be built to those that target a Gaussian prior or more generally limits the kinds of problems that can be generically solved to those that have conditionally linear score functions. In this work, we introduce a family of tractable denoising score matching objectives, called local-DSM, bu"},"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":"2407.07998","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-10T19:02:19Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"143939b006a12ac764d19ef61f27e8730ebe0e08ab69e1c7cf0ef50d7f33411c","abstract_canon_sha256":"1e533736d4479b42d9f117e399718c9c7f1c4ccfce9a2c6d8af7397dfc8424f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:41.635618Z","signature_b64":"pmAjQ4ppTdQbnrLq9bGUNl6z+DmUKxHa9094wFP45t1vpGqEH57t+nE932zGU3nXRErbo1ck7NmwL5KpDp7NCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e17e1d37d89cc914152e09d6859d8fb90af7c8a69fdb7b413890eb46eaff89d4","last_reissued_at":"2026-07-05T08:42:41.635173Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:41.635173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What's the score? Automated Denoising Score Matching for Nonlinear Diffusions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mark Goldstein, Raghav Singhal, Rajesh Ranganath","submitted_at":"2024-07-10T19:02:19Z","abstract_excerpt":"Reversing a diffusion process by learning its score forms the heart of diffusion-based generative modeling and for estimating properties of scientific systems. The diffusion processes that are tractable center on linear processes with a Gaussian stationary distribution. This limits the kinds of models that can be built to those that target a Gaussian prior or more generally limits the kinds of problems that can be generically solved to those that have conditionally linear score functions. In this work, we introduce a family of tractable denoising score matching objectives, called local-DSM, bu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07998","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/2407.07998/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":"2407.07998","created_at":"2026-07-05T08:42:41.635232+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.07998v1","created_at":"2026-07-05T08:42:41.635232+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07998","created_at":"2026-07-05T08:42:41.635232+00:00"},{"alias_kind":"pith_short_12","alias_value":"4F7B2N6YTTER","created_at":"2026-07-05T08:42:41.635232+00:00"},{"alias_kind":"pith_short_16","alias_value":"4F7B2N6YTTERIFJO","created_at":"2026-07-05T08:42:41.635232+00:00"},{"alias_kind":"pith_short_8","alias_value":"4F7B2N6Y","created_at":"2026-07-05T08:42:41.635232+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.19448","citing_title":"Reduced-Order Modeling of Cyclo-Stationary Time Series Using Score-Based Generative Methods","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4F7B2N6YTTERIFJOBHLILHMPXE","json":"https://pith.science/pith/4F7B2N6YTTERIFJOBHLILHMPXE.json","graph_json":"https://pith.science/api/pith-number/4F7B2N6YTTERIFJOBHLILHMPXE/graph.json","events_json":"https://pith.science/api/pith-number/4F7B2N6YTTERIFJOBHLILHMPXE/events.json","paper":"https://pith.science/paper/4F7B2N6Y"},"agent_actions":{"view_html":"https://pith.science/pith/4F7B2N6YTTERIFJOBHLILHMPXE","download_json":"https://pith.science/pith/4F7B2N6YTTERIFJOBHLILHMPXE.json","view_paper":"https://pith.science/paper/4F7B2N6Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.07998&json=true","fetch_graph":"https://pith.science/api/pith-number/4F7B2N6YTTERIFJOBHLILHMPXE/graph.json","fetch_events":"https://pith.science/api/pith-number/4F7B2N6YTTERIFJOBHLILHMPXE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4F7B2N6YTTERIFJOBHLILHMPXE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4F7B2N6YTTERIFJOBHLILHMPXE/action/storage_attestation","attest_author":"https://pith.science/pith/4F7B2N6YTTERIFJOBHLILHMPXE/action/author_attestation","sign_citation":"https://pith.science/pith/4F7B2N6YTTERIFJOBHLILHMPXE/action/citation_signature","submit_replication":"https://pith.science/pith/4F7B2N6YTTERIFJOBHLILHMPXE/action/replication_record"}},"created_at":"2026-07-05T08:42:41.635232+00:00","updated_at":"2026-07-05T08:42:41.635232+00:00"}