{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MMIVV7TKG3CWBYRJXTMH6ONYDK","short_pith_number":"pith:MMIVV7TK","schema_version":"1.0","canonical_sha256":"63115afe6a36c560e229bcd87f39b81ab6ba15abc78a9e761744eafdfddd4760","source":{"kind":"arxiv","id":"2509.24710","version":2},"attestation_state":"computed","paper":{"title":"MAD: Manifold Attracted Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA"],"primary_cat":"stat.ML","authors_text":"Dennis Elbr\\\"achter, Giovanni S. Alberti, Matteo Santacesaria","submitted_at":"2025-09-29T12:40:20Z","abstract_excerpt":"Score-based diffusion models are a highly effective method for generating samples from a distribution of images. We consider scenarios where the training data comes from a noisy version of the target distribution, and present an efficiently implementable modification of the inference procedure to generate noiseless samples. Our approach is motivated by the manifold hypothesis, according to which meaningful data is concentrated around some low-dimensional manifold of a high-dimensional ambient space. The central idea is that noise manifests as low magnitude variation in off-manifold directions "},"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":"2509.24710","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-09-29T12:40:20Z","cross_cats_sorted":["cs.LG","cs.NA","math.NA"],"title_canon_sha256":"f7f20322fb6b1f7ef62450c4d2cf889b925e4a6b002e811a9ca6c0b3483fd8be","abstract_canon_sha256":"9bb69fd53baa17944923b40fdd9294b36b70ee2a466189169d5b323897b6e46e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:09:44.002631Z","signature_b64":"e2l0OuhnNapKnG7qk83qX73kJyOb+C09ZS9Nc8TdTU7ldr0Ag8eADJpjMGBIo9jJF4gRS/n0A4QdT+syoBtlAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63115afe6a36c560e229bcd87f39b81ab6ba15abc78a9e761744eafdfddd4760","last_reissued_at":"2026-06-10T01:09:44.001606Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:09:44.001606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAD: Manifold Attracted Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA"],"primary_cat":"stat.ML","authors_text":"Dennis Elbr\\\"achter, Giovanni S. Alberti, Matteo Santacesaria","submitted_at":"2025-09-29T12:40:20Z","abstract_excerpt":"Score-based diffusion models are a highly effective method for generating samples from a distribution of images. We consider scenarios where the training data comes from a noisy version of the target distribution, and present an efficiently implementable modification of the inference procedure to generate noiseless samples. Our approach is motivated by the manifold hypothesis, according to which meaningful data is concentrated around some low-dimensional manifold of a high-dimensional ambient space. The central idea is that noise manifests as low magnitude variation in off-manifold directions "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.24710","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/2509.24710/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":"2509.24710","created_at":"2026-06-10T01:09:44.001766+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.24710v2","created_at":"2026-06-10T01:09:44.001766+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.24710","created_at":"2026-06-10T01:09:44.001766+00:00"},{"alias_kind":"pith_short_12","alias_value":"MMIVV7TKG3CW","created_at":"2026-06-10T01:09:44.001766+00:00"},{"alias_kind":"pith_short_16","alias_value":"MMIVV7TKG3CWBYRJ","created_at":"2026-06-10T01:09:44.001766+00:00"},{"alias_kind":"pith_short_8","alias_value":"MMIVV7TK","created_at":"2026-06-10T01:09:44.001766+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MMIVV7TKG3CWBYRJXTMH6ONYDK","json":"https://pith.science/pith/MMIVV7TKG3CWBYRJXTMH6ONYDK.json","graph_json":"https://pith.science/api/pith-number/MMIVV7TKG3CWBYRJXTMH6ONYDK/graph.json","events_json":"https://pith.science/api/pith-number/MMIVV7TKG3CWBYRJXTMH6ONYDK/events.json","paper":"https://pith.science/paper/MMIVV7TK"},"agent_actions":{"view_html":"https://pith.science/pith/MMIVV7TKG3CWBYRJXTMH6ONYDK","download_json":"https://pith.science/pith/MMIVV7TKG3CWBYRJXTMH6ONYDK.json","view_paper":"https://pith.science/paper/MMIVV7TK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.24710&json=true","fetch_graph":"https://pith.science/api/pith-number/MMIVV7TKG3CWBYRJXTMH6ONYDK/graph.json","fetch_events":"https://pith.science/api/pith-number/MMIVV7TKG3CWBYRJXTMH6ONYDK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MMIVV7TKG3CWBYRJXTMH6ONYDK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MMIVV7TKG3CWBYRJXTMH6ONYDK/action/storage_attestation","attest_author":"https://pith.science/pith/MMIVV7TKG3CWBYRJXTMH6ONYDK/action/author_attestation","sign_citation":"https://pith.science/pith/MMIVV7TKG3CWBYRJXTMH6ONYDK/action/citation_signature","submit_replication":"https://pith.science/pith/MMIVV7TKG3CWBYRJXTMH6ONYDK/action/replication_record"}},"created_at":"2026-06-10T01:09:44.001766+00:00","updated_at":"2026-06-10T01:09:44.001766+00:00"}