{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FYCHWX7BQGHOWAGA4LD4RLPRHJ","short_pith_number":"pith:FYCHWX7B","schema_version":"1.0","canonical_sha256":"2e047b5fe1818eeb00c0e2c7c8adf13a47c8e1a8fee640d7892dd8a6001457e0","source":{"kind":"arxiv","id":"2409.07032","version":1},"attestation_state":"computed","paper":{"title":"From optimal score matching to optimal sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Harrison H. Zhou, Subhodh Kotekal, Zehao Dou, Zhehao Xu","submitted_at":"2024-09-11T06:02:47Z","abstract_excerpt":"The recent, impressive advances in algorithmic generation of high-fidelity image, audio, and video are largely due to great successes in score-based diffusion models. A key implementing step is score matching, that is, the estimation of the score function of the forward diffusion process from training data. As shown in earlier literature, the total variation distance between the law of a sample generated from the trained diffusion model and the ground truth distribution can be controlled by the score matching risk.\n  Despite the widespread use of score-based diffusion models, basic theoretical"},"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":"2409.07032","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-09-11T06:02:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ec673f5b44bec918f4836ce1c6c2ff95bb16dac4e6945811f4714466ee6e94ca","abstract_canon_sha256":"c5a9a4909f773bc9a8fb848821dfee35b2918797b4bf16133ac4e1926bd8fa79"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:05:44.610492Z","signature_b64":"jDaY77rdE4f2T5XCY5L8T0XM565R7soJNlEAgf3DVNAjgBpcH5JUM6SLjvjEhoEhyg/1Y9KtgNJuA6fF3eWoAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e047b5fe1818eeb00c0e2c7c8adf13a47c8e1a8fee640d7892dd8a6001457e0","last_reissued_at":"2026-07-05T09:05:44.610012Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:05:44.610012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From optimal score matching to optimal sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Harrison H. Zhou, Subhodh Kotekal, Zehao Dou, Zhehao Xu","submitted_at":"2024-09-11T06:02:47Z","abstract_excerpt":"The recent, impressive advances in algorithmic generation of high-fidelity image, audio, and video are largely due to great successes in score-based diffusion models. A key implementing step is score matching, that is, the estimation of the score function of the forward diffusion process from training data. As shown in earlier literature, the total variation distance between the law of a sample generated from the trained diffusion model and the ground truth distribution can be controlled by the score matching risk.\n  Despite the widespread use of score-based diffusion models, basic theoretical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07032","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/2409.07032/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":"2409.07032","created_at":"2026-07-05T09:05:44.610081+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.07032v1","created_at":"2026-07-05T09:05:44.610081+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07032","created_at":"2026-07-05T09:05:44.610081+00:00"},{"alias_kind":"pith_short_12","alias_value":"FYCHWX7BQGHO","created_at":"2026-07-05T09:05:44.610081+00:00"},{"alias_kind":"pith_short_16","alias_value":"FYCHWX7BQGHOWAGA","created_at":"2026-07-05T09:05:44.610081+00:00"},{"alias_kind":"pith_short_8","alias_value":"FYCHWX7B","created_at":"2026-07-05T09:05:44.610081+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06179","citing_title":"Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06007","citing_title":"Diffusion Models for Adaptive Sequential Data Generation","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06179","citing_title":"Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07220","citing_title":"On the Robustness of Distribution Support under Diffusion Guidance","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15822","citing_title":"Intrinsic Wasserstein Rates for Score-Based Generative Models on Smooth Manifolds","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2603.20645","citing_title":"Diffusion Model for Manifold Data: Score Decomposition, Curvature, and Statistical Complexity","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07220","citing_title":"On the Robustness of Distribution Support under Diffusion Guidance","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FYCHWX7BQGHOWAGA4LD4RLPRHJ","json":"https://pith.science/pith/FYCHWX7BQGHOWAGA4LD4RLPRHJ.json","graph_json":"https://pith.science/api/pith-number/FYCHWX7BQGHOWAGA4LD4RLPRHJ/graph.json","events_json":"https://pith.science/api/pith-number/FYCHWX7BQGHOWAGA4LD4RLPRHJ/events.json","paper":"https://pith.science/paper/FYCHWX7B"},"agent_actions":{"view_html":"https://pith.science/pith/FYCHWX7BQGHOWAGA4LD4RLPRHJ","download_json":"https://pith.science/pith/FYCHWX7BQGHOWAGA4LD4RLPRHJ.json","view_paper":"https://pith.science/paper/FYCHWX7B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.07032&json=true","fetch_graph":"https://pith.science/api/pith-number/FYCHWX7BQGHOWAGA4LD4RLPRHJ/graph.json","fetch_events":"https://pith.science/api/pith-number/FYCHWX7BQGHOWAGA4LD4RLPRHJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FYCHWX7BQGHOWAGA4LD4RLPRHJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FYCHWX7BQGHOWAGA4LD4RLPRHJ/action/storage_attestation","attest_author":"https://pith.science/pith/FYCHWX7BQGHOWAGA4LD4RLPRHJ/action/author_attestation","sign_citation":"https://pith.science/pith/FYCHWX7BQGHOWAGA4LD4RLPRHJ/action/citation_signature","submit_replication":"https://pith.science/pith/FYCHWX7BQGHOWAGA4LD4RLPRHJ/action/replication_record"}},"created_at":"2026-07-05T09:05:44.610081+00:00","updated_at":"2026-07-05T09:05:44.610081+00:00"}