{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:V5356UHBZ47CWVFDXUYYQ5ME6P","short_pith_number":"pith:V5356UHB","schema_version":"1.0","canonical_sha256":"af77df50e1cf3e2b54a3bd31887584f3ea55fe10e5e71427bd847d6170be17a2","source":{"kind":"arxiv","id":"2209.12381","version":2},"attestation_state":"computed","paper":{"title":"Convergence of score-based generative modeling for general data distributions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.PR","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Holden Lee, Jianfeng Lu, Yixin Tan","submitted_at":"2022-09-26T02:38:36Z","abstract_excerpt":"Score-based generative modeling (SGM) has grown to be a hugely successful method for learning to generate samples from complex data distributions such as that of images and audio. It is based on evolving an SDE that transforms white noise into a sample from the learned distribution, using estimates of the score function, or gradient log-pdf. Previous convergence analyses for these methods have suffered either from strong assumptions on the data distribution or exponential dependencies, and hence fail to give efficient guarantees for the multimodal and non-smooth distributions that arise in pra"},"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":"2209.12381","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-26T02:38:36Z","cross_cats_sorted":["math.PR","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"5597072375f9f22fb4e7dba79ec5c1a815cc3a5f052b7928957ae18fe4e5f4dd","abstract_canon_sha256":"dc045863a77b013dff753db8eaa0519c31831416bb80363b2389c00a4108f51b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:02:44.779937Z","signature_b64":"0Urs+yIkcliBNY+d0A/nTOiyxp3bSCFPL86E5ZiR5omFbAVrlRMoE+pgDA2p7uLalfj1kdX3QXZNuXSg2422AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af77df50e1cf3e2b54a3bd31887584f3ea55fe10e5e71427bd847d6170be17a2","last_reissued_at":"2026-07-05T05:02:44.779421Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:02:44.779421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence of score-based generative modeling for general data distributions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.PR","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Holden Lee, Jianfeng Lu, Yixin Tan","submitted_at":"2022-09-26T02:38:36Z","abstract_excerpt":"Score-based generative modeling (SGM) has grown to be a hugely successful method for learning to generate samples from complex data distributions such as that of images and audio. It is based on evolving an SDE that transforms white noise into a sample from the learned distribution, using estimates of the score function, or gradient log-pdf. Previous convergence analyses for these methods have suffered either from strong assumptions on the data distribution or exponential dependencies, and hence fail to give efficient guarantees for the multimodal and non-smooth distributions that arise in pra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.12381","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/2209.12381/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":"2209.12381","created_at":"2026-07-05T05:02:44.779489+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.12381v2","created_at":"2026-07-05T05:02:44.779489+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.12381","created_at":"2026-07-05T05:02:44.779489+00:00"},{"alias_kind":"pith_short_12","alias_value":"V5356UHBZ47C","created_at":"2026-07-05T05:02:44.779489+00:00"},{"alias_kind":"pith_short_16","alias_value":"V5356UHBZ47CWVFD","created_at":"2026-07-05T05:02:44.779489+00:00"},{"alias_kind":"pith_short_8","alias_value":"V5356UHB","created_at":"2026-07-05T05:02:44.779489+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/V5356UHBZ47CWVFDXUYYQ5ME6P","json":"https://pith.science/pith/V5356UHBZ47CWVFDXUYYQ5ME6P.json","graph_json":"https://pith.science/api/pith-number/V5356UHBZ47CWVFDXUYYQ5ME6P/graph.json","events_json":"https://pith.science/api/pith-number/V5356UHBZ47CWVFDXUYYQ5ME6P/events.json","paper":"https://pith.science/paper/V5356UHB"},"agent_actions":{"view_html":"https://pith.science/pith/V5356UHBZ47CWVFDXUYYQ5ME6P","download_json":"https://pith.science/pith/V5356UHBZ47CWVFDXUYYQ5ME6P.json","view_paper":"https://pith.science/paper/V5356UHB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.12381&json=true","fetch_graph":"https://pith.science/api/pith-number/V5356UHBZ47CWVFDXUYYQ5ME6P/graph.json","fetch_events":"https://pith.science/api/pith-number/V5356UHBZ47CWVFDXUYYQ5ME6P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V5356UHBZ47CWVFDXUYYQ5ME6P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V5356UHBZ47CWVFDXUYYQ5ME6P/action/storage_attestation","attest_author":"https://pith.science/pith/V5356UHBZ47CWVFDXUYYQ5ME6P/action/author_attestation","sign_citation":"https://pith.science/pith/V5356UHBZ47CWVFDXUYYQ5ME6P/action/citation_signature","submit_replication":"https://pith.science/pith/V5356UHBZ47CWVFDXUYYQ5ME6P/action/replication_record"}},"created_at":"2026-07-05T05:02:44.779489+00:00","updated_at":"2026-07-05T05:02:44.779489+00:00"}