{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BXT4VUMBDXT64YBXHTKPVBZIDU","short_pith_number":"pith:BXT4VUMB","schema_version":"1.0","canonical_sha256":"0de7cad1811de7ee60373cd4fa87281d1ce4468cfc6c73d66fa7f28e74596bfd","source":{"kind":"arxiv","id":"2206.06227","version":2},"attestation_state":"computed","paper":{"title":"Convergence for score-based generative modeling with polynomial complexity","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":"2022-06-13T14:57:35Z","abstract_excerpt":"Score-based generative modeling (SGM) is a highly successful approach for learning a probability distribution from data and generating further samples. We prove the first polynomial convergence guarantees for the core mechanic behind SGM: drawing samples from a probability density $p$ given a score estimate (an estimate of $\\nabla \\ln p$) that is accurate in $L^2(p)$. Compared to previous works, we do not incur error that grows exponentially in time or that suffers from a curse of dimensionality. Our guarantee works for any smooth distribution and depends polynomially on its log-Sobolev consta"},"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":"2206.06227","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-13T14:57:35Z","cross_cats_sorted":["math.PR","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"405988b3bd7f292e6f97aa29e7873d11867b92f7c6e7fde0c667d923489f0ed1","abstract_canon_sha256":"3cdb98ad1797441e7ce5496390fc87dd7fd3d5f2e347d301f1a972df0ae17050"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:06:40.167604Z","signature_b64":"eoO/ND1cNDBpudWImkNAFjMnb4i8Wj4g1vnAiy7s2TPpaspmUMXkJj1SMrSHGASBgLODzaix1WhAY4vmP3APBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0de7cad1811de7ee60373cd4fa87281d1ce4468cfc6c73d66fa7f28e74596bfd","last_reissued_at":"2026-07-05T06:06:40.167178Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:06:40.167178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence for score-based generative modeling with polynomial complexity","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":"2022-06-13T14:57:35Z","abstract_excerpt":"Score-based generative modeling (SGM) is a highly successful approach for learning a probability distribution from data and generating further samples. We prove the first polynomial convergence guarantees for the core mechanic behind SGM: drawing samples from a probability density $p$ given a score estimate (an estimate of $\\nabla \\ln p$) that is accurate in $L^2(p)$. Compared to previous works, we do not incur error that grows exponentially in time or that suffers from a curse of dimensionality. Our guarantee works for any smooth distribution and depends polynomially on its log-Sobolev consta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.06227","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/2206.06227/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":"2206.06227","created_at":"2026-07-05T06:06:40.167233+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.06227v2","created_at":"2026-07-05T06:06:40.167233+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.06227","created_at":"2026-07-05T06:06:40.167233+00:00"},{"alias_kind":"pith_short_12","alias_value":"BXT4VUMBDXT6","created_at":"2026-07-05T06:06:40.167233+00:00"},{"alias_kind":"pith_short_16","alias_value":"BXT4VUMBDXT64YBX","created_at":"2026-07-05T06:06:40.167233+00:00"},{"alias_kind":"pith_short_8","alias_value":"BXT4VUMB","created_at":"2026-07-05T06:06:40.167233+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09705","citing_title":"When Do Local Score Models Extrapolate Across Size? A Diagnostic Theory and Benchmark","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22723","citing_title":"The Value of Covariance Matching in Gaussian DDPMs and the Lanczos Sampler","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2303.08797","citing_title":"Stochastic Interpolants: A Unifying Framework for Flows and Diffusions","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10857","citing_title":"Query Lower Bounds for Diffusion Sampling","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BXT4VUMBDXT64YBXHTKPVBZIDU","json":"https://pith.science/pith/BXT4VUMBDXT64YBXHTKPVBZIDU.json","graph_json":"https://pith.science/api/pith-number/BXT4VUMBDXT64YBXHTKPVBZIDU/graph.json","events_json":"https://pith.science/api/pith-number/BXT4VUMBDXT64YBXHTKPVBZIDU/events.json","paper":"https://pith.science/paper/BXT4VUMB"},"agent_actions":{"view_html":"https://pith.science/pith/BXT4VUMBDXT64YBXHTKPVBZIDU","download_json":"https://pith.science/pith/BXT4VUMBDXT64YBXHTKPVBZIDU.json","view_paper":"https://pith.science/paper/BXT4VUMB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.06227&json=true","fetch_graph":"https://pith.science/api/pith-number/BXT4VUMBDXT64YBXHTKPVBZIDU/graph.json","fetch_events":"https://pith.science/api/pith-number/BXT4VUMBDXT64YBXHTKPVBZIDU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BXT4VUMBDXT64YBXHTKPVBZIDU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BXT4VUMBDXT64YBXHTKPVBZIDU/action/storage_attestation","attest_author":"https://pith.science/pith/BXT4VUMBDXT64YBXHTKPVBZIDU/action/author_attestation","sign_citation":"https://pith.science/pith/BXT4VUMBDXT64YBXHTKPVBZIDU/action/citation_signature","submit_replication":"https://pith.science/pith/BXT4VUMBDXT64YBXHTKPVBZIDU/action/replication_record"}},"created_at":"2026-07-05T06:06:40.167233+00:00","updated_at":"2026-07-05T06:06:40.167233+00:00"}