{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GAQITL4OAVYB3ZKDV33KVLOJZI","short_pith_number":"pith:GAQITL4O","schema_version":"1.0","canonical_sha256":"302089af8e05701de543aef6aaadc9ca3735760987d3fbae22940863b1c34fe1","source":{"kind":"arxiv","id":"2308.11449","version":1},"attestation_state":"computed","paper":{"title":"Convergence guarantee for consistency models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NA","math.AP","math.PR"],"primary_cat":"math.NA","authors_text":"Junlong Lyu, Shoubo Feng, Zhitang Chen","submitted_at":"2023-08-22T13:57:35Z","abstract_excerpt":"We provide the first convergence guarantees for the Consistency Models (CMs), a newly emerging type of one-step generative models that can generate comparable samples to those generated by Diffusion Models. Our main result is that, under the basic assumptions on score-matching errors, consistency errors and smoothness of the data distribution, CMs can efficiently sample from any realistic data distribution in one step with small $W_2$ error. Our results (1) hold for $L^2$-accurate score and consistency assumption (rather than $L^\\infty$-accurate); (2) do note require strong assumptions on the "},"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":"2308.11449","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2023-08-22T13:57:35Z","cross_cats_sorted":["cs.AI","cs.NA","math.AP","math.PR"],"title_canon_sha256":"82d821ad280e0b6b32be981607cec23ba627dd7f0d791b96cbb381ff97b47534","abstract_canon_sha256":"6fdb28d9102da737aa0f782e5d7f74ab2a6c755a7b58260457cc329bc78247dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:43:34.883247Z","signature_b64":"EiZz3aWfso55vr116oFgUOwSl629L4hloe9ftNZyOdjbX7dhMyqFFbKh13R/Ui+0eVhtIA+2xtipl3KakTEMDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"302089af8e05701de543aef6aaadc9ca3735760987d3fbae22940863b1c34fe1","last_reissued_at":"2026-07-05T06:43:34.882860Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:43:34.882860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence guarantee for consistency models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NA","math.AP","math.PR"],"primary_cat":"math.NA","authors_text":"Junlong Lyu, Shoubo Feng, Zhitang Chen","submitted_at":"2023-08-22T13:57:35Z","abstract_excerpt":"We provide the first convergence guarantees for the Consistency Models (CMs), a newly emerging type of one-step generative models that can generate comparable samples to those generated by Diffusion Models. Our main result is that, under the basic assumptions on score-matching errors, consistency errors and smoothness of the data distribution, CMs can efficiently sample from any realistic data distribution in one step with small $W_2$ error. Our results (1) hold for $L^2$-accurate score and consistency assumption (rather than $L^\\infty$-accurate); (2) do note require strong assumptions on the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.11449","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/2308.11449/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":"2308.11449","created_at":"2026-07-05T06:43:34.882914+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.11449v1","created_at":"2026-07-05T06:43:34.882914+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.11449","created_at":"2026-07-05T06:43:34.882914+00:00"},{"alias_kind":"pith_short_12","alias_value":"GAQITL4OAVYB","created_at":"2026-07-05T06:43:34.882914+00:00"},{"alias_kind":"pith_short_16","alias_value":"GAQITL4OAVYB3ZKD","created_at":"2026-07-05T06:43:34.882914+00:00"},{"alias_kind":"pith_short_8","alias_value":"GAQITL4O","created_at":"2026-07-05T06:43:34.882914+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.03194","citing_title":"Convergence Of Consistency Model With Multistep Sampling Under General Data Assumptions","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GAQITL4OAVYB3ZKDV33KVLOJZI","json":"https://pith.science/pith/GAQITL4OAVYB3ZKDV33KVLOJZI.json","graph_json":"https://pith.science/api/pith-number/GAQITL4OAVYB3ZKDV33KVLOJZI/graph.json","events_json":"https://pith.science/api/pith-number/GAQITL4OAVYB3ZKDV33KVLOJZI/events.json","paper":"https://pith.science/paper/GAQITL4O"},"agent_actions":{"view_html":"https://pith.science/pith/GAQITL4OAVYB3ZKDV33KVLOJZI","download_json":"https://pith.science/pith/GAQITL4OAVYB3ZKDV33KVLOJZI.json","view_paper":"https://pith.science/paper/GAQITL4O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.11449&json=true","fetch_graph":"https://pith.science/api/pith-number/GAQITL4OAVYB3ZKDV33KVLOJZI/graph.json","fetch_events":"https://pith.science/api/pith-number/GAQITL4OAVYB3ZKDV33KVLOJZI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GAQITL4OAVYB3ZKDV33KVLOJZI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GAQITL4OAVYB3ZKDV33KVLOJZI/action/storage_attestation","attest_author":"https://pith.science/pith/GAQITL4OAVYB3ZKDV33KVLOJZI/action/author_attestation","sign_citation":"https://pith.science/pith/GAQITL4OAVYB3ZKDV33KVLOJZI/action/citation_signature","submit_replication":"https://pith.science/pith/GAQITL4OAVYB3ZKDV33KVLOJZI/action/replication_record"}},"created_at":"2026-07-05T06:43:34.882914+00:00","updated_at":"2026-07-05T06:43:34.882914+00:00"}