{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VMNR3JIMG7ICQ5ULNXPCIKCSK7","short_pith_number":"pith:VMNR3JIM","schema_version":"1.0","canonical_sha256":"ab1b1da50c37d028768b6dde24285257f2446e435247a8a8372a18d3b55ab71a","source":{"kind":"arxiv","id":"2410.18958","version":3},"attestation_state":"computed","paper":{"title":"Stable Consistency Tuning: Understanding and Improving Consistency Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Fu-Yun Wang, Hongsheng Li, Zhengyang Geng","submitted_at":"2024-10-24T17:55:52Z","abstract_excerpt":"Diffusion models achieve superior generation quality but suffer from slow generation speed due to the iterative nature of denoising. In contrast, consistency models, a new generative family, achieve competitive performance with significantly faster sampling. These models are trained either through consistency distillation, which leverages pretrained diffusion models, or consistency training/tuning directly from raw data. In this work, we propose a novel framework for understanding consistency models by modeling the denoising process of the diffusion model as a Markov Decision Process (MDP) and"},"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":"2410.18958","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-24T17:55:52Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"96973279afbf9f2d3165525d4823748ac0d3e12a0a87bb2d36d09e92fdd659c9","abstract_canon_sha256":"bde3396909cdeda7de0698806320bccaa59dbec20991894b41c31ed293ceb3d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:16.155122Z","signature_b64":"3mUHXXcTvAKi/c0ooJaz9qhSOtVW3/YnDzM3arJJvEVszQTup8A6fPEHtU8vTOPtcv83DgDBHjUByglVtH0/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab1b1da50c37d028768b6dde24285257f2446e435247a8a8372a18d3b55ab71a","last_reissued_at":"2026-07-05T09:44:16.154635Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:16.154635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stable Consistency Tuning: Understanding and Improving Consistency Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Fu-Yun Wang, Hongsheng Li, Zhengyang Geng","submitted_at":"2024-10-24T17:55:52Z","abstract_excerpt":"Diffusion models achieve superior generation quality but suffer from slow generation speed due to the iterative nature of denoising. In contrast, consistency models, a new generative family, achieve competitive performance with significantly faster sampling. These models are trained either through consistency distillation, which leverages pretrained diffusion models, or consistency training/tuning directly from raw data. In this work, we propose a novel framework for understanding consistency models by modeling the denoising process of the diffusion model as a Markov Decision Process (MDP) and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18958","kind":"arxiv","version":3},"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/2410.18958/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":"2410.18958","created_at":"2026-07-05T09:44:16.154697+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.18958v3","created_at":"2026-07-05T09:44:16.154697+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18958","created_at":"2026-07-05T09:44:16.154697+00:00"},{"alias_kind":"pith_short_12","alias_value":"VMNR3JIMG7IC","created_at":"2026-07-05T09:44:16.154697+00:00"},{"alias_kind":"pith_short_16","alias_value":"VMNR3JIMG7ICQ5UL","created_at":"2026-07-05T09:44:16.154697+00:00"},{"alias_kind":"pith_short_8","alias_value":"VMNR3JIM","created_at":"2026-07-05T09:44:16.154697+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/VMNR3JIMG7ICQ5ULNXPCIKCSK7","json":"https://pith.science/pith/VMNR3JIMG7ICQ5ULNXPCIKCSK7.json","graph_json":"https://pith.science/api/pith-number/VMNR3JIMG7ICQ5ULNXPCIKCSK7/graph.json","events_json":"https://pith.science/api/pith-number/VMNR3JIMG7ICQ5ULNXPCIKCSK7/events.json","paper":"https://pith.science/paper/VMNR3JIM"},"agent_actions":{"view_html":"https://pith.science/pith/VMNR3JIMG7ICQ5ULNXPCIKCSK7","download_json":"https://pith.science/pith/VMNR3JIMG7ICQ5ULNXPCIKCSK7.json","view_paper":"https://pith.science/paper/VMNR3JIM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.18958&json=true","fetch_graph":"https://pith.science/api/pith-number/VMNR3JIMG7ICQ5ULNXPCIKCSK7/graph.json","fetch_events":"https://pith.science/api/pith-number/VMNR3JIMG7ICQ5ULNXPCIKCSK7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VMNR3JIMG7ICQ5ULNXPCIKCSK7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VMNR3JIMG7ICQ5ULNXPCIKCSK7/action/storage_attestation","attest_author":"https://pith.science/pith/VMNR3JIMG7ICQ5ULNXPCIKCSK7/action/author_attestation","sign_citation":"https://pith.science/pith/VMNR3JIMG7ICQ5ULNXPCIKCSK7/action/citation_signature","submit_replication":"https://pith.science/pith/VMNR3JIMG7ICQ5ULNXPCIKCSK7/action/replication_record"}},"created_at":"2026-07-05T09:44:16.154697+00:00","updated_at":"2026-07-05T09:44:16.154697+00:00"}