{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UOP2IAYVJKCDDY6A2XZP6X25ZN","short_pith_number":"pith:UOP2IAYV","schema_version":"1.0","canonical_sha256":"a39fa403154a8431e3c0d5f2ff5f5dcb74186bb7107b7ec49c245e8a203d85af","source":{"kind":"arxiv","id":"2502.01441","version":2},"attestation_state":"computed","paper":{"title":"Improved Training Technique for Latent Consistency Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Di Liu, Dimitris Metaxas, Khanh Doan, Quan Dao, Trung Le","submitted_at":"2025-02-03T15:25:58Z","abstract_excerpt":"Consistency models are a new family of generative models capable of producing high-quality samples in either a single step or multiple steps. Recently, consistency models have demonstrated impressive performance, achieving results on par with diffusion models in the pixel space. However, the success of scaling consistency training to large-scale datasets, particularly for text-to-image and video generation tasks, is determined by performance in the latent space. In this work, we analyze the statistical differences between pixel and latent spaces, discovering that latent data often contains hig"},"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":"2502.01441","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-03T15:25:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5eb38dc3aec564124ace34e9b7e27e6f83fb3012cccfc071b4e862d88dcb8837","abstract_canon_sha256":"493c1cd401b91ee64a61c86008ae4cf1893cf341d36c952ca508516b601c8608"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:41.786103Z","signature_b64":"79rYP5/iATe0juRTjxRH4o1B4qlb9O+LSntqG16IRgggN1fV/leqMCFpeHT9pPKsv8W3irtOP7MQ4pF2URIaCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a39fa403154a8431e3c0d5f2ff5f5dcb74186bb7107b7ec49c245e8a203d85af","last_reissued_at":"2026-07-05T10:38:41.785631Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:41.785631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved Training Technique for Latent Consistency Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Di Liu, Dimitris Metaxas, Khanh Doan, Quan Dao, Trung Le","submitted_at":"2025-02-03T15:25:58Z","abstract_excerpt":"Consistency models are a new family of generative models capable of producing high-quality samples in either a single step or multiple steps. Recently, consistency models have demonstrated impressive performance, achieving results on par with diffusion models in the pixel space. However, the success of scaling consistency training to large-scale datasets, particularly for text-to-image and video generation tasks, is determined by performance in the latent space. In this work, we analyze the statistical differences between pixel and latent spaces, discovering that latent data often contains hig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01441","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/2502.01441/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":"2502.01441","created_at":"2026-07-05T10:38:41.785688+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.01441v2","created_at":"2026-07-05T10:38:41.785688+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01441","created_at":"2026-07-05T10:38:41.785688+00:00"},{"alias_kind":"pith_short_12","alias_value":"UOP2IAYVJKCD","created_at":"2026-07-05T10:38:41.785688+00:00"},{"alias_kind":"pith_short_16","alias_value":"UOP2IAYVJKCDDY6A","created_at":"2026-07-05T10:38:41.785688+00:00"},{"alias_kind":"pith_short_8","alias_value":"UOP2IAYV","created_at":"2026-07-05T10:38:41.785688+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.26357","citing_title":"MPDiT: Multi-Patch Global-to-Local Transformer Architecture For Efficient Flow Matching and Diffusion Model","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08837","citing_title":"Discrete Meanflow Training Curriculum","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15911","citing_title":"Efficient Video Diffusion Models: Advancements and Challenges","ref_index":250,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UOP2IAYVJKCDDY6A2XZP6X25ZN","json":"https://pith.science/pith/UOP2IAYVJKCDDY6A2XZP6X25ZN.json","graph_json":"https://pith.science/api/pith-number/UOP2IAYVJKCDDY6A2XZP6X25ZN/graph.json","events_json":"https://pith.science/api/pith-number/UOP2IAYVJKCDDY6A2XZP6X25ZN/events.json","paper":"https://pith.science/paper/UOP2IAYV"},"agent_actions":{"view_html":"https://pith.science/pith/UOP2IAYVJKCDDY6A2XZP6X25ZN","download_json":"https://pith.science/pith/UOP2IAYVJKCDDY6A2XZP6X25ZN.json","view_paper":"https://pith.science/paper/UOP2IAYV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.01441&json=true","fetch_graph":"https://pith.science/api/pith-number/UOP2IAYVJKCDDY6A2XZP6X25ZN/graph.json","fetch_events":"https://pith.science/api/pith-number/UOP2IAYVJKCDDY6A2XZP6X25ZN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UOP2IAYVJKCDDY6A2XZP6X25ZN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UOP2IAYVJKCDDY6A2XZP6X25ZN/action/storage_attestation","attest_author":"https://pith.science/pith/UOP2IAYVJKCDDY6A2XZP6X25ZN/action/author_attestation","sign_citation":"https://pith.science/pith/UOP2IAYVJKCDDY6A2XZP6X25ZN/action/citation_signature","submit_replication":"https://pith.science/pith/UOP2IAYVJKCDDY6A2XZP6X25ZN/action/replication_record"}},"created_at":"2026-07-05T10:38:41.785688+00:00","updated_at":"2026-07-05T10:38:41.785688+00:00"}