{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6VGFONXB63UBK53XEE5ACCD4RT","short_pith_number":"pith:6VGFONXB","schema_version":"1.0","canonical_sha256":"f54c5736e1f6e8157777213a01087c8cdf24571bd5a493eb69ad07010f9757e9","source":{"kind":"arxiv","id":"2410.16794","version":1},"attestation_state":"computed","paper":{"title":"One-Step Diffusion Distillation through Score Implicit Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Guo-jun Qi, J. Zico Kolter, Weijian Luo, Zemin Huang, Zhengyang Geng","submitted_at":"2024-10-22T08:17:20Z","abstract_excerpt":"Despite their strong performances on many generative tasks, diffusion models require a large number of sampling steps in order to generate realistic samples. This has motivated the community to develop effective methods to distill pre-trained diffusion models into more efficient models, but these methods still typically require few-step inference or perform substantially worse than the underlying model. In this paper, we present Score Implicit Matching (SIM) a new approach to distilling pre-trained diffusion models into single-step generator models, while maintaining almost the same sample gen"},"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":"2410.16794","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-22T08:17:20Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2b1a678d42937475f6bc892fb292a288f588a11f1db8dce1eda54f4b509949c8","abstract_canon_sha256":"833422f1302cb6744036ff520916c419c579084363b4cecb5d73fcd4f344c39b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:06.959987Z","signature_b64":"nVuSOJQNQmLnoTL140kZHLcC99lKjd2ms3/lXxCLastq2ehzN2foMX8d+8hRXJmHiWKS0KzaAzPfT+KigA66CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f54c5736e1f6e8157777213a01087c8cdf24571bd5a493eb69ad07010f9757e9","last_reissued_at":"2026-07-05T09:24:06.959509Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:06.959509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One-Step Diffusion Distillation through Score Implicit Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Guo-jun Qi, J. Zico Kolter, Weijian Luo, Zemin Huang, Zhengyang Geng","submitted_at":"2024-10-22T08:17:20Z","abstract_excerpt":"Despite their strong performances on many generative tasks, diffusion models require a large number of sampling steps in order to generate realistic samples. This has motivated the community to develop effective methods to distill pre-trained diffusion models into more efficient models, but these methods still typically require few-step inference or perform substantially worse than the underlying model. In this paper, we present Score Implicit Matching (SIM) a new approach to distilling pre-trained diffusion models into single-step generator models, while maintaining almost the same sample gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16794","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/2410.16794/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":"2410.16794","created_at":"2026-07-05T09:24:06.959568+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.16794v1","created_at":"2026-07-05T09:24:06.959568+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16794","created_at":"2026-07-05T09:24:06.959568+00:00"},{"alias_kind":"pith_short_12","alias_value":"6VGFONXB63UB","created_at":"2026-07-05T09:24:06.959568+00:00"},{"alias_kind":"pith_short_16","alias_value":"6VGFONXB63UBK53X","created_at":"2026-07-05T09:24:06.959568+00:00"},{"alias_kind":"pith_short_8","alias_value":"6VGFONXB","created_at":"2026-07-05T09:24:06.959568+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05254","citing_title":"Flash-WAM: Modality-Aware Distillation for World Action Models","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6VGFONXB63UBK53XEE5ACCD4RT","json":"https://pith.science/pith/6VGFONXB63UBK53XEE5ACCD4RT.json","graph_json":"https://pith.science/api/pith-number/6VGFONXB63UBK53XEE5ACCD4RT/graph.json","events_json":"https://pith.science/api/pith-number/6VGFONXB63UBK53XEE5ACCD4RT/events.json","paper":"https://pith.science/paper/6VGFONXB"},"agent_actions":{"view_html":"https://pith.science/pith/6VGFONXB63UBK53XEE5ACCD4RT","download_json":"https://pith.science/pith/6VGFONXB63UBK53XEE5ACCD4RT.json","view_paper":"https://pith.science/paper/6VGFONXB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.16794&json=true","fetch_graph":"https://pith.science/api/pith-number/6VGFONXB63UBK53XEE5ACCD4RT/graph.json","fetch_events":"https://pith.science/api/pith-number/6VGFONXB63UBK53XEE5ACCD4RT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6VGFONXB63UBK53XEE5ACCD4RT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6VGFONXB63UBK53XEE5ACCD4RT/action/storage_attestation","attest_author":"https://pith.science/pith/6VGFONXB63UBK53XEE5ACCD4RT/action/author_attestation","sign_citation":"https://pith.science/pith/6VGFONXB63UBK53XEE5ACCD4RT/action/citation_signature","submit_replication":"https://pith.science/pith/6VGFONXB63UBK53XEE5ACCD4RT/action/replication_record"}},"created_at":"2026-07-05T09:24:06.959568+00:00","updated_at":"2026-07-05T09:24:06.959568+00:00"}