{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DSCQJXP7KB67DM6WUGPWQAHFD2","short_pith_number":"pith:DSCQJXP7","schema_version":"1.0","canonical_sha256":"1c8504ddff507df1b3d6a19f6800e51e82f5bda491065a76a43430edde394884","source":{"kind":"arxiv","id":"2502.08364","version":2},"attestation_state":"computed","paper":{"title":"A Survey on Pre-Trained Diffusion Model Distillations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hongyu Wu, Xuhui Fan, Zhangkai Wu","submitted_at":"2025-02-12T12:50:24Z","abstract_excerpt":"Diffusion Models~(DMs) have emerged as the dominant approach in Generative Artificial Intelligence (GenAI), owing to their remarkable performance in tasks such as text-to-image synthesis. However, practical DMs, such as stable diffusion, are typically trained on massive datasets and thus usually require large storage. At the same time, many steps may be required, i.e., recursively evaluating the trained neural network, to generate a high-quality image, which results in significant computational costs during sample generation. As a result, distillation methods on pre-trained DM have become wide"},"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":"2502.08364","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-12T12:50:24Z","cross_cats_sorted":[],"title_canon_sha256":"0a7e434bf95d55e1e81fa4cbebb342965115fbc9b3fb92e2752d5cf68ec5f952","abstract_canon_sha256":"20725abce8248e263078aa5af80305f3423a027064ab7082b6227362e76806d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:10.707357Z","signature_b64":"DjSDhc+qTfOwPIMlr5tNa4CO8ibOIc88zK0YmSD3nfTc1MF8zj0JwrpKt4dsjtD6FhCCejEdRHUZBM6VuiK9Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c8504ddff507df1b3d6a19f6800e51e82f5bda491065a76a43430edde394884","last_reissued_at":"2026-07-05T11:54:10.706836Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:10.706836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Pre-Trained Diffusion Model Distillations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hongyu Wu, Xuhui Fan, Zhangkai Wu","submitted_at":"2025-02-12T12:50:24Z","abstract_excerpt":"Diffusion Models~(DMs) have emerged as the dominant approach in Generative Artificial Intelligence (GenAI), owing to their remarkable performance in tasks such as text-to-image synthesis. However, practical DMs, such as stable diffusion, are typically trained on massive datasets and thus usually require large storage. At the same time, many steps may be required, i.e., recursively evaluating the trained neural network, to generate a high-quality image, which results in significant computational costs during sample generation. As a result, distillation methods on pre-trained DM have become wide"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08364","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/2502.08364/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":"2502.08364","created_at":"2026-07-05T11:54:10.706892+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.08364v2","created_at":"2026-07-05T11:54:10.706892+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08364","created_at":"2026-07-05T11:54:10.706892+00:00"},{"alias_kind":"pith_short_12","alias_value":"DSCQJXP7KB67","created_at":"2026-07-05T11:54:10.706892+00:00"},{"alias_kind":"pith_short_16","alias_value":"DSCQJXP7KB67DM6W","created_at":"2026-07-05T11:54:10.706892+00:00"},{"alias_kind":"pith_short_8","alias_value":"DSCQJXP7","created_at":"2026-07-05T11:54:10.706892+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/DSCQJXP7KB67DM6WUGPWQAHFD2","json":"https://pith.science/pith/DSCQJXP7KB67DM6WUGPWQAHFD2.json","graph_json":"https://pith.science/api/pith-number/DSCQJXP7KB67DM6WUGPWQAHFD2/graph.json","events_json":"https://pith.science/api/pith-number/DSCQJXP7KB67DM6WUGPWQAHFD2/events.json","paper":"https://pith.science/paper/DSCQJXP7"},"agent_actions":{"view_html":"https://pith.science/pith/DSCQJXP7KB67DM6WUGPWQAHFD2","download_json":"https://pith.science/pith/DSCQJXP7KB67DM6WUGPWQAHFD2.json","view_paper":"https://pith.science/paper/DSCQJXP7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.08364&json=true","fetch_graph":"https://pith.science/api/pith-number/DSCQJXP7KB67DM6WUGPWQAHFD2/graph.json","fetch_events":"https://pith.science/api/pith-number/DSCQJXP7KB67DM6WUGPWQAHFD2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DSCQJXP7KB67DM6WUGPWQAHFD2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DSCQJXP7KB67DM6WUGPWQAHFD2/action/storage_attestation","attest_author":"https://pith.science/pith/DSCQJXP7KB67DM6WUGPWQAHFD2/action/author_attestation","sign_citation":"https://pith.science/pith/DSCQJXP7KB67DM6WUGPWQAHFD2/action/citation_signature","submit_replication":"https://pith.science/pith/DSCQJXP7KB67DM6WUGPWQAHFD2/action/replication_record"}},"created_at":"2026-07-05T11:54:10.706892+00:00","updated_at":"2026-07-05T11:54:10.706892+00:00"}