{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:L7SP64VT6NBVNWSGTNZKB3TXMZ","short_pith_number":"pith:L7SP64VT","schema_version":"1.0","canonical_sha256":"5fe4ff72b3f34356da469b72a0ee7766434e5e9fb22c06fad85267b47a7eae2c","source":{"kind":"arxiv","id":"2304.04262","version":1},"attestation_state":"computed","paper":{"title":"A Comprehensive Survey on Knowledge Distillation of Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Weijian Luo","submitted_at":"2023-04-09T15:49:28Z","abstract_excerpt":"Diffusion Models (DMs), also referred to as score-based diffusion models, utilize neural networks to specify score functions. Unlike most other probabilistic models, DMs directly model the score functions, which makes them more flexible to parametrize and potentially highly expressive for probabilistic modeling. DMs can learn fine-grained knowledge, i.e., marginal score functions, of the underlying distribution. Therefore, a crucial research direction is to explore how to distill the knowledge of DMs and fully utilize their potential. Our objective is to provide a comprehensible overview of th"},"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":"2304.04262","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-09T15:49:28Z","cross_cats_sorted":[],"title_canon_sha256":"0a0dc0beeadd4d35d492d7b7d119138d05c804bd7f7e423240d416966d2f0b66","abstract_canon_sha256":"3bfa013af121d109223845d9ca0755c04c55bd814e67398cc4b84e79d9f676b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:59:14.064947Z","signature_b64":"PP+TucbEVb8DvdX1vIEMCfRIZAp82w62+CPY7TllZVJ3Xk55lFRhUinVW9Fy+k2wgNLRnE+rC2ojQSo7CUcQDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fe4ff72b3f34356da469b72a0ee7766434e5e9fb22c06fad85267b47a7eae2c","last_reissued_at":"2026-07-05T05:59:14.064606Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:59:14.064606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comprehensive Survey on Knowledge Distillation of Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Weijian Luo","submitted_at":"2023-04-09T15:49:28Z","abstract_excerpt":"Diffusion Models (DMs), also referred to as score-based diffusion models, utilize neural networks to specify score functions. Unlike most other probabilistic models, DMs directly model the score functions, which makes them more flexible to parametrize and potentially highly expressive for probabilistic modeling. DMs can learn fine-grained knowledge, i.e., marginal score functions, of the underlying distribution. Therefore, a crucial research direction is to explore how to distill the knowledge of DMs and fully utilize their potential. Our objective is to provide a comprehensible overview of th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.04262","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/2304.04262/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":"2304.04262","created_at":"2026-07-05T05:59:14.064663+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.04262v1","created_at":"2026-07-05T05:59:14.064663+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.04262","created_at":"2026-07-05T05:59:14.064663+00:00"},{"alias_kind":"pith_short_12","alias_value":"L7SP64VT6NBV","created_at":"2026-07-05T05:59:14.064663+00:00"},{"alias_kind":"pith_short_16","alias_value":"L7SP64VT6NBVNWSG","created_at":"2026-07-05T05:59:14.064663+00:00"},{"alias_kind":"pith_short_8","alias_value":"L7SP64VT","created_at":"2026-07-05T05:59:14.064663+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13426","citing_title":"Accelerating Speculative Diffusions via Block Verification","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25042","citing_title":"Unbiased Diffusion Variational Inversion via Principled Posterior Matching","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2410.12557","citing_title":"One Step Diffusion via Shortcut Models","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12183","citing_title":"DriftXpress: Faster Drifting Models via Projected RKHS Fields","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L7SP64VT6NBVNWSGTNZKB3TXMZ","json":"https://pith.science/pith/L7SP64VT6NBVNWSGTNZKB3TXMZ.json","graph_json":"https://pith.science/api/pith-number/L7SP64VT6NBVNWSGTNZKB3TXMZ/graph.json","events_json":"https://pith.science/api/pith-number/L7SP64VT6NBVNWSGTNZKB3TXMZ/events.json","paper":"https://pith.science/paper/L7SP64VT"},"agent_actions":{"view_html":"https://pith.science/pith/L7SP64VT6NBVNWSGTNZKB3TXMZ","download_json":"https://pith.science/pith/L7SP64VT6NBVNWSGTNZKB3TXMZ.json","view_paper":"https://pith.science/paper/L7SP64VT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.04262&json=true","fetch_graph":"https://pith.science/api/pith-number/L7SP64VT6NBVNWSGTNZKB3TXMZ/graph.json","fetch_events":"https://pith.science/api/pith-number/L7SP64VT6NBVNWSGTNZKB3TXMZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L7SP64VT6NBVNWSGTNZKB3TXMZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L7SP64VT6NBVNWSGTNZKB3TXMZ/action/storage_attestation","attest_author":"https://pith.science/pith/L7SP64VT6NBVNWSGTNZKB3TXMZ/action/author_attestation","sign_citation":"https://pith.science/pith/L7SP64VT6NBVNWSGTNZKB3TXMZ/action/citation_signature","submit_replication":"https://pith.science/pith/L7SP64VT6NBVNWSGTNZKB3TXMZ/action/replication_record"}},"created_at":"2026-07-05T05:59:14.064663+00:00","updated_at":"2026-07-05T05:59:14.064663+00:00"}