{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:C6R2IGOCUAPTEFDG7UEY56UJQS","short_pith_number":"pith:C6R2IGOC","schema_version":"1.0","canonical_sha256":"17a3a419c2a01f321466fd098efa8984a8c50ece74350c4bf90c892977d79870","source":{"kind":"arxiv","id":"2305.18455","version":2},"attestation_state":"computed","paper":{"title":"Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jiacheng Sun, Shifeng Zhang, Tianyang Hu, Weijian Luo, Zhenguo Li, Zhihua Zhang","submitted_at":"2023-05-29T04:22:57Z","abstract_excerpt":"Due to the ease of training, ability to scale, and high sample quality, diffusion models (DMs) have become the preferred option for generative modeling, with numerous pre-trained models available for a wide variety of datasets. Containing intricate information about data distributions, pre-trained DMs are valuable assets for downstream applications. In this work, we consider learning from pre-trained DMs and transferring their knowledge to other generative models in a data-free fashion. Specifically, we propose a general framework called Diff-Instruct to instruct the training of arbitrary gene"},"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":"2305.18455","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-29T04:22:57Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"b6e5f35038fed4eaef55024b8da35639a5c244daf749636c8161cced93a08c8c","abstract_canon_sha256":"77ebadcc8d3a428ab5678d29ce683cd9f9c3a9df2fbf2939dbaa93baec4d7d5c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:33:15.246970Z","signature_b64":"/1oWhlIuI4kCKVtMpX24n1eYEhEWS8r1kmTa0oHItbgnSI0WbS2P6shNCaMg0/d90pdO6GDd57LkLxoCSnHsDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17a3a419c2a01f321466fd098efa8984a8c50ece74350c4bf90c892977d79870","last_reissued_at":"2026-07-05T07:33:15.246500Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:33:15.246500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jiacheng Sun, Shifeng Zhang, Tianyang Hu, Weijian Luo, Zhenguo Li, Zhihua Zhang","submitted_at":"2023-05-29T04:22:57Z","abstract_excerpt":"Due to the ease of training, ability to scale, and high sample quality, diffusion models (DMs) have become the preferred option for generative modeling, with numerous pre-trained models available for a wide variety of datasets. Containing intricate information about data distributions, pre-trained DMs are valuable assets for downstream applications. In this work, we consider learning from pre-trained DMs and transferring their knowledge to other generative models in a data-free fashion. Specifically, we propose a general framework called Diff-Instruct to instruct the training of arbitrary gene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18455","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/2305.18455/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":"2305.18455","created_at":"2026-07-05T07:33:15.246554+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.18455v2","created_at":"2026-07-05T07:33:15.246554+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18455","created_at":"2026-07-05T07:33:15.246554+00:00"},{"alias_kind":"pith_short_12","alias_value":"C6R2IGOCUAPT","created_at":"2026-07-05T07:33:15.246554+00:00"},{"alias_kind":"pith_short_16","alias_value":"C6R2IGOCUAPTEFDG","created_at":"2026-07-05T07:33:15.246554+00:00"},{"alias_kind":"pith_short_8","alias_value":"C6R2IGOC","created_at":"2026-07-05T07:33:15.246554+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06335","citing_title":"Bridging Diffusion Pruning and Step Distillation with Teacher-Aligned Repair","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2310.14189","citing_title":"Improved Techniques for Training Consistency Models","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C6R2IGOCUAPTEFDG7UEY56UJQS","json":"https://pith.science/pith/C6R2IGOCUAPTEFDG7UEY56UJQS.json","graph_json":"https://pith.science/api/pith-number/C6R2IGOCUAPTEFDG7UEY56UJQS/graph.json","events_json":"https://pith.science/api/pith-number/C6R2IGOCUAPTEFDG7UEY56UJQS/events.json","paper":"https://pith.science/paper/C6R2IGOC"},"agent_actions":{"view_html":"https://pith.science/pith/C6R2IGOCUAPTEFDG7UEY56UJQS","download_json":"https://pith.science/pith/C6R2IGOCUAPTEFDG7UEY56UJQS.json","view_paper":"https://pith.science/paper/C6R2IGOC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.18455&json=true","fetch_graph":"https://pith.science/api/pith-number/C6R2IGOCUAPTEFDG7UEY56UJQS/graph.json","fetch_events":"https://pith.science/api/pith-number/C6R2IGOCUAPTEFDG7UEY56UJQS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C6R2IGOCUAPTEFDG7UEY56UJQS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C6R2IGOCUAPTEFDG7UEY56UJQS/action/storage_attestation","attest_author":"https://pith.science/pith/C6R2IGOCUAPTEFDG7UEY56UJQS/action/author_attestation","sign_citation":"https://pith.science/pith/C6R2IGOCUAPTEFDG7UEY56UJQS/action/citation_signature","submit_replication":"https://pith.science/pith/C6R2IGOCUAPTEFDG7UEY56UJQS/action/replication_record"}},"created_at":"2026-07-05T07:33:15.246554+00:00","updated_at":"2026-07-05T07:33:15.246554+00:00"}