{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NDZC5L637ZHA3PNFITCBOV56QH","short_pith_number":"pith:NDZC5L63","schema_version":"1.0","canonical_sha256":"68f22eafdbfe4e0dbda544c41757be81d76cfb6cd39e5603b96da429d2224b0d","source":{"kind":"arxiv","id":"2409.03550","version":2},"attestation_state":"computed","paper":{"title":"DKDM: Data-Free Knowledge Distillation for Diffusion Models with Any Architecture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jianlong Wu, Liqiang Nie, Miao Zhang, Qianlong Xiang, Yan Yan, Yuzhang Shang","submitted_at":"2024-09-05T14:12:22Z","abstract_excerpt":"Diffusion models (DMs) have demonstrated exceptional generative capabilities across various domains, including image, video, and so on. A key factor contributing to their effectiveness is the high quantity and quality of data used during training. However, mainstream DMs now consume increasingly large amounts of data. For example, training a Stable Diffusion model requires billions of image-text pairs. This enormous data requirement poses significant challenges for training large DMs due to high data acquisition costs and storage expenses. To alleviate this data burden, we propose a novel scen"},"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":"2409.03550","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-05T14:12:22Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"25ca69db9f964cd1d2bbd2a0c99b4f23202ae4ce46a30fe27cdeb70dd23e83d0","abstract_canon_sha256":"d92d478e3e917d3bd95f6cc0c9df4436cac4733399966510a13860ce6707e770"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:22.851016Z","signature_b64":"8PxtZoWOkomRsL7Ll6DJ+WJRGt+HZJIlXrtt6fGZfzQxLR9TqwfIT5KZ9zLC1mLY5IzMvEor6jWFw0b98eAgAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68f22eafdbfe4e0dbda544c41757be81d76cfb6cd39e5603b96da429d2224b0d","last_reissued_at":"2026-07-05T10:21:22.850506Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:22.850506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DKDM: Data-Free Knowledge Distillation for Diffusion Models with Any Architecture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jianlong Wu, Liqiang Nie, Miao Zhang, Qianlong Xiang, Yan Yan, Yuzhang Shang","submitted_at":"2024-09-05T14:12:22Z","abstract_excerpt":"Diffusion models (DMs) have demonstrated exceptional generative capabilities across various domains, including image, video, and so on. A key factor contributing to their effectiveness is the high quantity and quality of data used during training. However, mainstream DMs now consume increasingly large amounts of data. For example, training a Stable Diffusion model requires billions of image-text pairs. This enormous data requirement poses significant challenges for training large DMs due to high data acquisition costs and storage expenses. To alleviate this data burden, we propose a novel scen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.03550","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/2409.03550/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":"2409.03550","created_at":"2026-07-05T10:21:22.850563+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.03550v2","created_at":"2026-07-05T10:21:22.850563+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.03550","created_at":"2026-07-05T10:21:22.850563+00:00"},{"alias_kind":"pith_short_12","alias_value":"NDZC5L637ZHA","created_at":"2026-07-05T10:21:22.850563+00:00"},{"alias_kind":"pith_short_16","alias_value":"NDZC5L637ZHA3PNF","created_at":"2026-07-05T10:21:22.850563+00:00"},{"alias_kind":"pith_short_8","alias_value":"NDZC5L63","created_at":"2026-07-05T10:21:22.850563+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.15159","citing_title":"Acquire and then Adapt: Squeezing out Text-to-Image Model for Image Restoration","ref_index":87,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NDZC5L637ZHA3PNFITCBOV56QH","json":"https://pith.science/pith/NDZC5L637ZHA3PNFITCBOV56QH.json","graph_json":"https://pith.science/api/pith-number/NDZC5L637ZHA3PNFITCBOV56QH/graph.json","events_json":"https://pith.science/api/pith-number/NDZC5L637ZHA3PNFITCBOV56QH/events.json","paper":"https://pith.science/paper/NDZC5L63"},"agent_actions":{"view_html":"https://pith.science/pith/NDZC5L637ZHA3PNFITCBOV56QH","download_json":"https://pith.science/pith/NDZC5L637ZHA3PNFITCBOV56QH.json","view_paper":"https://pith.science/paper/NDZC5L63","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.03550&json=true","fetch_graph":"https://pith.science/api/pith-number/NDZC5L637ZHA3PNFITCBOV56QH/graph.json","fetch_events":"https://pith.science/api/pith-number/NDZC5L637ZHA3PNFITCBOV56QH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NDZC5L637ZHA3PNFITCBOV56QH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NDZC5L637ZHA3PNFITCBOV56QH/action/storage_attestation","attest_author":"https://pith.science/pith/NDZC5L637ZHA3PNFITCBOV56QH/action/author_attestation","sign_citation":"https://pith.science/pith/NDZC5L637ZHA3PNFITCBOV56QH/action/citation_signature","submit_replication":"https://pith.science/pith/NDZC5L637ZHA3PNFITCBOV56QH/action/replication_record"}},"created_at":"2026-07-05T10:21:22.850563+00:00","updated_at":"2026-07-05T10:21:22.850563+00:00"}