{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:73LIABD3ZQPOHWNUAX5NGPW5OT","short_pith_number":"pith:73LIABD3","schema_version":"1.0","canonical_sha256":"fed680047bcc1ee3d9b405fad33edd74d9360d6342cec55a8bd33e7892a8a8f0","source":{"kind":"arxiv","id":"2504.00870","version":1},"attestation_state":"computed","paper":{"title":"Data-free Knowledge Distillation with Diffusion Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Xiao, Jun Yu, Long Peng, Mei Han, Peng Chang, Qiang Ling, Renda Li, Xiaohua Qi, Ziyi Chen","submitted_at":"2025-04-01T15:00:33Z","abstract_excerpt":"Recently Data-Free Knowledge Distillation (DFKD) has garnered attention and can transfer knowledge from a teacher neural network to a student neural network without requiring any access to training data. Although diffusion models are adept at synthesizing high-fidelity photorealistic images across various domains, existing methods cannot be easiliy implemented to DFKD. To bridge that gap, this paper proposes a novel approach based on diffusion models, DiffDFKD. Specifically, DiffDFKD involves targeted optimizations in two key areas. Firstly, DiffDFKD utilizes valuable information from teacher "},"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":"2504.00870","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-01T15:00:33Z","cross_cats_sorted":[],"title_canon_sha256":"2208fe7a092c89629dbfcf7f7942527b3e768cb8b81619b8d8e9c776249e2be8","abstract_canon_sha256":"5cb240fb52c0a57599294c28f8e130e97dbbc9700e2fdb756fd0f93aec1eba1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:51.776406Z","signature_b64":"qEXwzYItI+XJFvW2PltHvMxle7/P+MnmLLgJkDYBWTkX1KKTcWm3JSkhi1uVJMyOu7nrwxNsMpoxb6+w2TAmAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fed680047bcc1ee3d9b405fad33edd74d9360d6342cec55a8bd33e7892a8a8f0","last_reissued_at":"2026-07-05T10:42:51.775894Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:51.775894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-free Knowledge Distillation with Diffusion Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Xiao, Jun Yu, Long Peng, Mei Han, Peng Chang, Qiang Ling, Renda Li, Xiaohua Qi, Ziyi Chen","submitted_at":"2025-04-01T15:00:33Z","abstract_excerpt":"Recently Data-Free Knowledge Distillation (DFKD) has garnered attention and can transfer knowledge from a teacher neural network to a student neural network without requiring any access to training data. Although diffusion models are adept at synthesizing high-fidelity photorealistic images across various domains, existing methods cannot be easiliy implemented to DFKD. To bridge that gap, this paper proposes a novel approach based on diffusion models, DiffDFKD. Specifically, DiffDFKD involves targeted optimizations in two key areas. Firstly, DiffDFKD utilizes valuable information from teacher "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00870","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/2504.00870/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":"2504.00870","created_at":"2026-07-05T10:42:51.775960+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.00870v1","created_at":"2026-07-05T10:42:51.775960+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00870","created_at":"2026-07-05T10:42:51.775960+00:00"},{"alias_kind":"pith_short_12","alias_value":"73LIABD3ZQPO","created_at":"2026-07-05T10:42:51.775960+00:00"},{"alias_kind":"pith_short_16","alias_value":"73LIABD3ZQPOHWNU","created_at":"2026-07-05T10:42:51.775960+00:00"},{"alias_kind":"pith_short_8","alias_value":"73LIABD3","created_at":"2026-07-05T10:42:51.775960+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.01602","citing_title":"Enhancing Zero-Shot Brain Tumor Subtype Classification via Fine-Grained Patch-Text Alignment","ref_index":109,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/73LIABD3ZQPOHWNUAX5NGPW5OT","json":"https://pith.science/pith/73LIABD3ZQPOHWNUAX5NGPW5OT.json","graph_json":"https://pith.science/api/pith-number/73LIABD3ZQPOHWNUAX5NGPW5OT/graph.json","events_json":"https://pith.science/api/pith-number/73LIABD3ZQPOHWNUAX5NGPW5OT/events.json","paper":"https://pith.science/paper/73LIABD3"},"agent_actions":{"view_html":"https://pith.science/pith/73LIABD3ZQPOHWNUAX5NGPW5OT","download_json":"https://pith.science/pith/73LIABD3ZQPOHWNUAX5NGPW5OT.json","view_paper":"https://pith.science/paper/73LIABD3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.00870&json=true","fetch_graph":"https://pith.science/api/pith-number/73LIABD3ZQPOHWNUAX5NGPW5OT/graph.json","fetch_events":"https://pith.science/api/pith-number/73LIABD3ZQPOHWNUAX5NGPW5OT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/73LIABD3ZQPOHWNUAX5NGPW5OT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/73LIABD3ZQPOHWNUAX5NGPW5OT/action/storage_attestation","attest_author":"https://pith.science/pith/73LIABD3ZQPOHWNUAX5NGPW5OT/action/author_attestation","sign_citation":"https://pith.science/pith/73LIABD3ZQPOHWNUAX5NGPW5OT/action/citation_signature","submit_replication":"https://pith.science/pith/73LIABD3ZQPOHWNUAX5NGPW5OT/action/replication_record"}},"created_at":"2026-07-05T10:42:51.775960+00:00","updated_at":"2026-07-05T10:42:51.775960+00:00"}