{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FVNMXRNPMGLZB4I7WLU6ZIJNQF","short_pith_number":"pith:FVNMXRNP","schema_version":"1.0","canonical_sha256":"2d5acbc5af619790f11fb2e9eca12d8176ba91585bf18b965ccdc37da20909ec","source":{"kind":"arxiv","id":"2112.06253","version":2},"attestation_state":"computed","paper":{"title":"Up to 100$\\times$ Faster Data-free Knowledge Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gongfan Fang, Haofei Zhang, Jie Song, Kanya Mo, Mingli Song, Shitao Bei, Xinchao Wang","submitted_at":"2021-12-12T14:56:58Z","abstract_excerpt":"Data-free knowledge distillation (DFKD) has recently been attracting increasing attention from research communities, attributed to its capability to compress a model only using synthetic data. Despite the encouraging results achieved, state-of-the-art DFKD methods still suffer from the inefficiency of data synthesis, making the data-free training process extremely time-consuming and thus inapplicable for large-scale tasks. In this work, we introduce an efficacious scheme, termed as FastDFKD, that allows us to accelerate DFKD by a factor of orders of magnitude. At the heart of our approach is a"},"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":"2112.06253","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-12T14:56:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a21afcf4987b265ed16fe522dfda2b1da39c49ae42084d48598af1f0ea99e09a","abstract_canon_sha256":"2ba3c15e6aaf626a365924ab5faeb80fa177fdfc146be7f5b7f1adcc926026ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:59:53.433118Z","signature_b64":"TgU/Jvz7ipyYz70c/O07BHJgqkbAAQOE7KYOrAw9H17SGSISGy61uFpCONMtbrBGs8VxWW2KYf7TpFQaz8/8AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d5acbc5af619790f11fb2e9eca12d8176ba91585bf18b965ccdc37da20909ec","last_reissued_at":"2026-07-05T03:59:53.432642Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:59:53.432642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Up to 100$\\times$ Faster Data-free Knowledge Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gongfan Fang, Haofei Zhang, Jie Song, Kanya Mo, Mingli Song, Shitao Bei, Xinchao Wang","submitted_at":"2021-12-12T14:56:58Z","abstract_excerpt":"Data-free knowledge distillation (DFKD) has recently been attracting increasing attention from research communities, attributed to its capability to compress a model only using synthetic data. Despite the encouraging results achieved, state-of-the-art DFKD methods still suffer from the inefficiency of data synthesis, making the data-free training process extremely time-consuming and thus inapplicable for large-scale tasks. In this work, we introduce an efficacious scheme, termed as FastDFKD, that allows us to accelerate DFKD by a factor of orders of magnitude. At the heart of our approach is a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.06253","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/2112.06253/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":"2112.06253","created_at":"2026-07-05T03:59:53.432703+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.06253v2","created_at":"2026-07-05T03:59:53.432703+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.06253","created_at":"2026-07-05T03:59:53.432703+00:00"},{"alias_kind":"pith_short_12","alias_value":"FVNMXRNPMGLZ","created_at":"2026-07-05T03:59:53.432703+00:00"},{"alias_kind":"pith_short_16","alias_value":"FVNMXRNPMGLZB4I7","created_at":"2026-07-05T03:59:53.432703+00:00"},{"alias_kind":"pith_short_8","alias_value":"FVNMXRNP","created_at":"2026-07-05T03:59:53.432703+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/FVNMXRNPMGLZB4I7WLU6ZIJNQF","json":"https://pith.science/pith/FVNMXRNPMGLZB4I7WLU6ZIJNQF.json","graph_json":"https://pith.science/api/pith-number/FVNMXRNPMGLZB4I7WLU6ZIJNQF/graph.json","events_json":"https://pith.science/api/pith-number/FVNMXRNPMGLZB4I7WLU6ZIJNQF/events.json","paper":"https://pith.science/paper/FVNMXRNP"},"agent_actions":{"view_html":"https://pith.science/pith/FVNMXRNPMGLZB4I7WLU6ZIJNQF","download_json":"https://pith.science/pith/FVNMXRNPMGLZB4I7WLU6ZIJNQF.json","view_paper":"https://pith.science/paper/FVNMXRNP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.06253&json=true","fetch_graph":"https://pith.science/api/pith-number/FVNMXRNPMGLZB4I7WLU6ZIJNQF/graph.json","fetch_events":"https://pith.science/api/pith-number/FVNMXRNPMGLZB4I7WLU6ZIJNQF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FVNMXRNPMGLZB4I7WLU6ZIJNQF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FVNMXRNPMGLZB4I7WLU6ZIJNQF/action/storage_attestation","attest_author":"https://pith.science/pith/FVNMXRNPMGLZB4I7WLU6ZIJNQF/action/author_attestation","sign_citation":"https://pith.science/pith/FVNMXRNPMGLZB4I7WLU6ZIJNQF/action/citation_signature","submit_replication":"https://pith.science/pith/FVNMXRNPMGLZB4I7WLU6ZIJNQF/action/replication_record"}},"created_at":"2026-07-05T03:59:53.432703+00:00","updated_at":"2026-07-05T03:59:53.432703+00:00"}