{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:23CXDJ3RLPKI4V5YSFBPZMSWO3","short_pith_number":"pith:23CXDJ3R","schema_version":"1.0","canonical_sha256":"d6c571a7715bd48e57b89142fcb25676ca99865cd01fa9af5c48fef4569c40b6","source":{"kind":"arxiv","id":"2403.07030","version":2},"attestation_state":"computed","paper":{"title":"AuG-KD: Anchor-Based Mixup Generation for Out-of-Domain Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Fei Wu, Kun Kuang, Shengyu Zhang, Xinyu Duan, Yifan Zhou, Zheqi Lv, Zihao Tang","submitted_at":"2024-03-11T03:34:14Z","abstract_excerpt":"Due to privacy or patent concerns, a growing number of large models are released without granting access to their training data, making transferring their knowledge inefficient and problematic. In response, Data-Free Knowledge Distillation (DFKD) methods have emerged as direct solutions. However, simply adopting models derived from DFKD for real-world applications suffers significant performance degradation, due to the discrepancy between teachers' training data and real-world scenarios (student domain). The degradation stems from the portions of teachers' knowledge that are not applicable to "},"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":"2403.07030","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-11T03:34:14Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"d37079bc6471df307817d70142fefdf6de4780776f17d948758f1ac400a682ce","abstract_canon_sha256":"0f8f63978e3bc500af9c8cd7516c3fb3a8004dda4466615dc6b548d6851b4f60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:01.653436Z","signature_b64":"dKHiAOLm2ZZfEeg0kV1MIwDfzGWCUCNuaaRZvG3Hsmx9HIupXq3f6KOQSZkAtU7vrf0mskWKuRCxMn2w0J4rDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6c571a7715bd48e57b89142fcb25676ca99865cd01fa9af5c48fef4569c40b6","last_reissued_at":"2026-07-05T07:57:01.652843Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:01.652843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AuG-KD: Anchor-Based Mixup Generation for Out-of-Domain Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Fei Wu, Kun Kuang, Shengyu Zhang, Xinyu Duan, Yifan Zhou, Zheqi Lv, Zihao Tang","submitted_at":"2024-03-11T03:34:14Z","abstract_excerpt":"Due to privacy or patent concerns, a growing number of large models are released without granting access to their training data, making transferring their knowledge inefficient and problematic. In response, Data-Free Knowledge Distillation (DFKD) methods have emerged as direct solutions. However, simply adopting models derived from DFKD for real-world applications suffers significant performance degradation, due to the discrepancy between teachers' training data and real-world scenarios (student domain). The degradation stems from the portions of teachers' knowledge that are not applicable to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07030","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/2403.07030/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":"2403.07030","created_at":"2026-07-05T07:57:01.652915+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.07030v2","created_at":"2026-07-05T07:57:01.652915+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07030","created_at":"2026-07-05T07:57:01.652915+00:00"},{"alias_kind":"pith_short_12","alias_value":"23CXDJ3RLPKI","created_at":"2026-07-05T07:57:01.652915+00:00"},{"alias_kind":"pith_short_16","alias_value":"23CXDJ3RLPKI4V5Y","created_at":"2026-07-05T07:57:01.652915+00:00"},{"alias_kind":"pith_short_8","alias_value":"23CXDJ3R","created_at":"2026-07-05T07:57:01.652915+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12171","citing_title":"Beyond Dark Knowledge: Mixup-Based Distillation for Reliable Predictions","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2603.09465","citing_title":"EvoDriveVLA: Evolving Driving VLA Models via Collaborative Perception-Planning Distillation","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/23CXDJ3RLPKI4V5YSFBPZMSWO3","json":"https://pith.science/pith/23CXDJ3RLPKI4V5YSFBPZMSWO3.json","graph_json":"https://pith.science/api/pith-number/23CXDJ3RLPKI4V5YSFBPZMSWO3/graph.json","events_json":"https://pith.science/api/pith-number/23CXDJ3RLPKI4V5YSFBPZMSWO3/events.json","paper":"https://pith.science/paper/23CXDJ3R"},"agent_actions":{"view_html":"https://pith.science/pith/23CXDJ3RLPKI4V5YSFBPZMSWO3","download_json":"https://pith.science/pith/23CXDJ3RLPKI4V5YSFBPZMSWO3.json","view_paper":"https://pith.science/paper/23CXDJ3R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.07030&json=true","fetch_graph":"https://pith.science/api/pith-number/23CXDJ3RLPKI4V5YSFBPZMSWO3/graph.json","fetch_events":"https://pith.science/api/pith-number/23CXDJ3RLPKI4V5YSFBPZMSWO3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/23CXDJ3RLPKI4V5YSFBPZMSWO3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/23CXDJ3RLPKI4V5YSFBPZMSWO3/action/storage_attestation","attest_author":"https://pith.science/pith/23CXDJ3RLPKI4V5YSFBPZMSWO3/action/author_attestation","sign_citation":"https://pith.science/pith/23CXDJ3RLPKI4V5YSFBPZMSWO3/action/citation_signature","submit_replication":"https://pith.science/pith/23CXDJ3RLPKI4V5YSFBPZMSWO3/action/replication_record"}},"created_at":"2026-07-05T07:57:01.652915+00:00","updated_at":"2026-07-05T07:57:01.652915+00:00"}