{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:XREWF5H5ZM6NLVTDC7PYFEFUKF","short_pith_number":"pith:XREWF5H5","schema_version":"1.0","canonical_sha256":"bc4962f4fdcb3cd5d66317df8290b451710143023da8ac71e65c3c7b5ebfe336","source":{"kind":"arxiv","id":"2003.13960","version":1},"attestation_state":"computed","paper":{"title":"Neural Networks Are More Productive Teachers Than Human Raters: Active Mixup for Data-Efficient Knowledge Distillation from a Blackbox Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boqing Gong, Dongdong Wang, Liqiang Wang, Yandong Li","submitted_at":"2020-03-31T05:44:55Z","abstract_excerpt":"We study how to train a student deep neural network for visual recognition by distilling knowledge from a blackbox teacher model in a data-efficient manner. Progress on this problem can significantly reduce the dependence on large-scale datasets for learning high-performing visual recognition models. There are two major challenges. One is that the number of queries into the teacher model should be minimized to save computational and/or financial costs. The other is that the number of images used for the knowledge distillation should be small; otherwise, it violates our expectation of reducing "},"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":"2003.13960","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-31T05:44:55Z","cross_cats_sorted":[],"title_canon_sha256":"b267934801b989e705b2e5bd346e4a1733bec6529ff947dfa1e8698105d769e7","abstract_canon_sha256":"4c2386f80c83ef9f37152623e3b112ecf37d41d8d76a976d93ecece7e5644bee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:51:46.695818Z","signature_b64":"U6zOqjRl5n4VR/f1SY5in8tQn17rQc7r+cydhfqlc2kv4PdIJaBPBrk1wTdRxEpAs8Vwlyo5ayVOLI9lagS2Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc4962f4fdcb3cd5d66317df8290b451710143023da8ac71e65c3c7b5ebfe336","last_reissued_at":"2026-07-05T00:51:46.695391Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:51:46.695391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Networks Are More Productive Teachers Than Human Raters: Active Mixup for Data-Efficient Knowledge Distillation from a Blackbox Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boqing Gong, Dongdong Wang, Liqiang Wang, Yandong Li","submitted_at":"2020-03-31T05:44:55Z","abstract_excerpt":"We study how to train a student deep neural network for visual recognition by distilling knowledge from a blackbox teacher model in a data-efficient manner. Progress on this problem can significantly reduce the dependence on large-scale datasets for learning high-performing visual recognition models. There are two major challenges. One is that the number of queries into the teacher model should be minimized to save computational and/or financial costs. The other is that the number of images used for the knowledge distillation should be small; otherwise, it violates our expectation of reducing "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.13960","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/2003.13960/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":"2003.13960","created_at":"2026-07-05T00:51:46.695451+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.13960v1","created_at":"2026-07-05T00:51:46.695451+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.13960","created_at":"2026-07-05T00:51:46.695451+00:00"},{"alias_kind":"pith_short_12","alias_value":"XREWF5H5ZM6N","created_at":"2026-07-05T00:51:46.695451+00:00"},{"alias_kind":"pith_short_16","alias_value":"XREWF5H5ZM6NLVTD","created_at":"2026-07-05T00:51:46.695451+00:00"},{"alias_kind":"pith_short_8","alias_value":"XREWF5H5","created_at":"2026-07-05T00:51:46.695451+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09716","citing_title":"Medical Model Synthesis Architectures: A Case Study","ref_index":226,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XREWF5H5ZM6NLVTDC7PYFEFUKF","json":"https://pith.science/pith/XREWF5H5ZM6NLVTDC7PYFEFUKF.json","graph_json":"https://pith.science/api/pith-number/XREWF5H5ZM6NLVTDC7PYFEFUKF/graph.json","events_json":"https://pith.science/api/pith-number/XREWF5H5ZM6NLVTDC7PYFEFUKF/events.json","paper":"https://pith.science/paper/XREWF5H5"},"agent_actions":{"view_html":"https://pith.science/pith/XREWF5H5ZM6NLVTDC7PYFEFUKF","download_json":"https://pith.science/pith/XREWF5H5ZM6NLVTDC7PYFEFUKF.json","view_paper":"https://pith.science/paper/XREWF5H5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.13960&json=true","fetch_graph":"https://pith.science/api/pith-number/XREWF5H5ZM6NLVTDC7PYFEFUKF/graph.json","fetch_events":"https://pith.science/api/pith-number/XREWF5H5ZM6NLVTDC7PYFEFUKF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XREWF5H5ZM6NLVTDC7PYFEFUKF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XREWF5H5ZM6NLVTDC7PYFEFUKF/action/storage_attestation","attest_author":"https://pith.science/pith/XREWF5H5ZM6NLVTDC7PYFEFUKF/action/author_attestation","sign_citation":"https://pith.science/pith/XREWF5H5ZM6NLVTDC7PYFEFUKF/action/citation_signature","submit_replication":"https://pith.science/pith/XREWF5H5ZM6NLVTDC7PYFEFUKF/action/replication_record"}},"created_at":"2026-07-05T00:51:46.695451+00:00","updated_at":"2026-07-05T00:51:46.695451+00:00"}