{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YC2WL4NMZ4FHRKUTXZ6TMD4PPN","short_pith_number":"pith:YC2WL4NM","schema_version":"1.0","canonical_sha256":"c0b565f1accf0a78aa93be7d360f8f7b40db248264873dbe2072bf1f1d154b72","source":{"kind":"arxiv","id":"2305.18413","version":3},"attestation_state":"computed","paper":{"title":"Learning to Learn from APIs: Black-Box Data-Free Meta-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Baoyuan Wu, Chun Yuan, Dacheng Tao, Li Shen, Zhenyi Wang, Zixuan Hu","submitted_at":"2023-05-28T18:00:12Z","abstract_excerpt":"Data-free meta-learning (DFML) aims to enable efficient learning of new tasks by meta-learning from a collection of pre-trained models without access to the training data. Existing DFML work can only meta-learn from (i) white-box and (ii) small-scale pre-trained models (iii) with the same architecture, neglecting the more practical setting where the users only have inference access to the APIs with arbitrary model architectures and model scale inside. To solve this issue, we propose a Bi-level Data-free Meta Knowledge Distillation (BiDf-MKD) framework to transfer more general meta knowledge fr"},"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":"2305.18413","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-28T18:00:12Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"51e951711a59003229635b87f1520bc6f9e871553726a5959cefacec77ff84fd","abstract_canon_sha256":"2334615b2f40216b8cefdae286df2bf594f950098bf8eb906c7209775c50e625"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:35.616228Z","signature_b64":"oWsWyPV5juiJodOU46MEIM9UGc1TlIWcMY4b5IXdmDZT+U/W6FCpsJUUJRXAFU12jSoHipRFgb1BTFWLebOxDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0b565f1accf0a78aa93be7d360f8f7b40db248264873dbe2072bf1f1d154b72","last_reissued_at":"2026-07-05T10:14:35.615718Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:35.615718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Learn from APIs: Black-Box Data-Free Meta-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Baoyuan Wu, Chun Yuan, Dacheng Tao, Li Shen, Zhenyi Wang, Zixuan Hu","submitted_at":"2023-05-28T18:00:12Z","abstract_excerpt":"Data-free meta-learning (DFML) aims to enable efficient learning of new tasks by meta-learning from a collection of pre-trained models without access to the training data. Existing DFML work can only meta-learn from (i) white-box and (ii) small-scale pre-trained models (iii) with the same architecture, neglecting the more practical setting where the users only have inference access to the APIs with arbitrary model architectures and model scale inside. To solve this issue, we propose a Bi-level Data-free Meta Knowledge Distillation (BiDf-MKD) framework to transfer more general meta knowledge fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18413","kind":"arxiv","version":3},"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/2305.18413/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":"2305.18413","created_at":"2026-07-05T10:14:35.615776+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.18413v3","created_at":"2026-07-05T10:14:35.615776+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18413","created_at":"2026-07-05T10:14:35.615776+00:00"},{"alias_kind":"pith_short_12","alias_value":"YC2WL4NMZ4FH","created_at":"2026-07-05T10:14:35.615776+00:00"},{"alias_kind":"pith_short_16","alias_value":"YC2WL4NMZ4FHRKUT","created_at":"2026-07-05T10:14:35.615776+00:00"},{"alias_kind":"pith_short_8","alias_value":"YC2WL4NM","created_at":"2026-07-05T10:14:35.615776+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.02220","citing_title":"Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YC2WL4NMZ4FHRKUTXZ6TMD4PPN","json":"https://pith.science/pith/YC2WL4NMZ4FHRKUTXZ6TMD4PPN.json","graph_json":"https://pith.science/api/pith-number/YC2WL4NMZ4FHRKUTXZ6TMD4PPN/graph.json","events_json":"https://pith.science/api/pith-number/YC2WL4NMZ4FHRKUTXZ6TMD4PPN/events.json","paper":"https://pith.science/paper/YC2WL4NM"},"agent_actions":{"view_html":"https://pith.science/pith/YC2WL4NMZ4FHRKUTXZ6TMD4PPN","download_json":"https://pith.science/pith/YC2WL4NMZ4FHRKUTXZ6TMD4PPN.json","view_paper":"https://pith.science/paper/YC2WL4NM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.18413&json=true","fetch_graph":"https://pith.science/api/pith-number/YC2WL4NMZ4FHRKUTXZ6TMD4PPN/graph.json","fetch_events":"https://pith.science/api/pith-number/YC2WL4NMZ4FHRKUTXZ6TMD4PPN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YC2WL4NMZ4FHRKUTXZ6TMD4PPN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YC2WL4NMZ4FHRKUTXZ6TMD4PPN/action/storage_attestation","attest_author":"https://pith.science/pith/YC2WL4NMZ4FHRKUTXZ6TMD4PPN/action/author_attestation","sign_citation":"https://pith.science/pith/YC2WL4NMZ4FHRKUTXZ6TMD4PPN/action/citation_signature","submit_replication":"https://pith.science/pith/YC2WL4NMZ4FHRKUTXZ6TMD4PPN/action/replication_record"}},"created_at":"2026-07-05T10:14:35.615776+00:00","updated_at":"2026-07-05T10:14:35.615776+00:00"}