{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EOVHKII3IVZSQBJ6SHQPWFT2CQ","short_pith_number":"pith:EOVHKII3","schema_version":"1.0","canonical_sha256":"23aa75211b457328053e91e0fb167a14152bc05cc33591d8f5af079bde3cf3ba","source":{"kind":"arxiv","id":"2306.03828","version":4},"attestation_state":"computed","paper":{"title":"Quick-Tune: Quickly Learning Which Pretrained Model to Finetune and How","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arlind Kadra, Fabio Ferreira, Frank Hutter, Josif Grabocka, Sebastian Pineda Arango","submitted_at":"2023-06-06T16:15:26Z","abstract_excerpt":"With the ever-increasing number of pretrained models, machine learning practitioners are continuously faced with which pretrained model to use, and how to finetune it for a new dataset. In this paper, we propose a methodology that jointly searches for the optimal pretrained model and the hyperparameters for finetuning it. Our method transfers knowledge about the performance of many pretrained models with multiple hyperparameter configurations on a series of datasets. To this aim, we evaluated over 20k hyperparameter configurations for finetuning 24 pretrained image classification models on 87 "},"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":"2306.03828","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-06T16:15:26Z","cross_cats_sorted":[],"title_canon_sha256":"7b054c255a175f2010b9358bab8e4d1513923ff4dcedc0064b0b069901e09b0e","abstract_canon_sha256":"fc8c1fe94a700c840eb74b1a47459e35cbaed7c3cd298e65a9ab9bea6babba05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:16.500045Z","signature_b64":"eoxqYSkM6aNn7ggR7EsozZEaW7J8VCIMRDcMufPJVkw6IR4MP3m3OwmRgQcyl+zVE4sXWCMjVdhVj+jyWVn7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23aa75211b457328053e91e0fb167a14152bc05cc33591d8f5af079bde3cf3ba","last_reissued_at":"2026-07-05T07:48:16.499559Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:16.499559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quick-Tune: Quickly Learning Which Pretrained Model to Finetune and How","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arlind Kadra, Fabio Ferreira, Frank Hutter, Josif Grabocka, Sebastian Pineda Arango","submitted_at":"2023-06-06T16:15:26Z","abstract_excerpt":"With the ever-increasing number of pretrained models, machine learning practitioners are continuously faced with which pretrained model to use, and how to finetune it for a new dataset. In this paper, we propose a methodology that jointly searches for the optimal pretrained model and the hyperparameters for finetuning it. Our method transfers knowledge about the performance of many pretrained models with multiple hyperparameter configurations on a series of datasets. To this aim, we evaluated over 20k hyperparameter configurations for finetuning 24 pretrained image classification models on 87 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.03828","kind":"arxiv","version":4},"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/2306.03828/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":"2306.03828","created_at":"2026-07-05T07:48:16.499619+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.03828v4","created_at":"2026-07-05T07:48:16.499619+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.03828","created_at":"2026-07-05T07:48:16.499619+00:00"},{"alias_kind":"pith_short_12","alias_value":"EOVHKII3IVZS","created_at":"2026-07-05T07:48:16.499619+00:00"},{"alias_kind":"pith_short_16","alias_value":"EOVHKII3IVZSQBJ6","created_at":"2026-07-05T07:48:16.499619+00:00"},{"alias_kind":"pith_short_8","alias_value":"EOVHKII3","created_at":"2026-07-05T07:48:16.499619+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.17283","citing_title":"Quickly Tuning Foundation Models for Image Segmentation","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EOVHKII3IVZSQBJ6SHQPWFT2CQ","json":"https://pith.science/pith/EOVHKII3IVZSQBJ6SHQPWFT2CQ.json","graph_json":"https://pith.science/api/pith-number/EOVHKII3IVZSQBJ6SHQPWFT2CQ/graph.json","events_json":"https://pith.science/api/pith-number/EOVHKII3IVZSQBJ6SHQPWFT2CQ/events.json","paper":"https://pith.science/paper/EOVHKII3"},"agent_actions":{"view_html":"https://pith.science/pith/EOVHKII3IVZSQBJ6SHQPWFT2CQ","download_json":"https://pith.science/pith/EOVHKII3IVZSQBJ6SHQPWFT2CQ.json","view_paper":"https://pith.science/paper/EOVHKII3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.03828&json=true","fetch_graph":"https://pith.science/api/pith-number/EOVHKII3IVZSQBJ6SHQPWFT2CQ/graph.json","fetch_events":"https://pith.science/api/pith-number/EOVHKII3IVZSQBJ6SHQPWFT2CQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EOVHKII3IVZSQBJ6SHQPWFT2CQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EOVHKII3IVZSQBJ6SHQPWFT2CQ/action/storage_attestation","attest_author":"https://pith.science/pith/EOVHKII3IVZSQBJ6SHQPWFT2CQ/action/author_attestation","sign_citation":"https://pith.science/pith/EOVHKII3IVZSQBJ6SHQPWFT2CQ/action/citation_signature","submit_replication":"https://pith.science/pith/EOVHKII3IVZSQBJ6SHQPWFT2CQ/action/replication_record"}},"created_at":"2026-07-05T07:48:16.499619+00:00","updated_at":"2026-07-05T07:48:16.499619+00:00"}