{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GE5TE4W65WHJWE7LO4BP3J7ZKP","short_pith_number":"pith:GE5TE4W6","schema_version":"1.0","canonical_sha256":"313b3272deed8e9b13eb7702fda7f953c2cb5c80df909c00a9a55c5705b31e77","source":{"kind":"arxiv","id":"2608.09999","version":1},"attestation_state":"computed","paper":{"title":"Robustness of transferability estimation metrics for medical imaging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Dovile Juodelyte, Niclas Cla{\\ss}en, Rob van der Goot, Th\\'eo Sourget, Veronika Cheplygina","submitted_at":"2026-08-07T13:56:18Z","abstract_excerpt":"In transfer learning, the choice of source model largely influences the performance on a target dataset. Still, selecting a fitting source remains a challenging task, especially in medical imaging where one has to decide between models pre-trained on off-the-shelf options, such as ImageNet, and domain specific datasets. Transferability estimation (TE) metrics address this problem by aiming to predict the best performing source model in a computationally cost effective way. However, previous work has reported conflicting TE metric performances due to differences in experimental setups. Moreover"},"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":"2608.09999","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2026-08-07T13:56:18Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"569a6cc0c7bed2d84ef1f3ad8b76426c00310965217dbcdc80af53a56542b8c9","abstract_canon_sha256":"b3e5446a4eae6947f855920768d35cb9734ffa603d95f0b204cc8335ffe1f702"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-12T00:22:34.348227Z","signature_b64":"QKiIZFci/yVH9biQuDA32l2uv5/SDu+LJUSAVOh1ocHRmTM+MzAyrof1pho7DA+m8fTli52TYBn4A8RYRSYNBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"313b3272deed8e9b13eb7702fda7f953c2cb5c80df909c00a9a55c5705b31e77","last_reissued_at":"2026-08-12T00:22:34.346313Z","signature_status":"signed_v1","first_computed_at":"2026-08-12T00:22:34.346313Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robustness of transferability estimation metrics for medical imaging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Dovile Juodelyte, Niclas Cla{\\ss}en, Rob van der Goot, Th\\'eo Sourget, Veronika Cheplygina","submitted_at":"2026-08-07T13:56:18Z","abstract_excerpt":"In transfer learning, the choice of source model largely influences the performance on a target dataset. Still, selecting a fitting source remains a challenging task, especially in medical imaging where one has to decide between models pre-trained on off-the-shelf options, such as ImageNet, and domain specific datasets. Transferability estimation (TE) metrics address this problem by aiming to predict the best performing source model in a computationally cost effective way. However, previous work has reported conflicting TE metric performances due to differences in experimental setups. Moreover"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09999","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/2608.09999/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":"2608.09999","created_at":"2026-08-12T00:22:34.349124+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.09999v1","created_at":"2026-08-12T00:22:34.349124+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09999","created_at":"2026-08-12T00:22:34.349124+00:00"},{"alias_kind":"pith_short_12","alias_value":"GE5TE4W65WHJ","created_at":"2026-08-12T00:22:34.349124+00:00"},{"alias_kind":"pith_short_16","alias_value":"GE5TE4W65WHJWE7L","created_at":"2026-08-12T00:22:34.349124+00:00"},{"alias_kind":"pith_short_8","alias_value":"GE5TE4W6","created_at":"2026-08-12T00:22:34.349124+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/GE5TE4W65WHJWE7LO4BP3J7ZKP","json":"https://pith.science/pith/GE5TE4W65WHJWE7LO4BP3J7ZKP.json","graph_json":"https://pith.science/api/pith-number/GE5TE4W65WHJWE7LO4BP3J7ZKP/graph.json","events_json":"https://pith.science/api/pith-number/GE5TE4W65WHJWE7LO4BP3J7ZKP/events.json","paper":"https://pith.science/paper/GE5TE4W6"},"agent_actions":{"view_html":"https://pith.science/pith/GE5TE4W65WHJWE7LO4BP3J7ZKP","download_json":"https://pith.science/pith/GE5TE4W65WHJWE7LO4BP3J7ZKP.json","view_paper":"https://pith.science/paper/GE5TE4W6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.09999&json=true","fetch_graph":"https://pith.science/api/pith-number/GE5TE4W65WHJWE7LO4BP3J7ZKP/graph.json","fetch_events":"https://pith.science/api/pith-number/GE5TE4W65WHJWE7LO4BP3J7ZKP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GE5TE4W65WHJWE7LO4BP3J7ZKP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GE5TE4W65WHJWE7LO4BP3J7ZKP/action/storage_attestation","attest_author":"https://pith.science/pith/GE5TE4W65WHJWE7LO4BP3J7ZKP/action/author_attestation","sign_citation":"https://pith.science/pith/GE5TE4W65WHJWE7LO4BP3J7ZKP/action/citation_signature","submit_replication":"https://pith.science/pith/GE5TE4W65WHJWE7LO4BP3J7ZKP/action/replication_record"}},"created_at":"2026-08-12T00:22:34.349124+00:00","updated_at":"2026-08-12T00:22:34.349124+00:00"}