{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HF4LUGCJLF5WMIZKXTGOMKN5LF","short_pith_number":"pith:HF4LUGCJ","schema_version":"1.0","canonical_sha256":"3978ba1849597b66232abccce629bd595fd37d9b2bf65d5c864bf6350428d61a","source":{"kind":"arxiv","id":"2511.21007","version":2},"attestation_state":"computed","paper":{"title":"MetaRank: Task-Aware Metric Selection for Model Transferability Estimation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Wenjie Zhao, Xin Wang, Yuhang Liu, Yunhui Guo","submitted_at":"2025-11-26T03:15:13Z","abstract_excerpt":"Selecting an appropriate pre-trained source model is a critical, yet computationally expensive, task in transfer learning. Model Transferability Estimation (MTE) methods address this by providing efficient proxy metrics to rank models without full fine-tuning. In practice, the choice of which MTE metric to use is often ad hoc or guided simply by a metric's average historical performance. However, we observe that the effectiveness of MTE metrics is highly task-dependent and no single metric is universally optimal across all target datasets. To address this gap, we introduce MetaRank, a meta-lea"},"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":"2511.21007","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-26T03:15:13Z","cross_cats_sorted":[],"title_canon_sha256":"9238c8f00bc90de172fff7629d692b13c811e8bb812b8651c81e00b2c5ab0d3a","abstract_canon_sha256":"bf8546faa73e1d09b8351dc64025c8bc5c407dadf852235344440cd8be4d5a32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3978ba1849597b66232abccce629bd595fd37d9b2bf65d5c864bf6350428d61a","last_reissued_at":"2026-07-31T01:08:54.601874Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:08:54.601874Z"},"graph_snapshot":{"paper":{"title":"MetaRank: Task-Aware Metric Selection for Model Transferability Estimation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Wenjie Zhao, Xin Wang, Yuhang Liu, Yunhui Guo","submitted_at":"2025-11-26T03:15:13Z","abstract_excerpt":"Selecting an appropriate pre-trained source model is a critical, yet computationally expensive, task in transfer learning. Model Transferability Estimation (MTE) methods address this by providing efficient proxy metrics to rank models without full fine-tuning. In practice, the choice of which MTE metric to use is often ad hoc or guided simply by a metric's average historical performance. However, we observe that the effectiveness of MTE metrics is highly task-dependent and no single metric is universally optimal across all target datasets. To address this gap, we introduce MetaRank, a meta-lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.21007","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/2511.21007/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":"2511.21007","created_at":"2026-07-31T01:08:54.604901+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.21007v2","created_at":"2026-07-31T01:08:54.604901+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.21007","created_at":"2026-07-31T01:08:54.604901+00:00"},{"alias_kind":"pith_short_12","alias_value":"HF4LUGCJLF5W","created_at":"2026-07-31T01:08:54.604901+00:00"},{"alias_kind":"pith_short_16","alias_value":"HF4LUGCJLF5WMIZK","created_at":"2026-07-31T01:08:54.604901+00:00"},{"alias_kind":"pith_short_8","alias_value":"HF4LUGCJ","created_at":"2026-07-31T01:08:54.604901+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/HF4LUGCJLF5WMIZKXTGOMKN5LF","json":"https://pith.science/pith/HF4LUGCJLF5WMIZKXTGOMKN5LF.json","graph_json":"https://pith.science/api/pith-number/HF4LUGCJLF5WMIZKXTGOMKN5LF/graph.json","events_json":"https://pith.science/api/pith-number/HF4LUGCJLF5WMIZKXTGOMKN5LF/events.json","paper":"https://pith.science/paper/HF4LUGCJ"},"agent_actions":{"view_html":"https://pith.science/pith/HF4LUGCJLF5WMIZKXTGOMKN5LF","download_json":"https://pith.science/pith/HF4LUGCJLF5WMIZKXTGOMKN5LF.json","view_paper":"https://pith.science/paper/HF4LUGCJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.21007&json=true","fetch_graph":"https://pith.science/api/pith-number/HF4LUGCJLF5WMIZKXTGOMKN5LF/graph.json","fetch_events":"https://pith.science/api/pith-number/HF4LUGCJLF5WMIZKXTGOMKN5LF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HF4LUGCJLF5WMIZKXTGOMKN5LF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HF4LUGCJLF5WMIZKXTGOMKN5LF/action/storage_attestation","attest_author":"https://pith.science/pith/HF4LUGCJLF5WMIZKXTGOMKN5LF/action/author_attestation","sign_citation":"https://pith.science/pith/HF4LUGCJLF5WMIZKXTGOMKN5LF/action/citation_signature","submit_replication":"https://pith.science/pith/HF4LUGCJLF5WMIZKXTGOMKN5LF/action/replication_record"}},"created_at":"2026-07-31T01:08:54.604901+00:00","updated_at":"2026-07-31T01:08:54.604901+00:00"}