{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CEAQZUDLB7WTVXCCNJ43R4CRXS","short_pith_number":"pith:CEAQZUDL","schema_version":"1.0","canonical_sha256":"11010cd06b0fed3adc426a79b8f051bca37fd14f71b8ec071d74fb24ede6ec10","source":{"kind":"arxiv","id":"2502.15563","version":1},"attestation_state":"computed","paper":{"title":"Bridging vision language model (VLM) evaluation gaps with a framework for scalable and cost-effective benchmark generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"A. Emre Kavur, Annika Reinke, Bar{\\i}\\c{s} \\\"Ozt\\\"urk, Fabian Isensee, Klaus Maier-Hein, Lena Maier-Hein, Leon Mayer, Marcel Knopp, Paul F. Jaeger, Simon Pavicic, Tim R\\\"adsch","submitted_at":"2025-02-21T16:24:10Z","abstract_excerpt":"Reliable evaluation of AI models is critical for scientific progress and practical application. While existing VLM benchmarks provide general insights into model capabilities, their heterogeneous designs and limited focus on a few imaging domains pose significant challenges for both cross-domain performance comparison and targeted domain-specific evaluation. To address this, we propose three key contributions: (1) a framework for the resource-efficient creation of domain-specific VLM benchmarks enabled by task augmentation for creating multiple diverse tasks from a single existing task, (2) th"},"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":"2502.15563","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-21T16:24:10Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"e45cbb345f0fa8f9ef0d1842b20d0f0e558aaae6234d6a78f0ee84c1d4c0ab46","abstract_canon_sha256":"91b7efa7cc5fe944a807114e1a753922d72331896202718d6ea3d6b8a2610907"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:03.536839Z","signature_b64":"pjGAenDc0TdRvTk5C6LkkpiSMFazEI5b7AYlFd8fbcwxt2yyR1jnDsLGhh7UEQgcEOMKkP6u1QJN2nquwZinAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11010cd06b0fed3adc426a79b8f051bca37fd14f71b8ec071d74fb24ede6ec10","last_reissued_at":"2026-07-05T10:18:03.536388Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:03.536388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging vision language model (VLM) evaluation gaps with a framework for scalable and cost-effective benchmark generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"A. Emre Kavur, Annika Reinke, Bar{\\i}\\c{s} \\\"Ozt\\\"urk, Fabian Isensee, Klaus Maier-Hein, Lena Maier-Hein, Leon Mayer, Marcel Knopp, Paul F. Jaeger, Simon Pavicic, Tim R\\\"adsch","submitted_at":"2025-02-21T16:24:10Z","abstract_excerpt":"Reliable evaluation of AI models is critical for scientific progress and practical application. While existing VLM benchmarks provide general insights into model capabilities, their heterogeneous designs and limited focus on a few imaging domains pose significant challenges for both cross-domain performance comparison and targeted domain-specific evaluation. To address this, we propose three key contributions: (1) a framework for the resource-efficient creation of domain-specific VLM benchmarks enabled by task augmentation for creating multiple diverse tasks from a single existing task, (2) th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15563","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/2502.15563/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":"2502.15563","created_at":"2026-07-05T10:18:03.536443+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.15563v1","created_at":"2026-07-05T10:18:03.536443+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15563","created_at":"2026-07-05T10:18:03.536443+00:00"},{"alias_kind":"pith_short_12","alias_value":"CEAQZUDLB7WT","created_at":"2026-07-05T10:18:03.536443+00:00"},{"alias_kind":"pith_short_16","alias_value":"CEAQZUDLB7WTVXCC","created_at":"2026-07-05T10:18:03.536443+00:00"},{"alias_kind":"pith_short_8","alias_value":"CEAQZUDL","created_at":"2026-07-05T10:18:03.536443+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.06232","citing_title":"Challenging Vision-Language Models with Surgical Data: A New Dataset and Broad Benchmarking Study","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CEAQZUDLB7WTVXCCNJ43R4CRXS","json":"https://pith.science/pith/CEAQZUDLB7WTVXCCNJ43R4CRXS.json","graph_json":"https://pith.science/api/pith-number/CEAQZUDLB7WTVXCCNJ43R4CRXS/graph.json","events_json":"https://pith.science/api/pith-number/CEAQZUDLB7WTVXCCNJ43R4CRXS/events.json","paper":"https://pith.science/paper/CEAQZUDL"},"agent_actions":{"view_html":"https://pith.science/pith/CEAQZUDLB7WTVXCCNJ43R4CRXS","download_json":"https://pith.science/pith/CEAQZUDLB7WTVXCCNJ43R4CRXS.json","view_paper":"https://pith.science/paper/CEAQZUDL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.15563&json=true","fetch_graph":"https://pith.science/api/pith-number/CEAQZUDLB7WTVXCCNJ43R4CRXS/graph.json","fetch_events":"https://pith.science/api/pith-number/CEAQZUDLB7WTVXCCNJ43R4CRXS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CEAQZUDLB7WTVXCCNJ43R4CRXS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CEAQZUDLB7WTVXCCNJ43R4CRXS/action/storage_attestation","attest_author":"https://pith.science/pith/CEAQZUDLB7WTVXCCNJ43R4CRXS/action/author_attestation","sign_citation":"https://pith.science/pith/CEAQZUDLB7WTVXCCNJ43R4CRXS/action/citation_signature","submit_replication":"https://pith.science/pith/CEAQZUDLB7WTVXCCNJ43R4CRXS/action/replication_record"}},"created_at":"2026-07-05T10:18:03.536443+00:00","updated_at":"2026-07-05T10:18:03.536443+00:00"}