{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CEAQZUDLB7WTVXCCNJ43R4CRXS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"91b7efa7cc5fe944a807114e1a753922d72331896202718d6ea3d6b8a2610907","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-21T16:24:10Z","title_canon_sha256":"e45cbb345f0fa8f9ef0d1842b20d0f0e558aaae6234d6a78f0ee84c1d4c0ab46"},"schema_version":"1.0","source":{"id":"2502.15563","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.15563","created_at":"2026-07-05T10:18:03Z"},{"alias_kind":"arxiv_version","alias_value":"2502.15563v1","created_at":"2026-07-05T10:18:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15563","created_at":"2026-07-05T10:18:03Z"},{"alias_kind":"pith_short_12","alias_value":"CEAQZUDLB7WT","created_at":"2026-07-05T10:18:03Z"},{"alias_kind":"pith_short_16","alias_value":"CEAQZUDLB7WTVXCC","created_at":"2026-07-05T10:18:03Z"},{"alias_kind":"pith_short_8","alias_value":"CEAQZUDL","created_at":"2026-07-05T10:18:03Z"}],"graph_snapshots":[{"event_id":"sha256:311e7740346300ae9df93180ac811b9834fc3c273db46c37c6b45735f9e0dc12","target":"graph","created_at":"2026-07-05T10:18:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.15563/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-21T16:24:10Z","title":"Bridging vision language model (VLM) evaluation gaps with a framework for scalable and cost-effective benchmark generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15563","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0a31b686ab1de518c6bd8c9affda4a16fc3e5d7b0a05d6f0f5d55a1010a0c843","target":"record","created_at":"2026-07-05T10:18:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"91b7efa7cc5fe944a807114e1a753922d72331896202718d6ea3d6b8a2610907","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-21T16:24:10Z","title_canon_sha256":"e45cbb345f0fa8f9ef0d1842b20d0f0e558aaae6234d6a78f0ee84c1d4c0ab46"},"schema_version":"1.0","source":{"id":"2502.15563","kind":"arxiv","version":1}},"canonical_sha256":"11010cd06b0fed3adc426a79b8f051bca37fd14f71b8ec071d74fb24ede6ec10","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11010cd06b0fed3adc426a79b8f051bca37fd14f71b8ec071d74fb24ede6ec10","first_computed_at":"2026-07-05T10:18:03.536388Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:03.536388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pjGAenDc0TdRvTk5C6LkkpiSMFazEI5b7AYlFd8fbcwxt2yyR1jnDsLGhh7UEQgcEOMKkP6u1QJN2nquwZinAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:03.536839Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.15563","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a31b686ab1de518c6bd8c9affda4a16fc3e5d7b0a05d6f0f5d55a1010a0c843","sha256:311e7740346300ae9df93180ac811b9834fc3c273db46c37c6b45735f9e0dc12"],"state_sha256":"18f56094f93be2a57428066fa50e83ff44d05b014c6a1c883bc4b199b8755a1d"}