{"id":"W7082280113","doi":"10.48448/w2qw-q160","title":"Evaluating Visual and Cultural Interpretation: The K-Viscuit Benchmark with Human-VLM Collaboration","year":2025,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Benchmark (surveying); Process (computing); Key (lock); Set (abstract data type); Baseline (sea)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008593597,0.0002215323,0.000182453,0.0001590004,0.0006365801,0.000709207,0.001089642,0.000101951,0.000129133],"category_scores_gemma":[0.0002614459,0.0001330785,0.00001947442,0.001175524,0.0007571554,0.000357974,0.0004547617,0.0002266215,0.000008037665],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005532619,"about_ca_system_score_gemma":0.0006137035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006934382,"about_ca_topic_score_gemma":0.0001742219,"domain_scores_codex":[0.9981729,0.00007256516,0.0002131709,0.0006730782,0.0005862826,0.000281963],"domain_scores_gemma":[0.9987199,0.00009339232,0.0002488918,0.0004481647,0.0004270028,0.00006268529],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004875939,0.0003316313,0.001443119,0.000813939,0.0003130762,0.0000564776,0.01395296,0.006031202,0.01671865,0.4482071,0.2132688,0.2988143],"study_design_scores_gemma":[0.001088302,0.0008019189,0.0007431593,0.001331806,0.0001086001,0.00007738471,0.003368056,0.8526385,0.001899531,0.01266165,0.1239895,0.001291572],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.0009576118,0.0004544695,0.08828223,0.006976274,0.0005388113,0.0006976933,0.000007168476,0.0003145443,0.9017712],"genre_scores_gemma":[0.4877999,0.00002924718,0.03875734,0.0009523877,0.0003715996,0.00006603177,0.0000530367,0.00002364677,0.4719468],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.8466073,"threshold_uncertainty_score":0.6838899,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02122261821966825,"score_gpt":0.3482990247563129,"score_spread":0.3270764065366447,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}