{"id":"W4416810799","doi":"10.14740/aicm7","title":"Future Writing: Rethinking Audience, Ethics, and Purpose With Artificial Intelligence Benchmarks That Uplift Humanity Like Ending the Organ Shortage","year":2025,"lang":"en","type":"article","venue":"AI in Clinical Medicine","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Humanity; Economic shortage","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":["metaresearch","sts","research_integrity"],"consensus_categories":["sts"],"category_scores_codex":[0.02369132,0.0001864705,0.000456247,0.0001088186,0.002015723,0.0001946848,0.0005905873,0.0006894334,0.000126589],"category_scores_gemma":[0.01665113,0.000119525,0.00006013618,0.0007272201,0.004195781,0.0002696227,0.0001788665,0.004863919,0.000001603336],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007193195,"about_ca_system_score_gemma":0.0005582759,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002908997,"about_ca_topic_score_gemma":0.04908867,"domain_scores_codex":[0.9962246,0.001205238,0.0007985496,0.0004736836,0.0008087936,0.0004891704],"domain_scores_gemma":[0.9875268,0.01140145,0.0002226297,0.000312317,0.000331175,0.000205633],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006299452,0.0000903504,0.06098642,0.00004753864,0.00003931616,0.00003893772,0.1095206,0.000001772931,0.000009747605,0.7887052,0.001151634,0.03934556],"study_design_scores_gemma":[0.0003430713,0.0005278835,0.06215576,0.001709918,0.0001210117,0.000001805611,0.2407602,0.000103496,0.00002325573,0.6640635,0.02981309,0.0003770738],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.2455936,0.001298034,0.00114159,0.6695282,0.003785631,0.0009319338,0.000002928088,0.0001043822,0.07761366],"genre_scores_gemma":[0.9710705,0.003538594,0.0001899593,0.02322248,0.001766886,0.000008551358,0.000004093613,0.00001025016,0.0001886552],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7254769,"threshold_uncertainty_score":0.9992835,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1789247919863214,"score_gpt":0.493941832827258,"score_spread":0.3150170408409366,"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."}}