{"id":"W7092179641","doi":"10.5281/zenodo.17308056","title":"A whitepaper on reforming research assessment for a digital and AI-driven science future","year":2025,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Research Data Management Practices","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"European Commission","keywords":"Workflow; Modular design; Research ethics; Configurator; Scientific integrity; Ethical issues","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1104799,0.0009031202,0.0009455276,0.003716235,0.007796085,0.03088183,0.003858482,0.01377002,0.01123722],"category_scores_gemma":[0.118007,0.0009169866,0.001782083,0.003533941,0.01382199,0.02314566,0.01397996,0.01502519,0.005083014],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.009272997,"about_ca_system_score_gemma":0.03671961,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006685574,"about_ca_topic_score_gemma":0.006536775,"domain_scores_codex":[0.9028342,0.04462538,0.006514738,0.008210432,0.0344935,0.003321784],"domain_scores_gemma":[0.8891447,0.0615585,0.003492652,0.01810142,0.02003849,0.007664222],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001964214,0.00003233116,0.0001919791,0.0001574676,0.00001618487,0.00008915774,0.001596422,0.0007682481,0.0004009713,0.8440353,0.1064748,0.0462176],"study_design_scores_gemma":[0.00001890535,0.00002535605,0.0001864973,0.0007146958,0.00001479227,0.00008022106,0.0009124133,0.0009766166,0.0007881277,0.2124824,0.7837532,0.00004669847],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.006580485,0.008584201,0.2106696,0.6464456,0.02163872,0.0005163285,0.0005177647,0.001520577,0.1035267],"genre_scores_gemma":[0.1593214,0.01262882,0.473735,0.1744891,0.01184772,0.002022192,0.001547896,0.003154479,0.1612535],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.88952,"threshold_uncertainty_score":0.5842807,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05949982837922799,"score_gpt":0.361958035216352,"score_spread":0.302458206837124,"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."}}