{"id":"W7101431141","doi":"10.5281/zenodo.17458904","title":"Supporting Data of Distilling System Complexity to Enable Unbiased and Predictive Computational Reaction Investigations","year":2025,"lang":"","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Molecular Sensors and Ion Detection","field":"Chemistry","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"JSON; Benchmark (surveying); Computational complexity theory; Raw data; Energy (signal processing)","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":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001598676,0.0003839203,0.0005192702,0.0005127365,0.003091161,0.000770418,0.001512373,0.0002750234,0.002214503],"category_scores_gemma":[0.004108417,0.0004755906,0.00007566178,0.0009924495,0.0004382082,0.0003470481,0.003642083,0.0007251537,0.000214986],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004452189,"about_ca_system_score_gemma":0.00003916684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002004235,"about_ca_topic_score_gemma":0.000002196592,"domain_scores_codex":[0.9956085,0.0006935604,0.00112308,0.001300541,0.0007792597,0.0004950353],"domain_scores_gemma":[0.9955102,0.0001592921,0.0008800187,0.001553498,0.001485747,0.0004112038],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003341793,0.0003083683,0.000002248861,0.004412624,0.0003863165,0.00002261851,0.0005513845,0.004775823,0.013393,0.0008676701,0.9640694,0.01087634],"study_design_scores_gemma":[0.0005977367,0.0002001512,0.00003790563,0.001037029,0.0002370075,0.0001190303,0.001152329,0.08443383,0.001720565,0.0001016213,0.9099981,0.000364758],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.003647048,0.00009604508,0.04986648,0.0002738614,0.0002357659,0.001059573,0.9381592,0.000371241,0.006290813],"genre_scores_gemma":[0.1072962,0.00006719885,0.001176972,0.00005250363,0.0001889742,1.596106e-7,0.890505,0.0004643081,0.0002486487],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.1036491,"threshold_uncertainty_score":0.9997696,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06903414866088341,"score_gpt":0.2944512008934082,"score_spread":0.2254170522325248,"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."}}