{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001918751,0.002813901,0.001220425,0.002074887,0.0009241319,0.002365527,0.002901399,0.00266641,0.1263505],"category_scores_gemma":[0.007935483,0.0006244289,0.001669478,0.002869792,0.0007767366,0.001223197,0.001561504,0.002432743,0.08300301],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001264347,"about_ca_system_score_gemma":0.002267792,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004612898,"about_ca_topic_score_gemma":0.01172978,"domain_scores_codex":[0.9987424,0.0002204648,0.0001260039,0.000375384,0.0003903896,0.0001453936],"domain_scores_gemma":[0.9959804,0.002010597,0.0003760219,0.0008259474,0.0005274411,0.0002796462],"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":[0.000249661,0.0001174718,0.002557821,0.003080065,0.0001106546,0.00007047421,0.00003949774,0.005914661,0.0008591299,0.002684032,0.9792545,0.005062043],"study_design_scores_gemma":[0.0007898453,0.0001064753,0.005004054,0.0007009297,0.0001009166,0.0001287354,0.00007331853,0.009563425,0.00327677,0.01050495,0.9696932,0.0000573832],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0005666265,0.0001070704,0.0003825296,0.00006324112,0.00003278607,0.00002086451,0.9972947,0.0006839668,0.0008481787],"genre_scores_gemma":[0.002277917,0.00008248876,0.001237305,0.00006214529,0.00001195983,0.0001388211,0.9955427,0.0001616551,0.0004849604],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.1263505,"threshold_uncertainty_score":0.4226847,"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."}}