{"id":"W7116864682","doi":"10.64898/2025.12.19.695616","title":"Hidden sampling biases inflate performance in gene regulatory network inference","year":2025,"lang":"en","type":"article","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Canadian Institute for Advanced Research","keywords":"Inference; Exploit; Heuristics; Benchmarking; Graph; Gene regulatory network; Artificial neural network; Sampling (signal processing); Key (lock)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.01306368,0.0008029807,0.0007568078,0.0007131518,0.0006987276,0.001252504,0.001637322,0.001153874,0.0009599627],"category_scores_gemma":[0.04461978,0.0004949869,0.0006912941,0.000605836,0.001846593,0.001810973,0.001637189,0.001849975,0.000496592],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001269161,"about_ca_system_score_gemma":0.001226999,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006297862,"about_ca_topic_score_gemma":0.008582722,"domain_scores_codex":[0.9941402,0.003655089,0.0002038804,0.0009268918,0.0008050388,0.0002689308],"domain_scores_gemma":[0.9730378,0.02099894,0.000912275,0.003167667,0.00146479,0.0004184075],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009308239,0.0001729942,0.04966781,0.0005385813,0.0006790234,0.0001631224,0.0003372353,0.8185906,0.02434098,0.01227908,0.005754763,0.08654491],"study_design_scores_gemma":[0.00002432618,0.00008422176,0.003056463,0.00003896335,0.00002922149,0.00004787042,0.00005164281,0.9724062,0.01149795,0.01209119,0.0006540943,0.00001785991],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5696319,0.00231603,0.4159906,0.001732005,0.0003207259,0.00010795,0.000996392,0.005136158,0.003768176],"genre_scores_gemma":[0.9533793,0.0002358084,0.04393148,0.0003981185,0.00004164211,0.00006570281,0.001059731,0.0003965097,0.0004917646],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9869363,"threshold_uncertainty_score":0.06908816,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01759267543008775,"score_gpt":0.2285474132355435,"score_spread":0.2109547378054557,"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."}}