{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003157122,0.0002531458,0.0002349833,0.0001169253,0.0001342977,0.00005877109,0.0003046894,0.0002468189,0.000007638714],"category_scores_gemma":[0.0001456627,0.0002795818,0.00006599133,0.0004876923,0.00009029057,0.00001615777,0.0001041826,0.0001905186,0.000009511939],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000526578,"about_ca_system_score_gemma":0.0002607318,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002189525,"about_ca_topic_score_gemma":0.00001195192,"domain_scores_codex":[0.998516,0.00005546153,0.0003539472,0.0004973953,0.0001219701,0.0004551838],"domain_scores_gemma":[0.9990649,0.00003325398,0.00009040446,0.0005839295,0.0001347288,0.00009273839],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005542768,0.00004405417,0.1584712,0.0000388075,0.00002958779,0.000003759709,0.000002219815,0.0007114498,0.8404028,0.0001546773,0.00005832361,0.00002773916],"study_design_scores_gemma":[0.0004274274,0.00004873271,0.3875757,0.0001779484,0.0000147738,8.456351e-9,7.446142e-7,0.0003702041,0.6082881,0.000001128123,0.00284009,0.0002551064],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9962881,0.001385152,0.001512764,0.00004365375,0.000467044,0.0001981251,0.00001205835,0.0000593638,0.00003370983],"genre_scores_gemma":[0.9955689,0.0005559238,0.003134622,0.0003577748,0.000291719,0.00003625266,7.131306e-7,0.00003687322,0.00001722196],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2321147,"threshold_uncertainty_score":0.9999656,"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."}}