{"id":"W4411111057","doi":"10.1101/2025.06.03.657578","title":"Integrating multi-covariate disentanglement with counterfactual analysis on synthetic data enables cell type discovery and counterfactual predictions","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research","funders":"NIHR Newcastle Biomedical Research Centre; Lister Institute of Preventive Medicine; National Institute for Health and Care Research; Wellcome Trust","keywords":"Counterfactual thinking; Covariate; Econometrics; Computer science; Type (biology); Statistics; Data mining; Mathematics; Psychology; Biology","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":[0.009262327,0.0008523859,0.0008073277,0.0007161245,0.0003619801,0.001414859,0.001243897,0.00122822,0.001175765],"category_scores_gemma":[0.02243894,0.0005739237,0.001459394,0.0004828916,0.001567779,0.0009714016,0.00164647,0.002289359,0.0002271646],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000858743,"about_ca_system_score_gemma":0.001146868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002313719,"about_ca_topic_score_gemma":0.00257127,"domain_scores_codex":[0.9979681,0.001168918,0.0000917642,0.0004399958,0.0002636476,0.00006752551],"domain_scores_gemma":[0.9789523,0.01656624,0.001193552,0.002381659,0.0006588115,0.0002474585],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004136336,0.0001365006,0.01604033,0.0002374815,0.0003226953,0.0002300106,0.000164482,0.894016,0.02799212,0.01618776,0.001422353,0.04283658],"study_design_scores_gemma":[0.00001382925,0.00002906812,0.0008523823,0.000007248507,0.00001290671,0.00002815141,0.000008241199,0.985541,0.005734266,0.00722433,0.000536307,0.0000121978],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07928292,0.0002258742,0.918151,0.0002883096,0.00004631896,0.00006658389,0.0006592041,0.0008339604,0.0004458561],"genre_scores_gemma":[0.6982113,0.000164254,0.2970521,0.000298976,0.00005899568,0.0003137273,0.002727981,0.0002512798,0.0009213457],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009262327,"threshold_uncertainty_score":0.04898441,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01624914438009599,"score_gpt":0.2541763764022088,"score_spread":0.2379272320221128,"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."}}