{"id":"W3099026386","doi":"10.1101/366724","title":"Attack and defence in cellular decision-making: lessons from machine learning","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Samsung; Samsung Advanced Institute of Technology; McGill University","keywords":"Artificial intelligence; Computer science; Decision boundary; Machine learning; Analogy; Artificial neural network; Adversarial system; Support vector machine","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":[],"consensus_categories":[],"category_scores_codex":[0.001865021,0.0006542547,0.0008527064,0.0004609567,0.0006524168,0.001908585,0.000994664,0.002447826,0.002013317],"category_scores_gemma":[0.01055668,0.0003360297,0.0007939148,0.0002969775,0.005497559,0.003098387,0.001940979,0.003623386,0.0003736262],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001371276,"about_ca_system_score_gemma":0.000729884,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008549421,"about_ca_topic_score_gemma":0.0006431285,"domain_scores_codex":[0.9990433,0.0004227241,0.00004519277,0.0001934097,0.0001903102,0.0001051537],"domain_scores_gemma":[0.9941152,0.004166834,0.000523912,0.0006599755,0.0002524802,0.0002815489],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004488491,0.00003202587,0.001258255,0.0001288799,0.00005554098,0.0001265952,0.0001706842,0.3013108,0.003055781,0.6776659,0.001413092,0.01473761],"study_design_scores_gemma":[0.00001309453,0.00002434531,0.0003240863,0.00002179267,0.000005790696,0.00004558286,0.00002876633,0.315005,0.0007734984,0.6825729,0.001167436,0.00001769408],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.115961,0.002503365,0.8484721,0.01025958,0.0002356433,0.00004681218,0.0001335907,0.0002409502,0.02214696],"genre_scores_gemma":[0.9515018,0.001473028,0.04262121,0.0007908808,0.0001963365,0.00008632444,0.00006102568,0.00007865966,0.00319068],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002447826,"threshold_uncertainty_score":0.009949386,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01933415370169873,"score_gpt":0.2639332904317166,"score_spread":0.2445991367300179,"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."}}