{"id":"W3211711919","doi":"","title":"On minimizers and convolutional filters: a partial justification for the unreasonable effectiveness of CNNs in categorical sequence analysis.","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Convolutional neural network; Categorical variable; Hash function; Pooling; Sequence (biology); Pattern recognition (psychology); Artificial intelligence; Initialization; Mathematics; Computer science; Gaussian; Algorithm; Statistics; Physics","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":[0.01022638,0.001359448,0.001292296,0.001415004,0.001393415,0.003104182,0.003401734,0.00405414,0.00491583],"category_scores_gemma":[0.05193481,0.001028485,0.001441372,0.0009751242,0.01663613,0.0120352,0.00392627,0.007587705,0.001677026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002391081,"about_ca_system_score_gemma":0.001050421,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002006906,"about_ca_topic_score_gemma":0.001469341,"domain_scores_codex":[0.9938841,0.001994547,0.0004459043,0.001772125,0.001584725,0.0003185835],"domain_scores_gemma":[0.9717965,0.02076712,0.001212859,0.004561438,0.001334944,0.0003273328],"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":[0.0001374,0.00003229593,0.001265669,0.0002456594,0.00009496602,0.0002183693,0.0002189312,0.02299112,0.002779105,0.9272282,0.005646028,0.03914233],"study_design_scores_gemma":[0.00002860242,0.00007920069,0.0003833804,0.00007887462,0.00002044602,0.0003013248,0.00003546607,0.06638647,0.004056197,0.9230952,0.00549145,0.00004347296],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0212926,0.002991271,0.9408636,0.01371096,0.0005759688,0.00007397299,0.0002892717,0.0007608721,0.01944156],"genre_scores_gemma":[0.6134919,0.004505421,0.3554237,0.009447092,0.001543921,0.000543386,0.0004289667,0.001116022,0.01349959],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01022638,"threshold_uncertainty_score":0.05408293,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05336097870848226,"score_gpt":0.2301072896824181,"score_spread":0.1767463109739358,"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."}}