{"id":"W4393818958","doi":"10.5281/zenodo.10403474","title":"The impacts of active and self-supervised learning on efficient annotation of single-cell expression data - source data","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto","funders":"","keywords":"Annotation; Data source; Computer science; Expression (computer science); Artificial intelligence; Computational biology; Machine learning; Data mining; 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":[0.01083378,0.003074899,0.002187917,0.002463867,0.001451777,0.003059547,0.004241316,0.002646697,0.004322857],"category_scores_gemma":[0.02423952,0.0006521651,0.002631922,0.002682966,0.001400133,0.002980418,0.002983499,0.002460615,0.007321753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001869133,"about_ca_system_score_gemma":0.002060888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008953067,"about_ca_topic_score_gemma":0.02088545,"domain_scores_codex":[0.9922247,0.002910523,0.000623878,0.002807647,0.001091064,0.0003422752],"domain_scores_gemma":[0.9831564,0.009533876,0.0003866113,0.004795745,0.001658858,0.0004685054],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.004449023,0.001501584,0.02402455,0.006117842,0.002378405,0.0003944215,0.0003655042,0.0789025,0.01878378,0.006133255,0.5546013,0.3023478],"study_design_scores_gemma":[0.002233557,0.0009299748,0.03503118,0.001092226,0.001126561,0.0008953708,0.000664688,0.610117,0.05098589,0.03908363,0.2574326,0.0004073158],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.1587213,0.01246966,0.1098669,0.004671709,0.001704851,0.0007743977,0.6554819,0.04338575,0.0129236],"genre_scores_gemma":[0.07267793,0.0009863942,0.08064682,0.0006810087,0.00011573,0.000701673,0.8388199,0.001741606,0.003628804],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01083378,"threshold_uncertainty_score":0.0572952,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04563327408192022,"score_gpt":0.258690667010738,"score_spread":0.2130573929288178,"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."}}