{"id":"W4394039396","doi":"10.5281/zenodo.3930996","title":"Preprocessing scripts and data for study: Identifying high-confidence capture Hi-C interactions using CHiCANE","year":2020,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute of Cancer Research","funders":"","keywords":"Preprocessor; Scripting language; Computer science; Data pre-processing; Artificial intelligence; Operating system","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0008557161,0.000260113,0.0003029155,0.0002827002,0.002339248,0.003809827,0.004805412,0.00009527997,0.0003331763],"category_scores_gemma":[0.001268205,0.0002879927,0.00003347294,0.0005134176,0.00008816882,0.001329257,0.009245433,0.0006378593,0.0003966151],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001249034,"about_ca_system_score_gemma":0.00002247863,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003679325,"about_ca_topic_score_gemma":0.0000106238,"domain_scores_codex":[0.9969372,0.0002981276,0.0004283524,0.001466719,0.0004953588,0.0003742829],"domain_scores_gemma":[0.9969355,0.00005515861,0.0003007441,0.00205123,0.0004550835,0.0002023109],"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":[0.00001688218,0.00009269569,4.180769e-7,0.0003436069,0.00006978781,0.00002797453,0.001119828,0.00009751988,0.0003565151,0.0001908542,0.9850005,0.01268343],"study_design_scores_gemma":[0.0003583808,0.00008530667,0.00001791747,0.0001874762,0.00007018511,0.0001450482,0.0004179792,0.03479864,0.00001772586,0.0001722512,0.9634351,0.0002940142],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.000298949,0.0001620576,0.4704674,0.0005598554,0.000555436,0.001087824,0.5262156,0.0005365094,0.0001163744],"genre_scores_gemma":[0.02046455,0.00007362801,0.01427187,0.0002892267,0.0005539661,2.495713e-7,0.9634033,0.0008342051,0.0001089417],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.4561956,"threshold_uncertainty_score":0.9999572,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.160977707385079,"score_gpt":0.3419859801446908,"score_spread":0.1810082727596118,"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."}}