{"id":"W4392473475","doi":"10.2196/49411","title":"Machine Learning–Based Approach for Identifying Research Gaps: COVID-19 as a Case Study","year":2024,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Academic Publishing and Open Access","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Cluster analysis; Relevance (law); Data science; Artificial intelligence; Coronavirus disease 2019 (COVID-19); Scalability; Information retrieval; Machine learning; Scientific literature; Data mining","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1330242,0.0002957692,0.0005223164,0.004519472,0.003731636,0.01130824,0.004210968,0.0002970481,0.0006628663],"category_scores_gemma":[0.04877435,0.0002049497,0.0002460526,0.009426067,0.000738272,0.004419814,0.002021756,0.005412403,0.001045196],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008477151,"about_ca_system_score_gemma":0.002337187,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003611725,"about_ca_topic_score_gemma":0.0001531936,"domain_scores_codex":[0.9783356,0.007714752,0.001207045,0.001519359,0.00955283,0.001670369],"domain_scores_gemma":[0.9700493,0.02531661,0.0001573006,0.001007936,0.002523007,0.0009458588],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00113789,0.002103725,0.008447511,0.001397382,0.0002791384,0.00541004,0.2390935,0.00230418,0.0001335082,0.009543052,0.6704313,0.05971876],"study_design_scores_gemma":[0.001832536,0.001613572,0.0001767341,0.0001009772,0.0000116548,0.000722699,0.2953573,0.4045036,0.0001219535,0.02637273,0.2687642,0.0004220904],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7573001,0.004401572,0.1524934,0.01273698,0.001153786,0.01463923,0.0003392285,0.0008935501,0.05604214],"genre_scores_gemma":[0.9845845,0.00001884955,0.0004359049,0.0001700193,0.000272802,0.00232128,0.00005643973,0.00005469468,0.01208554],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4021994,"threshold_uncertainty_score":0.9997326,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5411560199070763,"score_gpt":0.6402366472363406,"score_spread":0.09908062732926426,"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."}}