{"id":"W7165055885","doi":"10.5683/sp3/vsml4b","title":"Dataset for the study titled \"A comparison of preprint search aggregators: comprehensive identification of preprints in the information retrieval stage of evidence syntheses\"","year":2025,"lang":"","type":"dataset","venue":"Borealis","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Preprint; Identification (biology); Stage (stratigraphy); Document retrieval; Human–computer information retrieval; Relevance (law)","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":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.006794233,0.001361481,0.001607751,0.005669177,0.001557645,0.003824716,0.002955027,0.002395429,0.1798246],"category_scores_gemma":[0.05515361,0.0006885303,0.001593084,0.007199331,0.0008201865,0.001866931,0.003691008,0.002210443,0.109564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004070728,"about_ca_system_score_gemma":0.007886744,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01919262,"about_ca_topic_score_gemma":0.05006035,"domain_scores_codex":[0.992806,0.001900262,0.001594516,0.001065067,0.002158183,0.0004760326],"domain_scores_gemma":[0.956225,0.02101365,0.005233961,0.005808149,0.009826771,0.00189244],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001520191,0.00003072055,0.0006195678,0.001179663,0.00003831161,0.00001569179,0.00004678226,0.0001142126,0.0000704164,0.0006995262,0.9940995,0.002933652],"study_design_scores_gemma":[0.0006394881,0.00005124988,0.005548245,0.0009562241,0.00008146793,0.00006971472,0.0002084976,0.0001872475,0.000313534,0.001789147,0.9901,0.00005530758],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.000169431,0.00006347211,0.0001251659,0.0001510059,0.00004103617,0.00008005604,0.9976163,0.000209932,0.001543729],"genre_scores_gemma":[0.0009427479,0.00005525813,0.0007329766,0.0001737845,0.00002794818,0.0007242976,0.9955282,0.0001488864,0.001665985],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.997045,"threshold_uncertainty_score":0.6015731,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1949814331637181,"score_gpt":0.4341130485395751,"score_spread":0.239131615375857,"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."}}