{"id":"W4393693293","doi":"10.5281/zenodo.8227899","title":"The Metadata of \"A Rapid Investigation of Artificial Intelligence Generated Content Footprints in Scholarly Publications\"","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Research Data Management Practices","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Metadata; Content (measure theory); Computer science; Information retrieval; World Wide Web; Mathematics","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"],"consensus_categories":[],"category_scores_codex":[0.001792018,0.00111588,0.0009390089,0.006534069,0.0008440539,0.002780974,0.001702242,0.001721732,0.03229105],"category_scores_gemma":[0.00799236,0.0005148447,0.0008060257,0.01055052,0.0006272167,0.001961767,0.002491178,0.00182903,0.05312887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001754725,"about_ca_system_score_gemma":0.003785044,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01699538,"about_ca_topic_score_gemma":0.03392271,"domain_scores_codex":[0.9980111,0.0002837672,0.000340117,0.0003177682,0.0007884473,0.0002587607],"domain_scores_gemma":[0.9937207,0.001331452,0.0007419827,0.001633193,0.001907426,0.0006652143],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001086361,0.00005206262,0.001764858,0.001258443,0.00002711441,0.00006924951,0.0001091138,0.000398062,0.001273283,0.002423562,0.9852615,0.007254068],"study_design_scores_gemma":[0.00008889384,0.0000235423,0.007639344,0.0003616801,0.00002216882,0.0001182281,0.000193311,0.0004090641,0.001508854,0.001738252,0.9878578,0.00003876815],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0003701735,0.00006066737,0.000301515,0.0001029215,0.00004635622,0.00002922134,0.997,0.0006100705,0.001479018],"genre_scores_gemma":[0.0005654003,0.00006465062,0.0007288444,0.00003443377,0.000008888948,0.00005188526,0.9978369,0.00008451031,0.0006245357],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.998208,"threshold_uncertainty_score":0.1080244,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2989589195219117,"score_gpt":0.3341489401328226,"score_spread":0.03519002061091087,"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."}}