{"id":"W2964987975","doi":"","title":"Overview of the 2019 open-source IR replicability challenge (OSIRRC 2019)","year":2019,"lang":"en","type":"article","venue":"Research Repository (Delft University of Technology)","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Replication (statistics); Information retrieval; Open source; Test (biology); World Wide Web; Track (disk drive); Data science; Operating system; Software","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":[0.06729464,0.00177395,0.001539075,0.005016607,0.002930785,0.01029433,0.008322544,0.00522661,0.01490062],"category_scores_gemma":[0.05761882,0.00188618,0.002172022,0.004007759,0.002706129,0.01596505,0.0118636,0.007884062,0.02249713],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003897282,"about_ca_system_score_gemma":0.008433855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008609725,"about_ca_topic_score_gemma":0.007559534,"domain_scores_codex":[0.9652756,0.01045353,0.002567082,0.004551047,0.01462649,0.002526193],"domain_scores_gemma":[0.9239151,0.01156077,0.002579906,0.02471773,0.02676652,0.01045998],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0008130062,0.001085345,0.001893165,0.001942267,0.0001034535,0.0003446751,0.001196657,0.006462285,0.03010808,0.0399946,0.4898424,0.426214],"study_design_scores_gemma":[0.000238452,0.0009097864,0.002803392,0.0005876916,0.00005920722,0.000675945,0.0005084614,0.01922787,0.01594014,0.02931183,0.9295198,0.0002173214],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01659553,0.02035175,0.7220403,0.04667441,0.006058083,0.006459195,0.007861511,0.08849473,0.08546448],"genre_scores_gemma":[0.0738683,0.009862011,0.7393823,0.01047754,0.003354383,0.005082409,0.06342528,0.02848787,0.06605995],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9916775,"threshold_uncertainty_score":0.3558924,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05332958677021043,"score_gpt":0.3337903719813969,"score_spread":0.2804607852111865,"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."}}