{"id":"W4293248177","doi":"10.1145/3539813.3545150","title":"WooIR","year":2022,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Canadian Institute of Steel Construction","keywords":"Computer science; Task (project management); Benchmark (surveying); Metric (unit); Baseline (sea); Field (mathematics); Segmentation; Information retrieval; Data mining; Quality (philosophy); Artificial intelligence","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002626787,0.002356122,0.001514125,0.004493488,0.001195578,0.004180427,0.003763268,0.002239862,0.01308256],"category_scores_gemma":[0.01168756,0.0006240422,0.001500067,0.005017199,0.0007118576,0.005325007,0.003210625,0.001614031,0.01722264],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001288619,"about_ca_system_score_gemma":0.001318613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01062386,"about_ca_topic_score_gemma":0.01745828,"domain_scores_codex":[0.9955118,0.0007011687,0.0005155146,0.001499399,0.001296584,0.0004753661],"domain_scores_gemma":[0.9954069,0.0009908188,0.0002915964,0.00179039,0.001105219,0.0004151553],"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":[0.002862857,0.001150311,0.00973318,0.004373122,0.0004440158,0.0004880963,0.0004271219,0.02174393,0.01519436,0.00763077,0.6624104,0.2735419],"study_design_scores_gemma":[0.0006611681,0.001273742,0.0192753,0.0005669448,0.0001964966,0.001535772,0.000875814,0.1539953,0.02854378,0.01552256,0.777353,0.0002001017],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"other","genre_scores_codex":[0.1400284,0.01589656,0.08835823,0.002592622,0.003757858,0.002187717,0.545217,0.1367354,0.06522626],"genre_scores_gemma":[0.06495709,0.001181876,0.06892776,0.0007406828,0.0002104096,0.000586711,0.8498935,0.003534489,0.009967513],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.9869174,"threshold_uncertainty_score":0,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01016426538243726,"score_gpt":0.2483751055498988,"score_spread":0.2382108401674615,"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."}}