{"id":"W1543603119","doi":"10.1007/s10462-009-9139-0","title":"A unified framework for improving the accuracy of all holistic face identification algorithms","year":2009,"lang":"en","type":"article","venue":"Artificial Intelligence Review","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Northern British Columbia","funders":"","keywords":"Computer science; Identification (biology); Benchmark (surveying); Face (sociological concept); Process (computing); Machine learning; Algorithm; Artificial intelligence; Baseline (sea); Stability (learning theory); Data mining","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":[],"consensus_categories":[],"category_scores_codex":[0.00361168,0.002175859,0.003087277,0.002176078,0.001056703,0.002747681,0.00338498,0.0017299,0.002910503],"category_scores_gemma":[0.006601376,0.0006132798,0.001653925,0.001745816,0.001002416,0.004194655,0.003326648,0.002467083,0.00238168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001003001,"about_ca_system_score_gemma":0.002313824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003217322,"about_ca_topic_score_gemma":0.00513115,"domain_scores_codex":[0.9971884,0.0005442319,0.0001673704,0.0004739276,0.001435843,0.0001901798],"domain_scores_gemma":[0.997525,0.0004087247,0.0001186281,0.0006289688,0.001247003,0.00007152373],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001225877,0.0001790504,0.0009780889,0.0005157018,0.0002348282,0.00008491558,0.0001017875,0.04673439,0.03315586,0.06648535,0.009425186,0.8419823],"study_design_scores_gemma":[0.00003564361,0.0003912396,0.00196999,0.0001645468,0.0003184084,0.0005742776,0.00009953634,0.8719336,0.04020254,0.05752315,0.02665968,0.0001273379],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.001767447,0.001791195,0.9938765,0.000155364,0.0001194862,0.00005343561,0.0000371131,0.0005857636,0.001613624],"genre_scores_gemma":[0.04051603,0.002280924,0.9537062,0.0002118094,0.0002464993,0.0001588365,0.0001932134,0.000159336,0.002527212],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.00361168,"threshold_uncertainty_score":0.01910067,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1581932759200924,"score_gpt":0.4015026794538817,"score_spread":0.2433094035337893,"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."}}