{"id":"W4380451742","doi":"10.1117/12.2663477","title":"Validation of ShipIR (v4.2)","year":2023,"lang":"en","type":"article","venue":"","topic":"Infrared Target Detection Methodologies","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"BGC Engineering (Canada)","funders":"","keywords":"Solver; Atmospheric model; Computer science; Problem solver; Remote sensing; Thermal; Sky; Atmosphere (unit); Meteorology; Geology; Computational science; Physics","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":[0.002787525,0.000883162,0.0004524901,0.0005867905,0.0005933795,0.001556639,0.002064099,0.0008520124,0.01061324],"category_scores_gemma":[0.004593994,0.0004245445,0.0009644892,0.0004856539,0.0005570424,0.001159431,0.001319231,0.001736047,0.005397786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001010745,"about_ca_system_score_gemma":0.001771346,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009811966,"about_ca_topic_score_gemma":0.007649319,"domain_scores_codex":[0.998471,0.0001553954,0.00009811028,0.0002608167,0.0008550197,0.0001597406],"domain_scores_gemma":[0.998243,0.0002987624,0.00006821527,0.0004016815,0.0009170727,0.00007126462],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007019769,0.0007348118,0.01729764,0.0007151985,0.0002076463,0.000361421,0.0006137033,0.609367,0.09347095,0.0169441,0.08916084,0.1704247],"study_design_scores_gemma":[0.00009099618,0.0002012274,0.0029156,0.00004769084,0.00002526882,0.0001101006,0.0001278787,0.8791572,0.08464867,0.001397066,0.03121717,0.00006106585],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2877125,0.0003347244,0.5646946,0.0008890067,0.001255135,0.0008226673,0.01620798,0.07001194,0.0580714],"genre_scores_gemma":[0.6051359,0.0002096636,0.3339508,0.0005289993,0.00006335627,0.0008435311,0.03192165,0.009558136,0.01778803],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01061324,"threshold_uncertainty_score":0.03550482,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05646828292270497,"score_gpt":0.2804566178393263,"score_spread":0.2239883349166214,"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."}}