{"id":"W3181452428","doi":"10.3390/geosciences11070284","title":"Geologist in the Loop: A Hybrid Intelligence Model for Identifying Geological Boundaries from Augmented Ground Penetrating Radar","year":2021,"lang":"en","type":"article","venue":"Geosciences","topic":"Geophysical Methods and Applications","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Rio Tinto","keywords":"Ground-penetrating radar; Geologist; Drill; Geology; Radar; Drill hole; Representation (politics); Mining engineering; Sampling (signal processing); Artificial intelligence; Computer science; Remote sensing; Paleontology; Engineering; Computer vision","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004068432,0.0001039664,0.0001315554,0.00002344223,0.0003818056,0.0003774341,0.0003748355,0.00003028418,0.00001819757],"category_scores_gemma":[0.000185503,0.00007463645,0.00005113357,0.000302899,0.0003527457,0.0001474353,0.00006108321,0.0001357943,0.000006457185],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001685028,"about_ca_system_score_gemma":0.0000484295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003702609,"about_ca_topic_score_gemma":0.0004370233,"domain_scores_codex":[0.9990116,0.00004640917,0.0002150775,0.0002763972,0.0001704088,0.0002800919],"domain_scores_gemma":[0.9992914,0.0004232759,0.00003071678,0.0001875044,0.00003552088,0.00003165084],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003741049,0.000767939,0.00687717,0.0003269907,0.0001016085,0.0001031973,0.01399738,0.1659778,0.2331946,0.2978624,0.001111174,0.2796423],"study_design_scores_gemma":[0.00007132893,0.00001958247,0.01622057,0.00002122487,0.00001127679,0.000005020021,0.002069173,0.7860686,0.002141834,0.1925588,0.0006461774,0.0001663971],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5432161,0.0003273499,0.4557356,0.0002671345,0.0001091398,0.0001143198,0.00002107952,0.0000401999,0.0001690559],"genre_scores_gemma":[0.9213712,0.000036316,0.07821201,0.0001368768,0.00005004933,0.0001097022,0.00002045761,0.000004282668,0.00005913562],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6200908,"threshold_uncertainty_score":0.3639606,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0794651957924074,"score_gpt":0.3206846682256603,"score_spread":0.2412194724332529,"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."}}