{"id":"W4407066124","doi":"10.1190/tle44020108.1","title":"Advancing geologic document digitalization and information retrieval with generative AI","year":2025,"lang":"en","type":"article","venue":"The Leading Edge","topic":"Image Processing and 3D Reconstruction","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Virtual Materials Group (Canada)","funders":"","keywords":"Generative grammar; Information retrieval; Computer science; Artificial intelligence","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001747489,0.00005711745,0.00005711894,0.00006807152,0.0002247747,0.000353542,0.0001205427,0.00002146112,5.752488e-7],"category_scores_gemma":[0.00004227548,0.00003477293,0.000007508536,0.0002803911,0.00005574296,0.002036679,0.00005745936,0.00007086866,0.000007565773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003337382,"about_ca_system_score_gemma":0.00005262224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000219614,"about_ca_topic_score_gemma":0.000001497151,"domain_scores_codex":[0.9996211,0.00002584143,0.00009214335,0.00009169739,0.00007003651,0.00009919724],"domain_scores_gemma":[0.9997183,0.00003277443,0.0000539246,0.0001104378,0.00007163757,0.00001291316],"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":[0.00006178415,0.00001734269,0.003649921,0.0001369372,0.00005170136,0.000002223406,0.007822643,0.0039789,0.001148656,0.1853761,0.003367753,0.794386],"study_design_scores_gemma":[0.002475826,0.0005067962,0.006879732,0.0008130352,0.00009297507,0.0003637202,0.0010219,0.6682665,0.1122244,0.1434106,0.06298329,0.0009611729],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02643594,0.00009341294,0.9653432,0.003043379,0.0002399686,0.00008164073,1.693821e-7,0.0000894633,0.004672781],"genre_scores_gemma":[0.9862992,0.00002138384,0.0112642,0.00142147,0.00003362322,0.000004230561,0.000003168168,0.000001862624,0.0009509167],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9598632,"threshold_uncertainty_score":0.3409214,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.003977792339939269,"score_gpt":0.2314456312494914,"score_spread":0.2274678389095521,"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."}}