{"id":"W1480389727","doi":"10.3390/rs70505805","title":"Active Collection of Land Cover Sample Data from Geo-Tagged Web Texts","year":2015,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Geographic Information Systems Studies","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"National Natural Science Foundation of China; Hong Kong Polytechnic University; National Science Foundation","keywords":"Web crawler; Computer science; Sample (material); Land cover; Field (mathematics); Information retrieval; Data collection; World Wide Web; Database; Data mining; Land use","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":[0.0007129429,0.00006877126,0.0001709264,0.00008872365,0.000314707,0.000038524,0.0001184996,0.00007219,0.00001707709],"category_scores_gemma":[0.001097951,0.00006697257,0.00002611358,0.0003908397,0.0001213427,0.0003204902,0.00009931461,0.00006988594,0.00003762952],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008583615,"about_ca_system_score_gemma":0.000200531,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.06598737,"about_ca_topic_score_gemma":0.0189953,"domain_scores_codex":[0.9989372,0.0001424865,0.0002116599,0.0001373829,0.0004076135,0.000163628],"domain_scores_gemma":[0.9988549,0.0002908504,0.0002027189,0.0002612438,0.000327783,0.00006250365],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007049137,0.0001093207,0.04705687,0.0001209655,0.001337166,0.0000207576,0.6050216,0.0009504387,0.002469243,0.000683889,0.1103497,0.2311752],"study_design_scores_gemma":[0.003762847,0.0001090971,0.02324964,0.0004648099,0.000197579,0.00001126419,0.1049944,0.2005743,0.001090962,0.01082087,0.6538454,0.0008788728],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9100111,0.0001309009,0.005767382,0.0006193828,0.001059524,0.0003761341,0.0001976265,0.0001020311,0.08173594],"genre_scores_gemma":[0.9961801,0.00003928167,0.003164786,0.00004585581,0.0001964534,1.038036e-8,0.00005680446,0.000005349987,0.0003113347],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5434957,"threshold_uncertainty_score":0.9989055,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0878753615499763,"score_gpt":0.3247121121824642,"score_spread":0.2368367506324879,"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."}}