{"id":"W4253929481","doi":"10.32920/14640141.v1","title":"Active Collection of Land Cover Sample Data from Geo-Tagged Web Texts","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Geographic Information Systems Studies","field":"Social Sciences","cited_by":2,"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; Sample (material); Computer science; Information retrieval; Field (mathematics); Land cover; Data collection; World Wide Web; Database; Data mining; Land use; Engineering","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007135999,0.0001492303,0.0004089466,0.0001395013,0.0004092417,0.000135783,0.0005506055,0.0002875338,0.002319041],"category_scores_gemma":[0.0008395413,0.0001415502,0.00009011058,0.0003833678,0.0001763964,0.0003452277,0.001281925,0.0002456392,0.0000345535],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009875525,"about_ca_system_score_gemma":0.0007009887,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.2224209,"about_ca_topic_score_gemma":0.1543841,"domain_scores_codex":[0.9981754,0.0002184071,0.0004298803,0.0003470387,0.0006342166,0.0001950832],"domain_scores_gemma":[0.9977149,0.0005582864,0.0004653258,0.0006753277,0.0005338051,0.00005234731],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000187443,0.0003595718,0.5488771,0.0004988699,0.003850596,0.000005420045,0.2799593,0.0005162979,0.00008393286,0.003069644,0.159089,0.003502821],"study_design_scores_gemma":[0.002130816,0.0000557232,0.3540334,0.0007840267,0.0004468166,0.00000107898,0.1899505,0.00314544,0.0003937306,0.007522106,0.4400855,0.001450859],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5492921,0.0006288326,0.003896953,0.001315955,0.004641675,0.001861686,0.006930379,0.0002523112,0.43118],"genre_scores_gemma":[0.9938336,0.0005939907,0.0009978691,0.00006778939,0.0002345252,0.00003690277,0.001565304,0.00000782899,0.002662198],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4445414,"threshold_uncertainty_score":0.998593,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06884180027173903,"score_gpt":0.3298803352212289,"score_spread":0.2610385349494899,"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."}}