{"id":"W4401349543","doi":"10.21203/rs.3.rs-4676415/v1","title":"A Geography of indoors for analyzing global ways of living using computer vision","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Urban Planning and Landscape Design","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Geography; Computer vision; Artificial intelligence; Data science; Regional science; Human–computer interaction","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":[0.001789837,0.0001694582,0.0003297901,0.0002663414,0.0001034274,0.00007077646,0.0004304158,0.0002428565,0.0001111007],"category_scores_gemma":[0.0001530494,0.0001477981,0.0002721841,0.0006603773,0.0002274188,0.00004322039,0.001869024,0.0006584764,0.00001333185],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000177196,"about_ca_system_score_gemma":0.00006384874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009802692,"about_ca_topic_score_gemma":0.00001676605,"domain_scores_codex":[0.9976619,0.0001996154,0.0003414278,0.0005161071,0.0008381119,0.000442768],"domain_scores_gemma":[0.998648,0.0006784751,0.0001236073,0.0003876601,0.00007322792,0.00008895889],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001498234,0.0002699177,0.8341953,0.004889666,0.0002784982,0.00006410657,0.001307143,0.03444551,0.003539906,0.000150869,0.110154,0.01055524],"study_design_scores_gemma":[0.000391754,0.001729325,0.2746752,0.02068688,0.0002023146,0.00002040217,0.0003080397,0.6913124,0.001220787,0.006142164,0.002400963,0.0009097588],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9790298,0.000866337,0.01729856,0.0001919464,0.0001902855,0.0009397456,0.0003675933,0.00005219937,0.001063529],"genre_scores_gemma":[0.9924549,0.00001461438,0.00732968,0.00001663488,0.000109665,0.0000179203,0.00002249134,0.00001979844,0.00001432821],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6568669,"threshold_uncertainty_score":0.6027032,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07442755063360723,"score_gpt":0.3711087440744886,"score_spread":0.2966811934408814,"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."}}