{"id":"W4417279024","doi":"10.5194/ica-abs-10-104-2025","title":"Waterloo Urban Scene Dataset: An Annotation-Efficient Dataset for Urban Scene Classification with Minimal Supervision","year":2025,"lang":"en","type":"article","venue":"Abstracts of the ICA","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"University of Waterloo","keywords":"Urban planning; Field (mathematics); Feature (linguistics); Identification (biology)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001036888,0.0001715703,0.0002103663,0.0001070919,0.0002445636,0.0001458752,0.001446646,0.00007099585,0.000003516712],"category_scores_gemma":[0.0001411646,0.0001141983,0.00005000398,0.0003836897,0.0001071876,0.0004444809,0.0001730598,0.0001261251,0.000006420656],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000029392,"about_ca_system_score_gemma":0.0001431799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001391594,"about_ca_topic_score_gemma":0.00006646911,"domain_scores_codex":[0.998319,0.0001351175,0.0004163837,0.0005110315,0.0003321662,0.0002862781],"domain_scores_gemma":[0.9976447,0.0002920371,0.0002334508,0.001593948,0.0001631159,0.00007280063],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.001611387,0.005273518,0.03307099,0.0009893631,0.0005158913,0.00003030821,0.00443209,0.02319764,0.1466126,0.02057254,0.4162743,0.3474194],"study_design_scores_gemma":[0.002005656,0.0005490686,0.7116687,0.000299014,0.00009162143,0.00001193435,0.0001585397,0.1051756,0.09375439,0.000836463,0.08489578,0.0005532952],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8699309,0.0002741473,0.1054584,0.01025432,0.00153166,0.001677232,0.01038327,0.0001580415,0.0003320218],"genre_scores_gemma":[0.9441112,0.000004875741,0.05197618,0.0003514558,0.00005604611,0.00002248135,0.003407885,0.00001093002,0.00005897233],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6785977,"threshold_uncertainty_score":0.4656872,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03222426086323529,"score_gpt":0.3130429663802485,"score_spread":0.2808187055170133,"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."}}