{"id":"W4414675845","doi":"10.1016/j.autcon.2025.106562","title":"ControlNet-based domain adaptation for synthetic construction images via graphical simulation and generative AI","year":2025,"lang":"en","type":"article","venue":"Automation in Construction","topic":"Image Processing and 3D Reconstruction","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Hyperparameter; Synthetic data; Generative grammar; Artificial neural network; Adaptation (eye); Domain (mathematical analysis); Representation (politics); Architecture","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":[0.0004634661,0.0001983727,0.0002436267,0.000737323,0.0003682075,0.0002975683,0.0001230233,0.0001839303,0.00000322316],"category_scores_gemma":[0.000155097,0.0002102297,0.00006500102,0.0007149035,0.0003094618,0.001128541,0.00002382805,0.0001650518,0.000001837931],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001189646,"about_ca_system_score_gemma":0.0002190387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001919446,"about_ca_topic_score_gemma":0.00001790316,"domain_scores_codex":[0.9983863,0.0002084219,0.0004851285,0.0005184867,0.0001829482,0.0002186969],"domain_scores_gemma":[0.998762,0.0003718853,0.0002657862,0.0002163714,0.0003406751,0.00004329187],"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":[0.00008768588,0.00004976216,0.00397621,0.0001563466,0.00003562534,0.000001036738,0.0003326503,0.06596551,0.005233645,0.1147236,0.00003626227,0.8094016],"study_design_scores_gemma":[0.001569333,0.00004739344,0.002718847,0.00009828829,0.00002090313,0.00003762432,0.0001552076,0.8877861,0.005453744,0.1018064,0.0001275042,0.0001786411],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03802773,0.00009567149,0.9567062,0.003095204,0.001083647,0.0005753276,0.000005936819,0.0002898265,0.0001204342],"genre_scores_gemma":[0.6790385,0.000004513713,0.3205796,0.0001897936,0.00003943328,0.0001134371,0.00001792248,0.000006514386,0.00001036962],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8218207,"threshold_uncertainty_score":0.8572917,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007687378988239925,"score_gpt":0.2659110875364778,"score_spread":0.2582237085482379,"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."}}