{"id":"W4405390300","doi":"10.1111/mice.13397","title":"A semi‐supervised approach for building wall layout segmentation based on transformers and limited data","year":2024,"lang":"en","type":"article","venue":"Computer-Aided Civil and Infrastructure Engineering","topic":"3D Surveying and Cultural Heritage","field":"Earth and Planetary Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates","keywords":"Segmentation; Computer science; Floor plan; Artificial intelligence; Transformer; Regularization (linguistics); Automation; Consistency (knowledge bases); Pattern recognition (psychology); Engineering drawing; Engineering","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":[0.0002064284,0.0002049602,0.0001714097,0.00009730033,0.0001107636,0.0002349765,0.0001428405,0.00007898019,0.00003173052],"category_scores_gemma":[0.00001147582,0.0001588575,0.00003339227,0.0001626846,0.00002098262,0.0003273337,0.00001368312,0.0001678061,7.017418e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006138489,"about_ca_system_score_gemma":0.00001574991,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002916178,"about_ca_topic_score_gemma":0.0000162478,"domain_scores_codex":[0.9990407,0.00002158141,0.0001618735,0.0004143038,0.0001226164,0.0002389441],"domain_scores_gemma":[0.9995582,0.0001638058,0.00001570838,0.0001366899,0.00001346735,0.0001121437],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004934323,0.000007694599,0.00519793,0.0010117,0.00007427477,0.000007897037,0.0007404291,0.6722738,0.00155698,0.00006191909,0.0007454966,0.3182726],"study_design_scores_gemma":[0.0003256538,0.0001216022,0.02089666,0.0001197488,0.00002232176,0.00001479687,0.00004248108,0.976612,0.00006336901,0.00002658788,0.00154671,0.0002081092],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3268102,0.001087628,0.6706755,0.00007948005,0.0003843156,0.0002957424,0.0002646774,0.0002205371,0.0001819268],"genre_scores_gemma":[0.9445122,0.000040887,0.05409385,0.0001558507,0.0001791123,0.000003139914,0.0009958701,0.00001038592,0.000008720525],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.617702,"threshold_uncertainty_score":0.6478019,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0167588373294902,"score_gpt":0.2099454491519316,"score_spread":0.1931866118224413,"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."}}