{"id":"W4220659750","doi":"10.3390/buildings12030354","title":"Towards Automated Construction Quantity Take-Off: An Integrated Approach to Information Extraction from Work Descriptions","year":2022,"lang":"en","type":"article","venue":"Buildings","topic":"BIM and Construction Integration","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Hidden Markov model; Conditional random field; Information extraction; Artificial intelligence; Process (computing); Machine learning; Natural language processing; Named-entity recognition; Field (mathematics); 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":[],"consensus_categories":[],"category_scores_codex":[0.0001749232,0.000182142,0.0001547724,0.0003355615,0.000368755,0.0002013749,0.0001612424,0.0001053605,0.0003373672],"category_scores_gemma":[0.00003176204,0.0002051536,0.00005768206,0.0009736062,0.00003489757,0.001402551,0.00003187524,0.0003765361,0.00005353133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004503693,"about_ca_system_score_gemma":0.00005377779,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006854804,"about_ca_topic_score_gemma":0.00002576779,"domain_scores_codex":[0.9988753,0.00006166133,0.0003752623,0.0002007103,0.0002848237,0.0002022295],"domain_scores_gemma":[0.9994534,0.00001159051,0.00008236321,0.0002146873,0.0001249691,0.0001129554],"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":[0.0001708098,0.000148092,0.00253536,0.00003067748,0.0001231442,0.000001187937,0.004032564,0.2921664,0.01976828,0.02521507,0.02535414,0.6304544],"study_design_scores_gemma":[0.0008624126,0.0001495945,0.02526778,0.00004155171,0.00009210997,0.0001571963,0.01261653,0.6098071,0.004325099,0.0009482998,0.3448151,0.0009172218],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6849824,0.00004260554,0.307602,0.00005607563,0.001931066,0.0002876844,0.0001236156,0.002495027,0.00247953],"genre_scores_gemma":[0.9237676,0.00001020082,0.07503222,0.00009798662,0.00009385669,0.0002090248,0.0007426173,0.00002291664,0.00002359408],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6295371,"threshold_uncertainty_score":0.836592,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01544492117892426,"score_gpt":0.2254504924078148,"score_spread":0.2100055712288905,"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."}}