{"id":"W2994999390","doi":"10.1016/j.autcon.2019.103045","title":"Automated excavators activity recognition and productivity analysis from construction site surveillance videos","year":2019,"lang":"en","type":"article","venue":"Automation in Construction","topic":"Occupational Health and Safety Research","field":"Health Professions","cited_by":191,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Mitacs","keywords":"Excavator; Productivity; Schedule; Activity recognition; Track (disk drive); Computer science; Engineering; Artificial intelligence; Civil 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":[0.001347322,0.0001981263,0.0004576627,0.000763682,0.0004290464,0.00002856381,0.00006860696,0.0003290912,0.0008728979],"category_scores_gemma":[0.0005110644,0.0002093076,0.00006655705,0.001810398,0.0001467629,0.0008325633,0.00005697132,0.0005932331,0.0005588222],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004290489,"about_ca_system_score_gemma":0.0003365901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004189745,"about_ca_topic_score_gemma":0.001895808,"domain_scores_codex":[0.9963938,0.001383884,0.0007053033,0.0006390233,0.0004492915,0.0004287015],"domain_scores_gemma":[0.9973668,0.001224126,0.00051952,0.0003510647,0.0003993661,0.0001391174],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002397852,0.00003104795,0.9290303,0.0001474983,0.00006767135,5.949628e-7,0.0003550971,0.000109141,0.001671557,0.0001219632,0.00003690916,0.06818846],"study_design_scores_gemma":[0.001054221,0.00004079518,0.9362705,0.00007922998,0.00003637933,0.000004128774,0.0003173067,0.06052087,0.0001904173,0.001173088,0.0001210789,0.0001919983],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9935262,0.00002834239,0.00120533,0.0006166211,0.001254811,0.001613051,0.0002822046,0.0005718583,0.00090161],"genre_scores_gemma":[0.9958968,0.00006131872,0.002893556,0.00005039885,0.0001650397,0.0001896011,0.0006849328,0.00001690122,0.00004145064],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06799646,"threshold_uncertainty_score":0.955762,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04385660045913507,"score_gpt":0.3887072293241019,"score_spread":0.3448506288649668,"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."}}