{"id":"W4391328675","doi":"10.1111/mice.13157","title":"Improving single‐stage activity recognition of excavators using knowledge distillation of temporal gradient data","year":2024,"lang":"en","type":"article","venue":"Computer-Aided Civil and Infrastructure Engineering","topic":"Occupational Health and Safety Research","field":"Health Professions","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Excavator; Stage (stratigraphy); Distillation; Computer science; Artificial intelligence; Pattern recognition (psychology); Chemistry; Geology; Chromatography; Engineering; Mechanical 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005878003,0.001100924,0.001253268,0.001741143,0.0003309087,0.000926669,0.001390047,0.0007203454,0.001472654],"category_scores_gemma":[0.002012141,0.0003280959,0.0006854152,0.001253154,0.0004112714,0.001825314,0.001652002,0.001075503,0.001855334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003380984,"about_ca_system_score_gemma":0.0009937476,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006505351,"about_ca_topic_score_gemma":0.0161648,"domain_scores_codex":[0.9992822,0.00006319991,0.00003288419,0.000345483,0.0001612802,0.0001149691],"domain_scores_gemma":[0.9993817,0.0001692512,0.00007269538,0.000186255,0.0001519253,0.00003825214],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003659774,0.0002736568,0.01015955,0.0002481702,0.0001039992,0.0001642795,0.0001961193,0.0387852,0.04531624,0.001565386,0.005802458,0.8970189],"study_design_scores_gemma":[0.00004229307,0.0002645875,0.01818544,0.00006956132,0.00009794387,0.0003678871,0.0002964423,0.9054598,0.05767886,0.004832085,0.01263734,0.00006769547],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1188699,0.001125595,0.866131,0.0001935411,0.0001461758,0.0001013543,0.002000401,0.007951078,0.003480882],"genre_scores_gemma":[0.6685047,0.0005755353,0.3188924,0.0001635992,0.00007495698,0.000140805,0.00667234,0.0002882323,0.004687259],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006505351,"threshold_uncertainty_score":0.01293492,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08397353969764823,"score_gpt":0.379546892838633,"score_spread":0.2955733531409848,"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."}}