{"id":"W3139005893","doi":"10.1016/j.forsciint.2021.110753","title":"Collecting data on textiles from the internet using web crawling and web scraping tools","year":2021,"lang":"en","type":"article","venue":"Forensic Science International","topic":"Forensic and Genetic Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"International Centre for Comparative Criminology; Université du Québec à Trois-Rivières","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds de Recherche du Québec-Société et Culture","keywords":"Population; Clothing; Computer science; Field (mathematics); The Internet; Textile; World Wide Web; Engineering; Mathematics; Geography; Medicine","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001327006,0.0008440828,0.0007080714,0.01332399,0.0009665816,0.001611856,0.0005076083,0.0005683627,0.003865114],"category_scores_gemma":[0.005785113,0.0003233455,0.0007437784,0.007720302,0.0003250569,0.001278961,0.001253901,0.0004908761,0.004067355],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003149991,"about_ca_system_score_gemma":0.001049695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004183285,"about_ca_topic_score_gemma":0.005887995,"domain_scores_codex":[0.9976406,0.0003337882,0.0004465148,0.0004872414,0.000917939,0.0001740732],"domain_scores_gemma":[0.9911826,0.002525451,0.001076956,0.002132986,0.00254528,0.0005367037],"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":[0.0006700481,0.00101201,0.3091294,0.002604273,0.0003588706,0.002009421,0.003513548,0.002728979,0.07535215,0.001591682,0.02920379,0.5718257],"study_design_scores_gemma":[0.00005519639,0.0004263748,0.7945933,0.0006070258,0.0004060969,0.00238573,0.004258047,0.02361215,0.06650165,0.003249607,0.1037335,0.0001712961],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.767737,0.001071429,0.07017168,0.0003535535,0.000142496,0.002408626,0.1124528,0.01247112,0.0331912],"genre_scores_gemma":[0.6598756,0.001393616,0.1505886,0.0002241918,0.0001291753,0.002117021,0.167436,0.001214643,0.01702115],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01332399,"threshold_uncertainty_score":0.0129301,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.098136974164257,"score_gpt":0.3628016248470887,"score_spread":0.2646646506828317,"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."}}