{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005276331,0.00009548532,0.00007643641,0.00004917373,0.0002323004,0.0003556331,0.000764025,0.00004363711,0.00006813534],"category_scores_gemma":[0.001310445,0.00007270173,0.00002755421,0.0002024453,0.000596271,0.00002363279,0.001101214,0.0001135351,0.000005836458],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002875056,"about_ca_system_score_gemma":0.0004679573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009347421,"about_ca_topic_score_gemma":0.0003257765,"domain_scores_codex":[0.9985809,0.0000361132,0.0001571422,0.0005495341,0.0004567583,0.0002195975],"domain_scores_gemma":[0.99908,0.0001096774,0.00005605335,0.0004597737,0.000240244,0.00005426667],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006003253,0.00002563835,0.009601774,0.000002717624,0.00006589929,0.00001432838,0.0001659129,0.0001890121,0.9531293,0.0005549254,0.004605099,0.03158539],"study_design_scores_gemma":[0.0008694066,0.0001535568,0.009764097,0.0002417095,0.00001872164,0.0001433566,0.001482856,0.3012713,0.6392887,0.0008811489,0.04553789,0.0003472632],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9950819,0.0002980214,0.0007912496,0.0006999868,0.0006547143,0.00007119522,0.0001271743,0.00000579489,0.002269959],"genre_scores_gemma":[0.994424,0.00006652748,0.003747077,0.0007007911,0.0004715686,0.000002379767,0.0001797444,0.000008366326,0.0003994709],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3138406,"threshold_uncertainty_score":0.3429378,"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."}}