{"id":"W4386802863","doi":"10.1080/24701475.2023.2258697","title":"Sorting URLs out: seeing the web through infrastructural inversion of archival crawling","year":2023,"lang":"en","type":"article","venue":"Internet Histories","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Crawling; World Wide Web; Sorting; Computer science; Web crawler; Biology; Algorithm; Anatomy","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006978214,0.0004162294,0.0004720413,0.006793641,0.007484465,0.01579505,0.001356723,0.001627885,0.002671913],"category_scores_gemma":[0.0156856,0.0006126156,0.000373005,0.005526929,0.02020105,0.01615783,0.009871802,0.002821351,0.0005488655],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004899851,"about_ca_system_score_gemma":0.003239079,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01235611,"about_ca_topic_score_gemma":0.02093137,"domain_scores_codex":[0.9950348,0.003164031,0.0001935162,0.0004803427,0.0006582804,0.0004690563],"domain_scores_gemma":[0.9868233,0.009333084,0.001051442,0.001641073,0.0007487473,0.0004022837],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00007075501,0.00002729853,0.01443068,0.0001582465,0.00001457903,0.0007807885,0.8561668,0.0002786176,0.002359174,0.09026129,0.001140261,0.03431146],"study_design_scores_gemma":[0.000013048,0.00004138752,0.01751236,0.0004413681,0.00005508805,0.001190545,0.7775674,0.002697718,0.003872184,0.09618125,0.1003657,0.00006203689],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.807066,0.002870226,0.06563994,0.008410998,0.00009421474,0.0001123047,0.000281214,0.0003754373,0.1151498],"genre_scores_gemma":[0.9840793,0.0005390687,0.01211907,0.0002208983,0.00002007082,0.00004700887,0.00007062025,0.0001476007,0.002756349],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01579505,"threshold_uncertainty_score":0.03690475,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02772148894892974,"score_gpt":0.2590313469284807,"score_spread":0.231309857979551,"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."}}