{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002648789,0.000108757,0.0001706012,0.00009897421,0.0001291469,0.00008845169,0.0009602063,0.00002487015,0.000008070742],"category_scores_gemma":[0.0001977919,0.00007896584,0.0001016027,0.0003899146,0.000141663,0.000425904,0.0005924832,0.0001495878,0.00004255725],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005577714,"about_ca_system_score_gemma":0.00005041548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003026833,"about_ca_topic_score_gemma":0.00005290216,"domain_scores_codex":[0.9989282,0.00005756591,0.0002879284,0.0002472099,0.0002670655,0.0002119913],"domain_scores_gemma":[0.9991525,0.0001707752,0.0001835661,0.000415551,0.00004956521,0.00002805746],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000608052,0.00005702386,0.05869954,0.0002886568,0.0005793779,0.000146356,0.5616254,0.00263886,0.05954704,0.09568491,0.1150907,0.1055813],"study_design_scores_gemma":[0.0006983764,0.0002265034,0.007908954,0.0005045466,0.000130195,0.00003141685,0.006103137,0.7371643,0.03526374,0.02224708,0.1887731,0.000948724],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9173786,0.0001417559,0.07443837,0.001386133,0.002167995,0.00005912956,0.00001017903,0.0003722828,0.004045543],"genre_scores_gemma":[0.9934469,0.000009787673,0.004638147,0.00006813569,0.0001081001,0.000002346968,0.0000095695,0.000007235199,0.001709795],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7345254,"threshold_uncertainty_score":0.3220133,"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."}}