{"id":"W2793625150","doi":"10.1002/asi.24048","title":"If these crawls could talk: Studying and documenting web archives provenance","year":2018,"lang":"en","type":"article","venue":"Journal of the Association for Information Science and Technology","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"World Wide Web; Computer science; Transparency (behavior); Context (archaeology); Data science; Process (computing); Geography; Archaeology","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":[0.002150562,0.00004981274,0.0001060115,0.0004601546,0.0004679193,0.0003866922,0.0007011126,0.00004008817,3.072747e-7],"category_scores_gemma":[0.001942466,0.0000319467,0.00002628307,0.001077252,0.0002343643,0.003329937,0.0002822742,0.0001082773,0.000001187654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005089272,"about_ca_system_score_gemma":0.0001522767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001262643,"about_ca_topic_score_gemma":0.000001134982,"domain_scores_codex":[0.9990699,0.00001534346,0.0003035967,0.00007754128,0.0003764717,0.0001571238],"domain_scores_gemma":[0.9981992,0.0001051685,0.0009151616,0.0001553424,0.0005981321,0.00002704936],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002127415,0.00006679184,0.1036576,0.00004514571,0.0001622434,7.037663e-7,0.01654205,0.00003798578,0.02249401,0.2451307,0.002368282,0.6094733],"study_design_scores_gemma":[0.004280523,0.001440921,0.06303629,0.0004357376,0.0001900799,0.0002829324,0.01127026,0.2957872,0.06294978,0.1122489,0.4473016,0.0007758298],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9213243,0.00008337849,0.0508798,0.02392402,0.0006254092,0.0002826922,0.000008878811,0.00006970823,0.002801787],"genre_scores_gemma":[0.9934469,0.00003329608,0.006200859,0.0001903683,0.00003443585,0.000002646181,1.394051e-7,9.521822e-7,0.00009036021],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6086974,"threshold_uncertainty_score":0.3728882,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009031874620079431,"score_gpt":0.2572771037646895,"score_spread":0.2482452291446101,"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."}}