{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.02888314,0.0003587739,0.0005278946,0.00808701,0.006125059,0.01065745,0.001260891,0.001457262,0.001757334],"category_scores_gemma":[0.148514,0.000952763,0.0006184802,0.006582465,0.006081573,0.01454659,0.005231049,0.002092135,0.0005452758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003513149,"about_ca_system_score_gemma":0.006998329,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01201761,"about_ca_topic_score_gemma":0.01849698,"domain_scores_codex":[0.9790562,0.01231174,0.001875873,0.001573573,0.004526153,0.0006564723],"domain_scores_gemma":[0.8665952,0.08960489,0.01252298,0.01847989,0.01144295,0.001354112],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0005412119,0.0002908982,0.2166717,0.0008106907,0.0001286975,0.002244584,0.4190868,0.002723923,0.006205402,0.1183854,0.00431576,0.2285949],"study_design_scores_gemma":[0.0001070045,0.0003358926,0.1818789,0.002890706,0.0004034496,0.003085685,0.2674572,0.02474111,0.02687773,0.2069003,0.2848721,0.0004500595],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8341457,0.002111535,0.1106026,0.003947759,0.0002119672,0.001108731,0.001301015,0.001107324,0.04546328],"genre_scores_gemma":[0.9164476,0.001092215,0.07524218,0.0002649099,0.00007829519,0.0004572193,0.0007548556,0.0004432504,0.005219341],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9893426,"threshold_uncertainty_score":0.1527505,"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."}}