{"id":"W4295094076","doi":"10.1080/23257962.2022.2100336","title":"Creating order from the mess: web archive derivative datasets and notebooks","year":2022,"lang":"en","type":"article","venue":"Archives and Records","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; York University","funders":"Andrew W. Mellon Foundation","keywords":"World Wide Web; Computer science; Point (geometry); Order (exchange)","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0001517532,0.0001015076,0.000129772,0.00004860065,0.0008100139,0.0001510449,0.000513455,0.000007977957,0.00002926184],"category_scores_gemma":[0.0000500209,0.00006796526,0.00002707108,0.0001315992,0.000131885,0.0001258649,0.001481902,0.0001952826,0.00000138052],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002803775,"about_ca_system_score_gemma":0.00004239756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005783933,"about_ca_topic_score_gemma":0.000100577,"domain_scores_codex":[0.9990074,0.0002159117,0.000127668,0.0003640087,0.0001249517,0.0001600848],"domain_scores_gemma":[0.9985533,0.0009297194,0.00007057348,0.0003820251,0.00000457897,0.0000597787],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004739396,0.00008634826,0.02342148,0.00001466689,0.0003616152,0.00005624505,0.03984715,0.0001000725,0.00298439,0.01886933,0.01442663,0.8997847],"study_design_scores_gemma":[0.001309247,0.000436876,0.07757387,0.00009997141,0.0001360683,0.00008776907,0.008744512,0.5988041,0.0002272664,0.0668755,0.2449006,0.0008042143],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7040312,0.001886088,0.2605151,0.007371067,0.0004637703,0.0003756311,0.006214693,0.0001905546,0.01895189],"genre_scores_gemma":[0.8653771,0.0005276671,0.1305476,0.001776779,0.0002016114,0.00005496557,0.0008386228,0.00001822526,0.000657368],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8989804,"threshold_uncertainty_score":0.6230053,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01105804425713074,"score_gpt":0.2253570037640169,"score_spread":0.2142989595068861,"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."}}