{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01475599,0.000573985,0.0005568624,0.005227426,0.003097813,0.01660665,0.003570331,0.001633741,0.004697041],"category_scores_gemma":[0.03673709,0.001000938,0.001051951,0.005508848,0.008269963,0.02689698,0.009789324,0.003697456,0.002103472],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002656221,"about_ca_system_score_gemma":0.005579737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007298624,"about_ca_topic_score_gemma":0.009600621,"domain_scores_codex":[0.9921631,0.003679984,0.0007201562,0.0007794483,0.002453074,0.0002042953],"domain_scores_gemma":[0.9678537,0.01196909,0.001684487,0.01499543,0.002623328,0.0008739235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008377885,0.00008740333,0.004938898,0.0002917815,0.00003153276,0.0004637858,0.01746922,0.005535663,0.001374362,0.7091882,0.01751334,0.2430221],"study_design_scores_gemma":[0.00003599565,0.00005641716,0.001325002,0.0005482697,0.00004764331,0.0007025928,0.009504679,0.02974008,0.00614093,0.3603589,0.5914206,0.0001189299],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01144488,0.0003355567,0.9567773,0.007275556,0.0001341264,0.0003490016,0.0006463029,0.004410648,0.01862662],"genre_scores_gemma":[0.08214237,0.0005533309,0.9055367,0.0005061801,0.00006978304,0.0002510198,0.0009686905,0.001178905,0.008793111],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01660665,"threshold_uncertainty_score":0.0780381,"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."}}