{"id":"W2740290295","doi":"10.1145/3097570","title":"Warcbase","year":2017,"lang":"en","type":"article","venue":"Journal on Computing and Cultural Heritage","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; World Wide Web; SPARK (programming language); Scalability; Big data; Process (computing); Data science; Web modeling; Analytics; Filter (signal processing); Resource (disambiguation); Web service; Database","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":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003663294,0.0001129922,0.0001560468,0.0000368927,0.001730122,0.002117421,0.0008506147,0.00003309366,0.000006319752],"category_scores_gemma":[0.00009625746,0.00007500048,0.00008225271,0.00004409791,0.00005037129,0.0006367514,0.0002643925,0.0002838165,0.00002951519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001508133,"about_ca_system_score_gemma":0.00001408107,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001298351,"about_ca_topic_score_gemma":0.000001856518,"domain_scores_codex":[0.9991629,0.00004563432,0.0001709783,0.0002128311,0.0001951648,0.0002125008],"domain_scores_gemma":[0.9991061,0.00003716972,0.0002161837,0.0004168726,0.0000615179,0.0001621701],"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":[0.00001942723,0.0001493088,0.007326645,0.00002626394,0.0001417758,0.0009051923,0.002904461,0.0001785544,0.002359163,0.01871848,0.01822824,0.9490425],"study_design_scores_gemma":[0.004853296,0.001726101,0.2260868,0.001544014,0.000132546,0.005319497,0.002608822,0.5846301,0.002169314,0.005248337,0.1631465,0.002534692],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9784697,0.0001901293,0.01287972,0.003714937,0.0005846311,0.00002380559,0.000001716101,0.00008226868,0.004053134],"genre_scores_gemma":[0.9888446,0.00004473359,0.00971001,0.0003483742,0.0003488277,1.521043e-7,7.141358e-7,0.000003848448,0.0006987763],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9465078,"threshold_uncertainty_score":0.9995695,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03107071811273536,"score_gpt":0.3015826552369414,"score_spread":0.2705119371242061,"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."}}