{"id":"W2899794679","doi":"10.20383/101.036","title":"Derivative data for Web Archives for Longitudinal Knowledge (WALK)","year":2018,"lang":"en","type":"article","venue":"Open MIND","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"World Wide Web; Computer science; Data file; Hyperlink; File format; Web page; Information retrieval; Database","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003402583,0.0007580114,0.0006385351,0.007242902,0.001374369,0.003775225,0.001649175,0.001012295,0.1325821],"category_scores_gemma":[0.03437067,0.0008792455,0.0006266016,0.01221965,0.0004791968,0.003616723,0.003015514,0.001651103,0.08569799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002515969,"about_ca_system_score_gemma":0.007014913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.06880875,"about_ca_topic_score_gemma":0.09452575,"domain_scores_codex":[0.9974563,0.0003553449,0.0004474681,0.0003670103,0.001121432,0.000252578],"domain_scores_gemma":[0.9711902,0.006080103,0.002302565,0.007649262,0.01147916,0.001298628],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001499877,0.00002952663,0.001821288,0.0004677369,0.00002169627,0.00005907492,0.0003378616,0.0001926934,0.0003522037,0.003177347,0.9793114,0.01407916],"study_design_scores_gemma":[0.00008479886,0.00001428554,0.007156375,0.0002203506,0.00001854747,0.00007264591,0.0003469196,0.0003105822,0.0009228681,0.002348032,0.9884558,0.00004881599],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.001022693,0.00004274064,0.001741694,0.0002081814,0.00008063441,0.0001071124,0.9858783,0.005448118,0.005470487],"genre_scores_gemma":[0.003602,0.00009069965,0.006041876,0.00009564501,0.00003126322,0.0005094521,0.9797063,0.00344672,0.006476028],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.1325821,"threshold_uncertainty_score":0.4435313,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2073289002366643,"score_gpt":0.4069224976154345,"score_spread":0.1995935973787702,"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."}}