{"id":"W3210708818","doi":"10.5281/zenodo.3633290","title":"General web archive collection derivatives","year":2020,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"World Wide Web; Computer science; Information retrieval; Database","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":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003957741,0.0002444367,0.000278948,0.0004640215,0.002125315,0.001983345,0.003476771,0.0001040475,0.002591297],"category_scores_gemma":[0.0006893848,0.0002571578,0.000105062,0.001381174,0.0001315436,0.0003763214,0.003623516,0.000530426,0.01506759],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001136974,"about_ca_system_score_gemma":0.00001832297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004512607,"about_ca_topic_score_gemma":0.000001436729,"domain_scores_codex":[0.9974057,0.0005967693,0.0003058191,0.0008207313,0.0005044861,0.0003664744],"domain_scores_gemma":[0.998255,0.00003777706,0.000216915,0.000955993,0.0002980639,0.0002362905],"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":[0.00001044415,0.00005735736,8.902658e-8,0.0000445738,0.00008676522,0.00002693759,0.0002311587,0.0000204108,0.0003281405,0.0004772224,0.9905615,0.008155413],"study_design_scores_gemma":[0.000221874,0.000194273,0.00001776899,0.0000314963,0.00002982559,0.00005822828,0.00003878623,0.004736123,0.00004936821,0.0001013464,0.9942518,0.0002690552],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00002145635,0.00003413464,0.03497903,0.0009798266,0.0001710114,0.0002165616,0.9580101,0.0007726374,0.004815174],"genre_scores_gemma":[0.0001464608,0.0002659688,0.002854159,0.0003003857,0.0003196875,5.447661e-8,0.9952725,0.0004584822,0.0003822977],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.03726234,"threshold_uncertainty_score":0.9999881,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03233145758320511,"score_gpt":0.2434345214602063,"score_spread":0.2111030638770012,"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."}}