{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001835312,0.001886713,0.001699512,0.01708238,0.004190987,0.01227386,0.003435096,0.001452433,0.6011736],"category_scores_gemma":[0.01254506,0.001804082,0.001001736,0.02665691,0.001145577,0.006684811,0.006053859,0.003343187,0.6421238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005755323,"about_ca_system_score_gemma":0.01262255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.08523905,"about_ca_topic_score_gemma":0.1026777,"domain_scores_codex":[0.9969777,0.0002279516,0.0002736345,0.0003284012,0.001916402,0.0002759567],"domain_scores_gemma":[0.9862781,0.0007251924,0.0003708175,0.003654167,0.00772428,0.001247533],"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":[0.00002301904,0.00001362268,0.0001102768,0.0001190554,0.000002835755,0.00002807952,0.0000579685,0.00002791233,0.0001701577,0.001335703,0.9778788,0.02023268],"study_design_scores_gemma":[0.000005419531,0.000002417305,0.0002857235,0.00005860953,0.000002666021,0.00003503652,0.00003317267,0.00003754463,0.0002319363,0.0004378828,0.9988557,0.00001375747],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"dataset","genre_scores_codex":[0.0009973821,0.0008743412,0.005857302,0.001220219,0.001540496,0.0005892616,0.2667815,0.07279024,0.6493493],"genre_scores_gemma":[0.002920053,0.001183873,0.00818497,0.0007358606,0.0003858439,0.000536999,0.3237795,0.04170264,0.6205702],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.6011736,"threshold_uncertainty_score":0.5688775,"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."}}