{"id":"W3120354622","doi":"10.1007/s42803-020-00029-6","title":"From archive to analysis: accessing web archives at scale through a cloud-based interface","year":2021,"lang":"en","type":"article","venue":"International Journal of Digital Humanities","topic":"Advanced Data Storage Technologies","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; York University","funders":"University of Waterloo; York University; Compute Canada; Andrew W. Mellon Foundation","keywords":"Cloud computing; World Wide Web; Computer science; Interface (matter); Scope (computer science); Mashup; Scale (ratio); Web development; Web service; Web page","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00004880402,0.000165536,0.000285684,0.0004522005,0.00008658868,0.001218802,0.002220909,0.0000291462,0.00004981038],"category_scores_gemma":[0.0001948018,0.0001531734,0.0002414141,0.0002886934,0.0001773274,0.002532289,0.001362162,0.0001991481,0.00002424498],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001441693,"about_ca_system_score_gemma":0.0001319588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007161641,"about_ca_topic_score_gemma":0.00006651474,"domain_scores_codex":[0.9984041,0.00003577526,0.0004825914,0.0002863004,0.0006062338,0.0001849319],"domain_scores_gemma":[0.9985079,0.0003890079,0.0003582682,0.0003702627,0.0003188589,0.00005567684],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002325243,0.003680671,0.03982329,0.0001147129,0.01955193,0.01332657,0.1121369,0.1153967,0.1138146,0.2206162,0.02691573,0.3322974],"study_design_scores_gemma":[0.002676174,0.0006284948,0.004413704,0.001154453,0.0003645369,0.0005249474,0.01217549,0.02186959,0.2418457,0.647766,0.06513856,0.001442354],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2701959,0.0003165288,0.724054,0.001152959,0.0006532406,0.00002878449,0.0003150715,0.00008100701,0.003202492],"genre_scores_gemma":[0.9070174,0.00001520147,0.09197813,0.0003620379,0.0002563109,0.000002483951,0.00004365001,0.000009892761,0.0003149013],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6368215,"threshold_uncertainty_score":0.999818,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03119082774501818,"score_gpt":0.3008049511167233,"score_spread":0.2696141233717051,"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."}}