{"id":"W4406937501","doi":"10.1007/s10502-025-09475-z","title":"Conceptualizing aggregate-level description in web archives","year":2025,"lang":"en","type":"article","venue":"Archival Science","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council; Social Sciences and Humanities Research Council of Canada","keywords":"Cultural heritage; Web application; Aggregate (composite); World Wide Web; History; Data science; Geography; Computer science; Archaeology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006547297,0.0001020698,0.0001368095,0.0006061473,0.0002638953,0.0003318026,0.001964058,0.00001206736,0.000002770937],"category_scores_gemma":[0.0002510819,0.00009147114,0.00004586765,0.002307102,0.000628828,0.0009524369,0.0007214395,0.0001404458,0.00002351039],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003512282,"about_ca_system_score_gemma":0.0003935704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000106174,"about_ca_topic_score_gemma":0.00006939026,"domain_scores_codex":[0.9984065,0.0000818491,0.0002183043,0.0005761839,0.0002926371,0.0004245474],"domain_scores_gemma":[0.9991315,0.0001612367,0.00005362766,0.0005430593,0.00002003965,0.0000905269],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005513648,0.00006422351,0.01925293,0.000009808949,0.000006917019,0.00001852728,0.003161408,0.0003598145,0.1169182,0.5169166,0.0001910315,0.343095],"study_design_scores_gemma":[0.0005815304,0.00005593086,0.2535336,0.0003570165,0.000008935283,0.00001041043,0.0004650169,0.6529517,0.01408722,0.07500252,0.00253911,0.0004070038],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4868189,0.00008867394,0.4702257,0.001205645,0.0003062196,0.00008463157,0.000005947674,0.000125813,0.0411384],"genre_scores_gemma":[0.9541003,0.00002496408,0.04500921,0.0002807959,0.00001419214,0.00000624144,0.000001689193,0.000001969114,0.0005606025],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6525919,"threshold_uncertainty_score":0.3730085,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03931571689309058,"score_gpt":0.2820524073915678,"score_spread":0.2427366904984773,"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."}}