{"id":"W4324277966","doi":"10.1177/20539517231163172","title":"All WARC and no playback: The materialities of data-centered web archives research","year":2023,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Computer science; Standardization; Metadata; World Wide Web; Interoperability; Data science","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":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.002478977,0.0001024515,0.000175458,0.00004880204,0.0002489611,0.0003765306,0.005601711,0.00003752278,0.000008839025],"category_scores_gemma":[0.0001521281,0.00006937542,0.00004211999,0.0004816671,0.0004129514,0.0006961331,0.01147366,0.000161957,0.00007418644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005659326,"about_ca_system_score_gemma":0.0001203881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003321691,"about_ca_topic_score_gemma":0.00004098884,"domain_scores_codex":[0.9980648,0.0002567737,0.0002292763,0.0006391259,0.0004526539,0.0003573921],"domain_scores_gemma":[0.995361,0.0005182106,0.00006787346,0.003945744,0.00004435579,0.00006282981],"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":[0.000009645178,0.00004268405,0.0004703263,0.0001054039,0.0002223314,0.000003933638,0.005587243,8.158123e-7,0.006737655,0.001113817,0.9629284,0.02277779],"study_design_scores_gemma":[0.0005525509,0.00004576899,0.003978889,0.0001050901,0.00005136314,0.000007085087,0.004481418,0.2469925,0.0003881781,0.00080127,0.7423357,0.0002601461],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8106482,0.002939621,0.02754191,0.04438158,0.003853623,0.001351691,0.1021555,0.001490028,0.005637828],"genre_scores_gemma":[0.9070123,0.01190964,0.05208403,0.0009590285,0.001433777,0.00002749605,0.022795,0.00005144736,0.00372724],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2469917,"threshold_uncertainty_score":0.9997784,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4562295496170037,"score_gpt":0.3975399753386789,"score_spread":0.05868957427832477,"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."}}