{"id":"W4399363341","doi":"10.1145/3630106.3659030","title":"Data, Annotation, and Meaning-Making: The Politics of Categorization in Annotating a Dataset of Faith-based Communal Violence","year":2024,"lang":"en","type":"article","venue":"","topic":"Media, Religion, Digital Communication","field":"Arts and Humanities","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Annotation; Politics; Categorization; Faith; Meaning (existential); Context (archaeology); Sociology; Computer science; Political science; Psychology; Epistemology; Law; Artificial intelligence; History","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":[],"consensus_categories":[],"category_scores_codex":[0.0004446139,0.00007744986,0.0001120213,0.0001134033,0.0001205284,0.0001608454,0.0003962784,0.00001973097,0.00003106541],"category_scores_gemma":[0.0001948845,0.00005593238,0.00001107478,0.00009888519,0.0003525141,0.0004059657,0.000153546,0.0001052326,0.00000186027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001208927,"about_ca_system_score_gemma":0.00008743659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001097038,"about_ca_topic_score_gemma":0.001952982,"domain_scores_codex":[0.9991133,0.00009544624,0.0004071204,0.0001256189,0.000165511,0.0000930557],"domain_scores_gemma":[0.998608,0.0005565188,0.0001254145,0.0005773422,0.0001179312,0.0000148092],"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":[0.000005864185,0.00003843756,0.0007202543,0.0002322893,0.00001219099,6.338674e-7,0.0113794,0.0001367084,0.00004815711,0.9825399,0.002518641,0.00236752],"study_design_scores_gemma":[0.0006971803,0.0002519992,0.001426114,0.00249046,0.0001165301,0.000006999299,0.00784428,0.5721201,0.0009335165,0.3729552,0.04068838,0.00046923],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5195895,0.02260298,0.02849863,0.007904696,0.00138615,0.003390075,0.0477763,0.0005532795,0.3682984],"genre_scores_gemma":[0.9949335,0.00007191322,0.000398921,0.000121829,0.00003138778,0.000005623534,0.00440375,0.000009211719,0.00002388421],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6095847,"threshold_uncertainty_score":0.2280856,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07266227581691898,"score_gpt":0.3107712937276856,"score_spread":0.2381090179107667,"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."}}