{"id":"W4405419073","doi":"10.1017/s1049096524000714","title":"Achieving Transparency, Traceability, and Readability with Human-Coded Data","year":2024,"lang":"en","type":"article","venue":"PS Political Science & Politics","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"University of Melbourne; Deutsche Forschungsgemeinschaft","keywords":"Readability; Traceability; Transparency (behavior); Political science; Computer science; Data science; Accounting; Business; Computer security; Software engineering; Programming language","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.004714926,0.0001655985,0.0002442374,0.0001622552,0.001298629,0.0006501403,0.0009143468,0.00007024705,0.0001258283],"category_scores_gemma":[0.00126572,0.0001285072,0.00005286032,0.0008960857,0.005857045,0.0008553846,0.0002288611,0.0002617095,0.00001188177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003532537,"about_ca_system_score_gemma":0.001406712,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008092169,"about_ca_topic_score_gemma":0.00214674,"domain_scores_codex":[0.9960722,0.0003040408,0.000345071,0.0008744365,0.001117551,0.001286676],"domain_scores_gemma":[0.9971408,0.001129442,0.00002840896,0.000567132,0.0001908667,0.0009433174],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000001630859,0.00006041422,0.01256475,0.00004033631,0.0000107594,0.000006824324,0.001799006,0.000003243625,0.00009372726,0.9821415,0.00002216978,0.003255671],"study_design_scores_gemma":[0.0001765389,0.0001775094,0.1825603,0.0001447593,0.0002920638,0.00002678454,0.00471885,0.01567982,0.0002302115,0.7795013,0.01577165,0.0007202299],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9174043,0.0002277082,0.00911594,0.01740426,0.0002203802,0.0002916991,0.0001237008,0.0003848552,0.05482718],"genre_scores_gemma":[0.9922512,0.000006621673,0.006712304,0.000246055,0.0003439241,0.000005070339,0.0000133281,0.000009799889,0.0004116638],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2026402,"threshold_uncertainty_score":0.9988135,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1341012651542852,"score_gpt":0.4721743285163266,"score_spread":0.3380730633620413,"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."}}