{"id":"W2578588058","doi":"10.1017/s0008423916001165","title":"Digitization of the Canadian Parliamentary Debates","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Political Science","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Digitization; House of Commons; Political science; Architecture; Politics; Commons; Public administration; Library science; Media studies; Computer science; Sociology; Geography; Law; Telecommunications; Parliament; Archaeology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":["sts"],"category_scores_codex":[0.0016382,0.00004155531,0.00009448113,0.0001820176,0.002859258,0.0003601473,0.00107933,0.00002905629,0.0001537231],"category_scores_gemma":[0.003748757,0.00002944227,0.00007551714,0.0002777265,0.003048855,0.0004020554,0.00001920739,0.00009303835,0.000002827996],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007070474,"about_ca_system_score_gemma":0.015425,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9705923,"about_ca_topic_score_gemma":0.9947588,"domain_scores_codex":[0.9986835,0.00008462875,0.0001916317,0.00007357745,0.0004549439,0.0005116911],"domain_scores_gemma":[0.9974084,0.00009901572,0.0001734716,0.0001492127,0.0005008053,0.001669034],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[3.920013e-7,0.000002914571,0.1416765,0.000001037972,0.000005240062,0.000006535107,0.0006417116,0.00002908103,0.00001933166,0.8527229,0.0001709262,0.004723422],"study_design_scores_gemma":[0.0000472285,0.0000110019,0.9320996,0.00002519091,0.0000148687,0.000005288927,0.0007140479,0.00009992487,0.0002579543,0.06102996,0.005643808,0.00005110227],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8986006,0.00005330582,0.0003519087,0.04180527,0.001100892,0.00008202303,0.00001903805,0.000001960127,0.05798501],"genre_scores_gemma":[0.9988765,0.000001066159,0.0003613151,0.0004281864,0.0001685268,1.928658e-7,1.472954e-7,0.000001713232,0.0001623164],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.791693,"threshold_uncertainty_score":0.9996642,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04302063556107077,"score_gpt":0.3648532980313726,"score_spread":0.3218326624703018,"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."}}