{"id":"W4320498557","doi":"10.1016/j.asw.2022.100691","title":"Comparing summative and dynamic assessments of L2 written argumentative discourse: Microgenetic validity evidence","year":2023,"lang":"en","type":"article","venue":"Assessing Writing","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"","keywords":"Summative assessment; Argumentative; Dialogic; Mediation; Argumentation theory; Psychology; Argument (complex analysis); Dynamic assessment; Protocol analysis; Construct (python library); Formative assessment; Mathematics education; Cognitive psychology; Linguistics; Computer science; Pedagogy; Cognitive science; Developmental psychology; Sociology","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":[0.001013256,0.0002189387,0.000361282,0.0001576032,0.000265875,0.0001394153,0.0002424677,0.00008977645,0.0001699845],"category_scores_gemma":[0.0001014172,0.0002065639,0.00006996513,0.0005366859,0.0002553662,0.0003781446,0.0001512925,0.0002733682,0.00006948712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007008985,"about_ca_system_score_gemma":0.00005613082,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009307525,"about_ca_topic_score_gemma":0.000006968981,"domain_scores_codex":[0.9976772,0.0004792122,0.0005323331,0.0005405232,0.0003334408,0.0004373117],"domain_scores_gemma":[0.9976856,0.0014671,0.0003733316,0.0002505397,0.0001179215,0.0001054956],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000286189,0.0003156081,0.9516743,0.0001380801,0.0002228403,0.00003199139,0.003639926,0.00001598006,0.01511944,0.001492771,0.000479597,0.02684086],"study_design_scores_gemma":[0.0004241585,0.000102328,0.968459,0.0006691645,0.00006895098,0.00001816279,0.02636199,0.0006184061,0.0003820533,0.002639026,0.00002255054,0.0002342366],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9913267,0.0004242029,0.0009936207,0.000593218,0.0004668519,0.0002323535,0.00001931119,0.00009252381,0.005851168],"genre_scores_gemma":[0.9959097,0.00006285457,0.003207688,0.0001073639,0.00007305128,0.00006547214,0.00005466223,0.000025044,0.0004941727],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02660662,"threshold_uncertainty_score":0.842343,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2598054623629933,"score_gpt":0.5350411908807765,"score_spread":0.2752357285177832,"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."}}