{"id":"W4385386988","doi":"10.18280/ria.370320","title":"Evaluation of Short Answers Using Domain Specific Embedding and Siamese Stacked BiLSTM with Contrastive Loss","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Domain (mathematical analysis); Embedding; Computer science; Artificial intelligence; Natural language processing; Linguistics; Mathematics; Philosophy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002113814,0.0001511163,0.0002245433,0.0002146253,0.0001274145,0.00008397945,0.0003432535,0.00005480387,0.0000234927],"category_scores_gemma":[0.00006734609,0.0001390798,0.0000414676,0.0009145878,0.000145398,0.0003408227,0.0001275105,0.0001177801,0.00001649279],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009533665,"about_ca_system_score_gemma":0.00009605786,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002192005,"about_ca_topic_score_gemma":0.000009647551,"domain_scores_codex":[0.9980429,0.0001435895,0.0003919728,0.0005181162,0.0005836147,0.0003198166],"domain_scores_gemma":[0.9987864,0.0001739217,0.0001075205,0.000511464,0.0003384901,0.00008223493],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002412326,0.00005543879,0.00189487,0.00005109409,0.00004701513,0.00003642102,0.009483585,0.8405542,0.02421506,0.01391286,0.00002375792,0.1097016],"study_design_scores_gemma":[0.00006740831,0.00006546532,0.0001477027,0.00013392,0.00001945892,0.00002337864,0.002560453,0.9714883,0.02135512,0.003864667,0.0001122844,0.0001618627],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4658264,0.0001306903,0.5333917,0.00008694033,0.00009692625,0.0002195444,0.000001695116,0.00004892645,0.0001971832],"genre_scores_gemma":[0.9673707,0.00005049588,0.03246232,0.00001261052,0.0000417953,0.00001223802,0.000002116153,0.00001306005,0.00003461243],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5015444,"threshold_uncertainty_score":0.5671508,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1025520882371787,"score_gpt":0.3313457783093441,"score_spread":0.2287936900721654,"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."}}