{"id":"W3133076675","doi":"","title":"AriEL: Volume Coding for Sentence Generation Comparisons","year":2021,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Benchmark (surveying); Language model; Artificial intelligence; Sampling (signal processing); Autoencoder; Coding (social sciences); Natural language processing; Machine learning; Data mining; Deep learning; Mathematics; Computer vision; Statistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004970828,0.001258912,0.0008599033,0.002656443,0.0007959874,0.002136692,0.00288848,0.001951055,0.01885919],"category_scores_gemma":[0.02810744,0.0003525572,0.001092509,0.001505449,0.0008867338,0.00418305,0.002859647,0.002459464,0.003123583],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001329219,"about_ca_system_score_gemma":0.00125304,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002205697,"about_ca_topic_score_gemma":0.003663197,"domain_scores_codex":[0.9959893,0.001818938,0.0003197845,0.0007606545,0.0008710187,0.0002404071],"domain_scores_gemma":[0.9911326,0.005869704,0.0003194204,0.001472034,0.001017025,0.0001892438],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001916402,0.0003330578,0.002785663,0.0007596192,0.0002402916,0.0002602378,0.0004086742,0.1581467,0.01107131,0.05934055,0.03991302,0.7248244],"study_design_scores_gemma":[0.0002557233,0.0005481071,0.001076358,0.00009108787,0.00004053603,0.0001947477,0.0001845206,0.8843219,0.01308697,0.08786459,0.01226764,0.00006778468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05499009,0.001933339,0.9125796,0.0006695077,0.0007055812,0.0004580729,0.004936838,0.01443054,0.009296454],"genre_scores_gemma":[0.4342462,0.0003988908,0.5400597,0.0005208196,0.0002405734,0.001148792,0.01466821,0.003274155,0.005442581],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01885919,"threshold_uncertainty_score":0.06309026,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04400621447422936,"score_gpt":0.3029627731544972,"score_spread":0.2589565586802678,"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."}}