{"id":"W4400282035","doi":"10.32473/flairs.37.1.135283","title":"Assessing the Impact of Sequence Length Learning on Classification Tasks for Transformer Encoder Models","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ... International Florida Artificial Intelligence Research Society Conference","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Encoder; Transformer; Computer science; Artificial intelligence; Sequence (biology); Sequence learning; Speech recognition; Pattern recognition (psychology); Engineering; Electrical engineering; Biology; Voltage","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":[0.00208555,0.0001629576,0.0001608576,0.00009303696,0.0004746091,0.0009678479,0.002452902,0.00008772501,0.00001767136],"category_scores_gemma":[0.0002625549,0.00009757494,0.0004181863,0.0009372841,0.0004457025,0.001237554,0.0001917477,0.0007461051,0.000006441869],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002099006,"about_ca_system_score_gemma":0.0003939722,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001060958,"about_ca_topic_score_gemma":0.000002672721,"domain_scores_codex":[0.9976094,0.00003188832,0.0004933538,0.0004787107,0.001015567,0.0003710139],"domain_scores_gemma":[0.9967507,0.000954045,0.0001687793,0.0002180656,0.001846607,0.00006187438],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001389988,0.00005166067,0.00003785261,0.0000547225,0.00007143321,6.782889e-8,0.002210837,0.01102598,0.1306832,0.8116741,0.0008370632,0.04333926],"study_design_scores_gemma":[0.00001323113,0.00008213828,0.00005802335,0.0001818878,0.000005376303,0.000001829806,0.001222176,0.7430351,0.06830662,0.1867673,0.0002478466,0.00007853064],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1620198,0.0001406825,0.8076555,0.01907271,0.0006578078,0.001358357,0.00003923637,0.000125086,0.008930911],"genre_scores_gemma":[0.9966999,0.000266736,0.002390859,0.0000297281,0.0002240423,0.0001752175,0.000003426202,0.00001357556,0.0001965254],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8346801,"threshold_uncertainty_score":0.933298,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.374587593761272,"score_gpt":0.4799399593753982,"score_spread":0.1053523656141263,"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."}}