{"id":"W4377200570","doi":"10.1007/978-3-031-32883-1_55","title":"Preliminary Performance Assessment on Ask4Summary’s Reading Methods for Summary Generation","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Athabasca University","funders":"","keywords":"Python (programming language); Computer science; Reading (process); Syntax; Mathematics education; Artificial intelligence; World Wide Web; Natural language processing; Programming language; Linguistics; Psychology","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":[0.009082771,0.002332481,0.001773118,0.004205016,0.001258732,0.003753832,0.003823593,0.00241164,0.08518436],"category_scores_gemma":[0.05591201,0.0007804474,0.001775112,0.002611984,0.0004935953,0.004844564,0.003697166,0.002072566,0.03446254],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001457049,"about_ca_system_score_gemma":0.002220005,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01246664,"about_ca_topic_score_gemma":0.01565385,"domain_scores_codex":[0.9909253,0.004394506,0.0008528072,0.001503663,0.001890909,0.0004328402],"domain_scores_gemma":[0.9463535,0.03660332,0.0007416216,0.006974732,0.007968231,0.00135848],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002318188,0.0007188288,0.0032023,0.001013357,0.0003920156,0.0001772423,0.0008154478,0.007251267,0.007712344,0.002538822,0.09796869,0.8758915],"study_design_scores_gemma":[0.002391766,0.001915569,0.01141226,0.0004892268,0.000890512,0.0007747486,0.003486773,0.7315637,0.071358,0.009728986,0.1656692,0.0003192669],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1709755,0.004038863,0.4507289,0.002963213,0.002394173,0.002655556,0.02208151,0.2984904,0.04567185],"genre_scores_gemma":[0.2364604,0.0006738419,0.6637036,0.0008129627,0.0003701969,0.001211638,0.04937153,0.01027976,0.03711614],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.08518436,"threshold_uncertainty_score":0.2849701,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06385710022590928,"score_gpt":0.3447172890229146,"score_spread":0.2808601887970053,"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."}}