{"id":"W2115230584","doi":"","title":"A Critical Reassessment of Evaluation Baselines for Speech Summarization","year":2008,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Automatic summarization; Computer science; Speech recognition; Speech analytics; Voice activity detection; Natural language processing; Speech processing; Surprise; Speech synthesis; Artificial intelligence; Information retrieval","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":[0.0005172376,0.00004927257,0.00008388695,0.00007452764,0.00005916994,0.00001846028,0.0001100273,0.00003066899,0.0002002511],"category_scores_gemma":[0.0008923948,0.00004270914,0.00004700626,0.0001556345,0.00002549174,0.0002451696,0.00002202798,0.0000162347,0.00001118365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001940057,"about_ca_system_score_gemma":0.0001025636,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001171446,"about_ca_topic_score_gemma":0.000005635201,"domain_scores_codex":[0.9992029,0.0000598426,0.0001824747,0.0001563476,0.0003114915,0.00008695188],"domain_scores_gemma":[0.998723,0.0003541827,0.00003405501,0.000169721,0.0006829477,0.00003609971],"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":[0.00001161721,0.0002365679,0.0006699987,0.00002808866,0.00001165114,0.000003032034,0.00009565261,0.000006299569,0.002221724,0.08293061,0.004921576,0.9088632],"study_design_scores_gemma":[0.0006261655,0.0001290329,0.009475394,0.00002405483,0.00002604843,0.00005619139,0.0000410801,0.8575863,0.1103933,0.01987845,0.001593864,0.0001701261],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007965853,0.00001280568,0.9830353,0.001219636,0.000147901,0.000237613,0.000003245834,0.00005390338,0.007323767],"genre_scores_gemma":[0.5065826,0.000009865508,0.4929655,0.0001847201,0.00003567849,0.00004042139,0.000008471302,0.000002832629,0.0001699692],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9086931,"threshold_uncertainty_score":0.2192609,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08207451475019102,"score_gpt":0.3518459785605035,"score_spread":0.2697714638103125,"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."}}