{"id":"W4393090174","doi":"10.1007/978-3-031-56069-9_20","title":"eval-rationales: An End-to-End Toolkit to Explain and Evaluate Transformers-Based Models","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Fonds de Recherche du Québec - Santé","keywords":"Interpretability; Computer science; Transformer; Artificial intelligence; End-to-end principle; Machine learning; Data science; Software engineering; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00423993,0.003082909,0.001161534,0.002924655,0.0009240527,0.007432473,0.004673728,0.00277371,0.0767362],"category_scores_gemma":[0.01487173,0.002370308,0.003633414,0.001277037,0.001348918,0.008004232,0.005899516,0.004519934,0.02175847],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001416246,"about_ca_system_score_gemma":0.002007914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002295754,"about_ca_topic_score_gemma":0.006153902,"domain_scores_codex":[0.9975294,0.0008517747,0.0002450698,0.0003033417,0.0009122057,0.0001581785],"domain_scores_gemma":[0.9928758,0.004865792,0.0002111328,0.001282541,0.0006101458,0.0001545361],"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":[0.0005513139,0.0004593396,0.001934452,0.002460401,0.0003485535,0.001044182,0.001542314,0.03706722,0.006538526,0.3676246,0.1870292,0.3933998],"study_design_scores_gemma":[0.0003091649,0.00009824424,0.0004143316,0.0007370406,0.0001389254,0.0007262715,0.0003661279,0.2489309,0.01747904,0.3111568,0.4194798,0.0001633258],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001272664,0.0001687671,0.8811454,0.000284172,0.0001073344,0.0002633352,0.003652135,0.1016696,0.01143659],"genre_scores_gemma":[0.03029707,0.0006116008,0.8986791,0.0003389034,0.00005280502,0.0005685012,0.01492661,0.03850737,0.01601794],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0767362,"threshold_uncertainty_score":0.2567081,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04916689337903857,"score_gpt":0.3026271434946071,"score_spread":0.2534602501155685,"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."}}