{"id":"W2890419630","doi":"10.18653/v1/d18-1409","title":"BanditSum: Extractive Summarization as a Contextual Bandit","year":2018,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":176,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Automatic summarization; Computer science; Artificial intelligence; Reinforcement learning; Context (archaeology); Sequence (biology); Natural language processing; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001360837,0.00007628155,0.00007671535,0.00005478082,0.0001031639,0.0001147404,0.000366936,0.0000475112,0.0002715454],"category_scores_gemma":[0.00006012142,0.00006620225,0.00002485922,0.0001443838,0.00003870966,0.000563835,0.0001173047,0.00006105153,0.0006320475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002791615,"about_ca_system_score_gemma":0.00005740039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001193729,"about_ca_topic_score_gemma":0.00005233387,"domain_scores_codex":[0.9992118,0.00002963755,0.0001284941,0.0002816046,0.0001795479,0.0001688973],"domain_scores_gemma":[0.9993909,0.0000572757,0.00004208949,0.0003329895,0.0001144783,0.00006226132],"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":[0.00001195996,0.00006227688,0.0008801062,0.000003723061,0.0000238346,0.00001290372,0.002641732,0.00003967722,0.002157411,0.8558768,0.004576434,0.1337132],"study_design_scores_gemma":[0.001447502,0.0004868452,0.005418157,0.00004113064,0.00001390439,0.00007370745,0.0002806799,0.8353384,0.03515557,0.05542559,0.06562328,0.0006952841],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01337843,0.00001277834,0.8869017,0.0005023055,0.0004057821,0.0000848907,4.034524e-7,0.0001659338,0.09854776],"genre_scores_gemma":[0.9715726,0.000002313731,0.02296729,0.0007104105,0.0002699867,0.000005296334,0.000001523938,0.000004578012,0.004465996],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9581942,"threshold_uncertainty_score":0.8123903,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0206302257562439,"score_gpt":0.2686749282276282,"score_spread":0.2480447024713843,"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."}}