{"id":"W3031557112","doi":"10.18653/v1/2020.coling-main.6","title":"Catching Attention with Automatic Pull Quote Selection","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Automatic summarization; Task (project management); Readability; Computer science; Selection (genetic algorithm); Identification (biology); Presentation (obstetrics); Salient; Code (set theory); Natural language processing; Artificial intelligence; Perception; Cognitive psychology; Psychology","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":[0.0001647549,0.0002653179,0.0003282118,0.0001983486,0.0001003007,0.0004126228,0.0009036463,0.0001404288,0.00001167705],"category_scores_gemma":[0.00002084073,0.0002212526,0.0001097565,0.0005024397,0.00002014687,0.0004636374,0.000909248,0.0005716115,0.00004028376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001713307,"about_ca_system_score_gemma":0.0001164464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002757839,"about_ca_topic_score_gemma":0.00007794124,"domain_scores_codex":[0.9982206,0.0000766962,0.0002993558,0.000787373,0.0003996584,0.0002163379],"domain_scores_gemma":[0.9988173,0.00002909683,0.0003035376,0.0006323852,0.0001356042,0.00008203638],"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":[0.00002931633,0.0005188644,0.008362736,0.001462227,0.001596031,0.0001660987,0.002568607,0.09989937,0.01908473,0.3398324,0.009321565,0.517158],"study_design_scores_gemma":[0.00006518442,0.00005969971,0.001378305,0.00009701581,0.0000493977,0.00001470086,0.000009519084,0.9679745,0.001088628,0.02865039,0.000269586,0.0003430831],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005390755,0.0000323248,0.9882946,0.001329423,0.0001020655,0.0003199071,5.649859e-7,0.003011937,0.001518436],"genre_scores_gemma":[0.4529293,0.00001105272,0.5464734,0.0001251096,0.00005106773,0.00005760292,0.00001336602,0.00001660641,0.0003224178],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8680751,"threshold_uncertainty_score":0.9022421,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01647314170779892,"score_gpt":0.2747997570315964,"score_spread":0.2583266153237975,"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."}}