{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002511792,0.00118927,0.0008819347,0.00120723,0.0005319339,0.002292209,0.001164131,0.0014822,0.006869742],"category_scores_gemma":[0.01701849,0.0003983997,0.0006428653,0.000707036,0.000552177,0.004322073,0.002615645,0.001480404,0.005639857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003745285,"about_ca_system_score_gemma":0.0005443502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006197959,"about_ca_topic_score_gemma":0.001168864,"domain_scores_codex":[0.9974425,0.001092947,0.0001178377,0.000623095,0.0005327737,0.0001908261],"domain_scores_gemma":[0.9915719,0.004986531,0.0007753114,0.001010891,0.001196326,0.0004590148],"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":[0.002169111,0.0005867613,0.01069531,0.00104605,0.0001570082,0.0005901593,0.003194107,0.0113215,0.1445712,0.006462157,0.01762133,0.8015853],"study_design_scores_gemma":[0.0002603862,0.001800781,0.02780293,0.0002754321,0.0001874232,0.001233002,0.002783156,0.7148579,0.1425952,0.06570753,0.04223468,0.0002616022],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2246394,0.001532154,0.7404196,0.001256158,0.0004418492,0.0004598958,0.0007586914,0.01678775,0.01370446],"genre_scores_gemma":[0.820718,0.0003370387,0.1623627,0.0003881823,0.0003035818,0.0003301892,0.001238039,0.0008201174,0.01350208],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006869742,"threshold_uncertainty_score":0.02298152,"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."}}