{"id":"W4281652650","doi":"10.2196/38052","title":"Exploiting Intersentence Information for Better Question-Driven Abstractive Summarization: Algorithm Development and Validation","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Science Foundation of Liaoning Province; National Natural Science Foundation of China","keywords":"Computer science; Automatic summarization; Development (topology); Artificial intelligence; Algorithm; Natural language processing; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005548059,0.00009661329,0.0001059898,0.000127665,0.000309712,0.0001504496,0.0003529575,0.00005123249,0.00002374261],"category_scores_gemma":[0.00009515205,0.0000969644,0.00002240517,0.0001502087,0.0000261562,0.002232827,0.0004129237,0.0002100824,0.000008969786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001235155,"about_ca_system_score_gemma":0.0001605626,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003636019,"about_ca_topic_score_gemma":6.341836e-7,"domain_scores_codex":[0.9984348,0.00002943132,0.0006011976,0.00008886187,0.000667191,0.0001784645],"domain_scores_gemma":[0.9992609,0.0001112923,0.000250937,0.0001518635,0.0001167864,0.0001082204],"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":[0.000003720183,0.00002651163,0.0002009923,0.00008801178,0.00001528098,0.00000127881,0.02920446,0.0007664108,0.000002642272,0.01066736,0.0004470682,0.9585763],"study_design_scores_gemma":[0.0003901889,0.00004020054,0.0001652194,0.0000437869,0.000002712668,0.00002604717,0.003524966,0.9768078,0.000197063,0.000658064,0.01800565,0.0001383208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02988842,0.000003289006,0.9682391,0.0008481771,0.0002836423,0.0003616358,0.000005309442,0.00009652036,0.0002738996],"genre_scores_gemma":[0.1352249,0.000004569576,0.8614085,0.002509859,0.00008352953,0.0005538499,0.0001874101,0.000006012838,0.00002144126],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9760414,"threshold_uncertainty_score":0.3954093,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02004162927015088,"score_gpt":0.2743435395010483,"score_spread":0.2543019102308974,"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."}}