{"id":"W2626975399","doi":"","title":"Narrative generation from extracted associations","year":2015,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Natural language processing; Exploit; Natural language generation; Rhetorical question; Interpretation (philosophy); Artificial intelligence; Causality (physics); Coherence (philosophical gambling strategy); Association rule learning; Pipeline (software); Natural language; Linguistics; Mathematics; Programming language; Statistics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.000113917,0.00004643088,0.00005107405,0.00002037511,0.00009458586,0.0001647192,0.0002820371,0.00002828511,0.00002178967],"category_scores_gemma":[0.00005400058,0.00004165158,0.00001324775,0.0001981371,0.000007811779,0.0005263453,0.00006202671,0.00004376015,0.0001539087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003692607,"about_ca_system_score_gemma":0.00006825066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003716904,"about_ca_topic_score_gemma":0.00009051827,"domain_scores_codex":[0.9994799,0.00002402715,0.0001013337,0.000178135,0.0001382338,0.00007836426],"domain_scores_gemma":[0.9994519,0.00003139911,0.00004602355,0.0002754613,0.000119737,0.00007552996],"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":[5.327331e-7,0.0001913091,0.0005231994,1.643651e-7,0.00003865392,0.00000221615,0.02000951,0.0001101901,0.005789675,0.4718264,0.4082599,0.09324822],"study_design_scores_gemma":[0.0004252503,0.0000419175,0.0126607,0.000002121958,0.000007160947,0.000001565469,0.0008852766,0.9092,0.003758436,0.01343501,0.05932872,0.000253871],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0279722,0.00001846954,0.9624695,0.00308526,0.000190321,0.00006067608,0.00003133519,0.0001852207,0.005987056],"genre_scores_gemma":[0.2922032,0.000001509654,0.7047226,0.0004332643,0.0002489522,0.00003342599,0.0003768049,0.000004058998,0.001976105],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9090898,"threshold_uncertainty_score":0.1978236,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09738704675361089,"score_gpt":0.3013592775135804,"score_spread":0.2039722307599696,"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."}}