{"id":"W2573346038","doi":"","title":"Predicting sentential semantic compatibility for aggregation in text-to-text generation","year":2016,"lang":"en","type":"article","venue":"International Conference on Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Sentence; Natural language processing; Artificial intelligence; Task (project management); Cluster analysis; Process (computing); Context (archaeology); Information retrieval","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":[0.0004128842,0.0001672073,0.0001639186,0.0002739658,0.0001020978,0.0001870358,0.000594028,0.00006484918,0.00003020112],"category_scores_gemma":[0.002323562,0.0001493234,0.00005975924,0.0001473531,0.00003164546,0.0001366285,0.0001303178,0.00009738513,0.00004997393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002366887,"about_ca_system_score_gemma":0.0001890139,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004430134,"about_ca_topic_score_gemma":0.0001086204,"domain_scores_codex":[0.9979912,0.00006451212,0.0005554918,0.0005788722,0.0005854228,0.0002244895],"domain_scores_gemma":[0.9975317,0.0004837943,0.0001811113,0.0002402074,0.001472809,0.00009044122],"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":[0.00003778527,0.0001173622,0.007682639,0.00001088765,0.00002035797,0.000004482955,0.0002330678,0.06653775,0.0005920973,0.8960314,0.0001585348,0.02857368],"study_design_scores_gemma":[0.000677692,0.0000795795,0.005149633,0.0001400714,0.000003272348,0.000002681025,0.00001007325,0.9368224,0.0003441961,0.0560502,0.0005494456,0.0001707553],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0830668,0.00000328529,0.9096187,0.002924894,0.002467597,0.0003581633,0.00005361512,0.00008403627,0.001422943],"genre_scores_gemma":[0.9130513,0.000002395051,0.08542663,0.000362361,0.0009240219,0.00004281515,0.00006006867,0.00001044376,0.00011997],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8702847,"threshold_uncertainty_score":0.608923,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07688502906661919,"score_gpt":0.3287613563504564,"score_spread":0.2518763272838372,"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."}}