{"id":"W2047851837","doi":"10.1017/s1351324901002716","title":"Scalable generation of texts using causal and temporal expansions of sentences","year":2001,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Lethbridge","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Sentence; Artificial intelligence; Natural language processing; Scalability; Kernel (algebra); Process (computing); Theoretical computer science; Information retrieval; Programming language","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":[0.0001323281,0.0001108056,0.000164434,0.0001580325,0.00003493913,0.00003159939,0.0002364906,0.00006181744,0.00000360424],"category_scores_gemma":[0.00009097067,0.00009352991,0.00003091366,0.0003609267,0.00002617633,0.0004432208,0.0001184681,0.0001418322,1.896829e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002393148,"about_ca_system_score_gemma":0.00002437732,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002258936,"about_ca_topic_score_gemma":0.00001516274,"domain_scores_codex":[0.9992613,0.00001463244,0.0002002317,0.00017827,0.0001889795,0.0001566153],"domain_scores_gemma":[0.9995744,0.00003602299,0.0000879374,0.0001875573,0.00007552905,0.00003860261],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000237329,0.00001189098,0.0008075627,0.00005586527,0.000009384128,0.00002856039,0.0007230564,0.0004322385,0.9835241,0.00138454,0.00001445418,0.01300593],"study_design_scores_gemma":[0.0001370465,0.00003125844,0.0003099165,0.0001365092,0.000008285559,0.0001112133,0.00007244504,0.5973214,0.4016088,0.00007400581,0.00002083452,0.000168302],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8167372,0.01572579,0.1670711,0.00003933239,0.0001694818,0.00007918,0.000002089683,0.0001607017,0.00001508898],"genre_scores_gemma":[0.7011808,0.00001342843,0.2987182,0.000009597681,0.00004473744,0.000001158087,0.000002752754,0.000005778634,0.00002363025],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5968891,"threshold_uncertainty_score":0.3814039,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01503705218098906,"score_gpt":0.2628490486382299,"score_spread":0.2478119964572408,"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."}}