{"id":"W2076311126","doi":"10.7202/003464ar","title":"ROSS: Semantic Dictionary for Text Understanding and Summarization","year":2002,"lang":"fr","type":"article","venue":"Meta Journal des traducteurs","topic":"Literature, Language, and Rhetoric Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Automatic summarization; Linguistics; Humanities; Philosophy; Computer science; Natural language processing","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0007456304,0.0002209845,0.0003660442,0.0001246335,0.002253503,0.0004219563,0.0001342948,0.0001383834,0.0003436588],"category_scores_gemma":[0.0002435509,0.000176686,0.0002567497,0.0004783663,0.0007478593,0.0007821508,0.00001901379,0.0002722182,0.000007385562],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002603868,"about_ca_system_score_gemma":0.00002648896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005184101,"about_ca_topic_score_gemma":0.00009946903,"domain_scores_codex":[0.9982944,0.0002948628,0.0003465787,0.0002459497,0.0003516979,0.0004665133],"domain_scores_gemma":[0.9990752,0.0003154765,0.0001903022,0.00008274105,0.0001333877,0.0002028607],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001027568,0.0005680021,0.006945542,0.000533213,0.006965536,0.0001565805,0.1261154,0.00009049047,0.0001556017,0.4928894,0.0876364,0.2778411],"study_design_scores_gemma":[0.001287767,0.0003781916,0.002776605,0.0002966423,0.004668457,0.0005763426,0.01387983,0.00110848,0.00002980575,0.1670874,0.8072742,0.000636265],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.01061224,0.9433345,0.02726833,0.0091687,0.006756014,0.0002750302,0.00003929029,0.00003581291,0.002510051],"genre_scores_gemma":[0.4317455,0.5033707,0.002361203,0.000467424,0.004795773,0.00001683432,0.000007517694,0.00005326795,0.05718175],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.7196378,"threshold_uncertainty_score":0.9990454,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1060726652056354,"score_gpt":0.2967473193659344,"score_spread":0.1906746541602991,"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."}}