{"id":"W1921587136","doi":"10.1007/s10579-015-9318-3","title":"Cross level semantic similarity: an evaluation framework for universal measures of similarity","year":2015,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Topic Modeling","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"European Research Council","keywords":"Computer science; Natural language processing; Similarity (geometry); Semantic similarity; Sentence; Task (project management); Artificial intelligence; Word (group theory); SemEval; Paragraph; Process (computing); Meaning (existential); WordNet; Information retrieval; Linguistics; Psychology; World Wide Web","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":[0.004648539,0.0001042185,0.0001542748,0.00008391269,0.0001071765,0.0001384583,0.0002821788,0.0001186903,0.00001235267],"category_scores_gemma":[0.0008957342,0.00009853405,0.00003913455,0.0001473496,0.00004085109,0.0004287245,0.00008647648,0.00009024714,8.018935e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000732385,"about_ca_system_score_gemma":0.0001334979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002787231,"about_ca_topic_score_gemma":0.0001448171,"domain_scores_codex":[0.9980518,0.0003017166,0.0002203564,0.0003327066,0.0009269362,0.0001665484],"domain_scores_gemma":[0.998542,0.000135312,0.0001438689,0.0004233865,0.000657859,0.0000975883],"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":[0.0001224733,0.000149998,0.009041608,0.0001339356,0.00006718814,0.00000247694,0.08972238,0.06784435,0.001173257,0.01453962,0.00006871789,0.817134],"study_design_scores_gemma":[0.0008422256,0.0001118307,0.006954814,0.00003536484,0.00006432435,0.000002450622,0.001686854,0.9661856,0.0006086114,0.02324813,0.0001403904,0.0001194535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5476088,0.0005781897,0.4510719,0.0001913152,0.00009610457,0.0003173305,0.000006149855,0.00002857829,0.0001016167],"genre_scores_gemma":[0.9372215,0.000004252731,0.06250168,0.00007262365,0.0001337953,0.00001815306,0.00001891267,0.000007355911,0.00002169596],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8983412,"threshold_uncertainty_score":0.4018102,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.212328201095616,"score_gpt":0.3869887300338786,"score_spread":0.1746605289382627,"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."}}