{"id":"W1554237613","doi":"","title":"Identifying synonyms among distributionally similar words","year":2003,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":208,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing","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":[0.0003072942,0.00008611588,0.00008368709,0.00004120052,0.0001121648,0.0001786104,0.000479849,0.00004084048,0.0001288136],"category_scores_gemma":[0.00007582796,0.00007948543,0.00005023459,0.0002149673,0.00002164986,0.0004753781,0.0001148021,0.00009142038,0.00006797715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004430194,"about_ca_system_score_gemma":0.00004865066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001749749,"about_ca_topic_score_gemma":0.00001420492,"domain_scores_codex":[0.9989946,0.00004140634,0.0001710809,0.0002967042,0.0002594656,0.0002366783],"domain_scores_gemma":[0.9993672,0.00004198793,0.00003589721,0.0004282795,0.00004662395,0.00007995825],"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":[3.546989e-7,0.00002057114,0.01038672,0.000005354691,0.000009217323,0.00001499813,0.0001301983,0.0005588724,0.0001361695,0.9853601,0.0004960716,0.002881351],"study_design_scores_gemma":[0.001171454,0.00007898588,0.06725685,0.000119764,0.00002386781,0.00009918126,0.0002942946,0.6045823,0.01281079,0.2768161,0.03525124,0.001495239],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03621425,0.00005129517,0.9429518,0.0002530784,0.0003432797,0.00005716608,6.541662e-7,0.0001704088,0.01995805],"genre_scores_gemma":[0.8857433,0.000002871321,0.1128131,0.0001801754,0.00002702019,0.000005530327,0.000001396455,0.000003778144,0.001222905],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.849529,"threshold_uncertainty_score":0.3241322,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02478478907119317,"score_gpt":0.2520004980326496,"score_spread":0.2272157089614564,"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."}}