{"id":"W4392811535","doi":"10.1111/cogs.13416","title":"Probing the Representational Structure of Regular Polysemy via Sense Analogy Questions: Insights from Contextual Word Vectors","year":2024,"lang":"en","type":"article","venue":"Cognitive Science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Polysemy; Analogy; Computer science; Natural language processing; Linguistics; Artificial intelligence; Mathematics; Cognitive psychology; Psychology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000251983,0.0001539166,0.0001838672,0.0003839706,0.0003196214,0.0002302111,0.0008289775,0.00004774314,0.0000225716],"category_scores_gemma":[0.000526916,0.0001074175,0.00008119555,0.002745847,0.001463207,0.001275474,0.0003723782,0.0002299381,0.00001233925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007315879,"about_ca_system_score_gemma":0.0002627782,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001170703,"about_ca_topic_score_gemma":0.00006248034,"domain_scores_codex":[0.9979299,0.0001541099,0.0002965669,0.0007484376,0.0006359804,0.0002349514],"domain_scores_gemma":[0.9980817,0.000715394,0.0001343466,0.0004588067,0.0005347314,0.0000750269],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001618859,0.00004842358,0.0004574575,0.00001444238,0.0001140357,0.00009698179,0.006935617,0.0002420075,0.66738,0.1902321,0.0001233088,0.1343394],"study_design_scores_gemma":[0.0001832397,0.00008820384,0.01765554,0.0003577085,0.00007501406,0.00006215325,0.000589502,0.117358,0.4855628,0.3774855,0.0002134523,0.0003688892],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2390116,0.0009088957,0.7589718,0.0002534804,0.0002023343,0.0002127779,0.0000199145,0.000179783,0.0002394743],"genre_scores_gemma":[0.9815705,0.00001149497,0.01812614,0.0001531754,0.00006784641,0.00001276877,0.000009090046,0.000007184668,0.00004175456],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.742559,"threshold_uncertainty_score":0.5391248,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01417811215482184,"score_gpt":0.305005640284556,"score_spread":0.2908275281297341,"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."}}