{"id":"W2949223751","doi":"10.48550/arxiv.1702.03470","title":"Vector Embedding of Wikipedia Concepts and Entities","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Embedding; Word embedding; Natural language processing; Similarity (geometry); Popularity; Artificial intelligence; Analogy; Word (group theory); Task (project management); Deep learning; Information retrieval; Linguistics; Image (mathematics)","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":[0.000149727,0.0001717357,0.0002798558,0.0001254957,0.000122113,0.0001161732,0.001325863,0.0001603604,0.00001226084],"category_scores_gemma":[0.00004430626,0.0002054027,0.00009113352,0.00005824718,0.0001701136,0.0003621943,0.002223451,0.0002574524,0.000006287883],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005012489,"about_ca_system_score_gemma":0.0001209414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001997097,"about_ca_topic_score_gemma":0.00002200647,"domain_scores_codex":[0.9989036,0.00004921745,0.000138561,0.0006469048,0.00007029843,0.0001914346],"domain_scores_gemma":[0.998351,0.00007002581,0.0002884672,0.001107508,0.00009701659,0.00008593663],"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":[0.00001708577,0.00005134451,0.01475636,0.0004661558,0.0001582503,0.0002622254,0.002990972,0.07698958,0.0002260148,0.9007546,0.0002069295,0.003120471],"study_design_scores_gemma":[0.0004200705,0.00003132564,0.002371001,0.0002549622,0.00005580346,0.000004121649,0.0001425983,0.9389392,0.0003817266,0.05660956,0.0003786677,0.0004109277],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5702004,0.0001676507,0.4258834,0.00003864099,0.0006723645,0.0001079731,0.000007635009,0.00007499466,0.00284696],"genre_scores_gemma":[0.9948944,0.0001861418,0.00346856,0.00001426095,0.00007461321,2.624813e-7,0.000001814125,0.000007261582,0.001352725],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8619497,"threshold_uncertainty_score":0.8376079,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08734957569459353,"score_gpt":0.2230107496963628,"score_spread":0.1356611740017692,"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."}}