{"id":"W4417112536","doi":"10.21203/rs.3.rs-7724663/v1","title":"Evolutionary Feature-wise Thresholding for Binary Representation of NLP Embeddings","year":2025,"lang":"","type":"preprint","venue":"Research Square","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Wilfrid Laurier University; Brock University","funders":"","keywords":"Binary number; Thresholding; Representation (politics); Embedding; Pattern recognition (psychology); Range (aeronautics); Key (lock)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003281786,0.0005877143,0.0009411961,0.003011714,0.001159449,0.0006310852,0.004688184,0.00114624,0.0001102021],"category_scores_gemma":[0.003632209,0.0006156103,0.0007323139,0.004402963,0.001051628,0.00108389,0.007349877,0.002205446,0.00004092685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008874981,"about_ca_system_score_gemma":0.001860443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001600479,"about_ca_topic_score_gemma":0.000006603255,"domain_scores_codex":[0.9916399,0.0006838011,0.001213839,0.002419463,0.002685082,0.001357878],"domain_scores_gemma":[0.9885889,0.002900699,0.0007538032,0.003645057,0.003893103,0.000218409],"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":[0.0008295212,0.001396178,0.01040483,0.009996279,0.0004547568,0.00002948636,0.003771838,0.003999742,0.009473475,0.5648356,0.2284452,0.1663631],"study_design_scores_gemma":[0.003039055,0.002197815,0.04150111,0.01006203,0.0001442242,0.00001427643,0.009149541,0.4252201,0.06724725,0.358315,0.08117059,0.001939002],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07031175,0.03648536,0.7130135,0.1084556,0.00733487,0.03201421,0.00240833,0.003239521,0.02673689],"genre_scores_gemma":[0.9063473,0.004884029,0.06342399,0.00004993433,0.0003157286,0.002690008,0.0004172552,0.00005180925,0.02181993],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8360355,"threshold_uncertainty_score":0.9996295,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1112056394478961,"score_gpt":0.4393729790355389,"score_spread":0.3281673395876428,"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."}}