{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00128764,0.0004460723,0.0008102387,0.001233702,0.0004644983,0.001394438,0.001153805,0.001105898,0.003805407],"category_scores_gemma":[0.007625193,0.0002744513,0.0006174754,0.001276972,0.000664059,0.00150704,0.001211419,0.001399052,0.001187182],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007174169,"about_ca_system_score_gemma":0.0007775779,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0016905,"about_ca_topic_score_gemma":0.002140698,"domain_scores_codex":[0.9992017,0.0001908861,0.00006545678,0.0002445588,0.0001945266,0.0001028274],"domain_scores_gemma":[0.997758,0.001046938,0.0001614709,0.0003655631,0.000589942,0.0000780686],"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":[0.0002231661,0.0001535644,0.002016173,0.0001559528,0.00004699489,0.00008842082,0.0001820422,0.06287614,0.03358944,0.02403444,0.005427718,0.871206],"study_design_scores_gemma":[0.00001722442,0.0000744955,0.001217687,0.00003562511,0.00002106744,0.0001224918,0.00005736847,0.9609759,0.01220306,0.02356707,0.0016939,0.00001400132],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0447121,0.0002242012,0.9516436,0.0002940247,0.0001035706,0.00006305306,0.0002028798,0.001113723,0.001642908],"genre_scores_gemma":[0.4559982,0.0001909381,0.5368401,0.0001834189,0.0000807782,0.0001912563,0.001185399,0.0004863229,0.004843617],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003805407,"threshold_uncertainty_score":0.0127303,"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."}}