{"id":"W4404579539","doi":"10.1101/2024.11.20.624526","title":"SIGNAL: Dataset for Semantic and Inferred Grammar Neurological Analysis of Language","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology; Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Grammar; Computer science; Natural language processing; Linguistics; Semantic analysis (machine learning); SIGNAL (programming language); Artificial intelligence; Psychology; Philosophy; Programming language","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":[0.000876486,0.002630737,0.001131313,0.002698027,0.000733713,0.001142578,0.001941318,0.002437573,0.008687424],"category_scores_gemma":[0.003839212,0.0002658442,0.001240736,0.002047288,0.0005001046,0.0008167077,0.001483761,0.001214027,0.01479118],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005968072,"about_ca_system_score_gemma":0.000925648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004480155,"about_ca_topic_score_gemma":0.008958909,"domain_scores_codex":[0.9990205,0.0001649461,0.0001611202,0.0002989221,0.0002463706,0.000108098],"domain_scores_gemma":[0.998418,0.0004198142,0.0001781932,0.0004305126,0.0003979338,0.000155577],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001624602,0.0006815912,0.01226706,0.003766487,0.0004386553,0.001804292,0.0004419003,0.002784882,0.02860201,0.001324453,0.8767866,0.0694775],"study_design_scores_gemma":[0.001592065,0.000910877,0.127045,0.0005463151,0.0004906515,0.005545221,0.00102317,0.02026329,0.02533579,0.007487198,0.8093582,0.0004021935],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.02765683,0.000998814,0.0032147,0.0003727664,0.0002244454,0.0002946374,0.960417,0.004069897,0.002750877],"genre_scores_gemma":[0.01384503,0.0001324546,0.003674539,0.0000710817,0.00005361349,0.0004405073,0.9806788,0.0001232509,0.000980667],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.008687424,"threshold_uncertainty_score":0.02906239,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02677932533337592,"score_gpt":0.2768971367176807,"score_spread":0.2501178113843048,"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."}}