{"id":"W4415283783","doi":"10.1177/20539517251386055","title":"Cosine capital: Large language models and the embedding of all things","year":2025,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Complex Systems and Time Series Analysis","field":"Economics, Econometrics and Finance","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Koneen Säätiö","keywords":"Commodification; Abstraction; Embedding; sort; Language model; Process (computing); Modeling language; Natural 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008970158,0.0000868361,0.0003450535,0.0000298609,0.0001084758,0.00006702637,0.0003864675,0.00004832894,0.00005833407],"category_scores_gemma":[0.00004147774,0.00007060725,0.0001294335,0.0001905404,0.00008149793,0.000248095,0.0005456334,0.00008169276,0.000007631152],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001905739,"about_ca_system_score_gemma":0.0000104564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003359478,"about_ca_topic_score_gemma":0.0001488596,"domain_scores_codex":[0.9991669,0.00001190228,0.0003603707,0.0002786967,0.00002993014,0.0001522069],"domain_scores_gemma":[0.998979,0.00006917912,0.0001897151,0.0007219458,0.00001867177,0.00002153759],"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":[0.00002104723,0.00007122895,0.001561829,0.0002070501,0.0009367827,8.901234e-7,0.01864686,0.00008823376,0.00003568583,0.9329361,0.04375315,0.001741085],"study_design_scores_gemma":[0.002297704,0.00001299228,0.00124904,0.00006697103,0.0001041397,0.000001852713,0.01126254,0.755327,0.00001495475,0.03343331,0.1959612,0.0002683262],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5763615,0.1574956,0.1999282,0.01086173,0.001032658,0.001219345,0.01070924,0.0001679412,0.04222384],"genre_scores_gemma":[0.9960266,0.0009694349,0.0006827943,0.0006926742,0.0000557433,0.000005104904,0.000188877,0.000008443244,0.001370369],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8995029,"threshold_uncertainty_score":0.5078549,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06613855722414949,"score_gpt":0.2689227084585134,"score_spread":0.2027841512343639,"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."}}