{"id":"W4413910953","doi":"10.1038/s41597-025-05445-3","title":"The Indo-European Cognate Relationships dataset","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Language and cultural evolution","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Lexeme; Cognate; Metadata; Computer science; Benchmark (surveying); Lexicon; Language family; Natural language processing; Interoperability; Linguistics; Artificial intelligence; Information retrieval; World Wide Web; Geography; Cartography","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.005107426,0.00004186097,0.00003482771,0.00002991682,0.004490871,0.0008331605,0.001619631,0.00002198024,0.0001171336],"category_scores_gemma":[0.001642206,0.00002640832,0.00001173476,0.0006187275,0.0005852276,0.0005341406,0.0005291944,0.0001239484,0.0006720495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002744362,"about_ca_system_score_gemma":0.0001365981,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003486144,"about_ca_topic_score_gemma":0.007513945,"domain_scores_codex":[0.9986374,0.0004869459,0.0001182922,0.0002995043,0.0002639114,0.0001939459],"domain_scores_gemma":[0.9986113,0.0001378277,0.00004137331,0.001109205,0.00005636965,0.00004397099],"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":[0.000001552833,0.000006927021,0.0001390775,0.000001123958,0.000004841295,0.000001346082,0.001011706,3.954102e-7,0.00004618296,0.02264076,0.9594862,0.01665987],"study_design_scores_gemma":[0.00005348981,8.299506e-7,0.002301374,0.000009388202,0.00001050859,1.430221e-7,0.004368301,0.00004846644,0.000008110883,0.001497551,0.9916624,0.00003947418],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.01409693,0.003846866,0.0007692762,0.0335922,0.01210073,0.001010309,0.03221161,0.0003741948,0.9019979],"genre_scores_gemma":[0.8048254,0.00009860945,0.0001936785,0.0004099616,0.0002829655,0.000005797347,0.05046454,0.000006275932,0.1437127],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.7907285,"threshold_uncertainty_score":0.9968051,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1068008655528147,"score_gpt":0.3751298188663035,"score_spread":0.2683289533134888,"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."}}