{"id":"W4412889013","doi":"10.18653/v1/2025.conll-1.37","title":"Spatial relation marking across languages: extraction, evaluation, analysis","year":2025,"lang":"en","type":"article","venue":"","topic":"Categorization, perception, and language","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Relation (database); Relationship extraction; Spatial relation; Artificial intelligence; Extraction (chemistry); Natural language processing; Data mining","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009360884,0.000136077,0.0001801335,0.000365017,0.0002780829,0.00008291349,0.0001171608,0.0001700567,0.03558946],"category_scores_gemma":[0.000122209,0.0001334687,0.0001501964,0.001469118,0.00004015967,0.0001735646,0.00002121424,0.0001239728,0.0003276461],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001361949,"about_ca_system_score_gemma":0.00005337549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00489937,"about_ca_topic_score_gemma":0.008939781,"domain_scores_codex":[0.9984652,0.0002327927,0.0003793521,0.0004023222,0.000284753,0.0002355428],"domain_scores_gemma":[0.9989769,0.0001065563,0.0001183659,0.0004505372,0.0003064848,0.00004119369],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001221555,0.0003115401,0.7745194,0.00002119705,0.001755308,0.000007121753,0.02931879,0.001485461,0.001296784,0.02321956,0.01565502,0.1522876],"study_design_scores_gemma":[0.0006083775,0.00001120654,0.9772704,0.000004910284,0.0006786446,0.000002781204,0.009153617,0.003940346,0.00005317346,0.0004031024,0.007724458,0.0001490351],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4762479,0.0003891492,0.305376,0.0003072007,0.001046482,0.0003685967,0.00001399081,0.0002308088,0.2160199],"genre_scores_gemma":[0.953926,0.00001194941,0.0001948984,0.0002951846,0.0002474773,0.00006596219,0.0005211893,0.00001181821,0.04472555],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4776781,"threshold_uncertainty_score":0.9652922,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01969847816972198,"score_gpt":0.4196993493624682,"score_spread":0.4000008711927462,"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."}}