{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006374283,0.00327153,0.001778868,0.00355092,0.001474242,0.003998307,0.003139514,0.003147001,0.006922767],"category_scores_gemma":[0.01713644,0.0009775087,0.001587434,0.002833885,0.001411521,0.007779579,0.004353457,0.002766378,0.006825277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001670014,"about_ca_system_score_gemma":0.002389706,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02061152,"about_ca_topic_score_gemma":0.02239858,"domain_scores_codex":[0.9953819,0.001392246,0.0003140262,0.001816847,0.0007810103,0.0003140271],"domain_scores_gemma":[0.9900928,0.005652701,0.0003755676,0.001864684,0.001549915,0.0004642237],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.003118127,0.001513209,0.02765924,0.002745775,0.0009721016,0.001046371,0.002151007,0.04479251,0.03683968,0.003263177,0.05463637,0.8212625],"study_design_scores_gemma":[0.0005514638,0.001468598,0.02603631,0.0004159346,0.0008367573,0.001920598,0.004918578,0.8449847,0.07410634,0.008146552,0.03633559,0.000278724],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6818444,0.0107728,0.1851309,0.003492378,0.001405255,0.001700023,0.02403294,0.0681452,0.02347616],"genre_scores_gemma":[0.8060685,0.001898102,0.1309547,0.0007877665,0.0002066617,0.0005769461,0.04814597,0.002296811,0.009064418],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02061152,"threshold_uncertainty_score":0.04098308,"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."}}