{"id":"W4402670845","doi":"10.18653/v1/2024.findings-acl.115","title":"A Graph per Persona: Reasoning about Subjective Natural Language Descriptions","year":2024,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency; Canadian Institute for Advanced Research","keywords":"Persona; Computer science; Natural language processing; Natural language; Artificial intelligence; Graph; Natural (archaeology); Programming language; Theoretical computer science; Human–computer interaction; History","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002560812,0.000956972,0.0005620364,0.002145564,0.0009374316,0.002462178,0.001855154,0.001652621,0.00406277],"category_scores_gemma":[0.01475793,0.0006199087,0.001919131,0.001351164,0.001569033,0.008154852,0.001652703,0.002761501,0.0009876753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001337699,"about_ca_system_score_gemma":0.001134138,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01094857,"about_ca_topic_score_gemma":0.01641652,"domain_scores_codex":[0.9981712,0.0008729003,0.00008746473,0.0004942075,0.0003098564,0.00006439049],"domain_scores_gemma":[0.9933317,0.004253893,0.0006130951,0.0009485964,0.0005790558,0.0002735558],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003452573,0.0002255827,0.008240019,0.0005781797,0.0004321983,0.0008104919,0.002337113,0.1832279,0.00626627,0.4954758,0.02688558,0.2751756],"study_design_scores_gemma":[0.00001300992,0.00002677054,0.0005679684,0.00004325755,0.00005416536,0.0001312272,0.0001708756,0.6824816,0.001105812,0.3085593,0.006816573,0.0000292993],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01748118,0.0002657164,0.9745394,0.002474231,0.00006808255,0.0001087774,0.001020974,0.001174775,0.002866917],"genre_scores_gemma":[0.4677956,0.0005455353,0.5227457,0.0009451181,0.0001537107,0.0002024324,0.002761304,0.0002903753,0.004560336],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01094857,"threshold_uncertainty_score":0.0217697,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007859001521344656,"score_gpt":0.268956318106387,"score_spread":0.2610973165850424,"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."}}