{"id":"W4404534114","doi":"10.1162/coli_a_00545","title":"The Emergence of Chunking Structures with Hierarchical RNN","year":2024,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; University of Waterloo; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Alberta Innovates; University of Alberta; DeepMind; Canadian Institute for Advanced Research","keywords":"Chunking (psychology); Computer science; Natural language processing; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001678004,0.0000788805,0.00009099914,0.0000482155,0.0002174122,0.0001880703,0.0003944099,0.0000188749,0.00001049401],"category_scores_gemma":[0.0003264382,0.00004828427,0.00004875451,0.0003813104,0.0001107454,0.00003016182,0.000114007,0.0001201104,0.000003857863],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007466908,"about_ca_system_score_gemma":0.0001154006,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005723778,"about_ca_topic_score_gemma":0.000003805985,"domain_scores_codex":[0.99912,0.00002115561,0.0002195962,0.0001853782,0.0003176824,0.0001361884],"domain_scores_gemma":[0.9989621,0.0004836874,0.00006028387,0.0001587932,0.0002975742,0.00003758186],"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":[0.000002709276,0.000003861086,0.00008765836,0.00001626134,0.00003531303,0.000009479655,0.0002006968,0.08482827,0.000004001419,0.8986862,0.0003083733,0.01581717],"study_design_scores_gemma":[0.00002706726,0.00003813114,0.0009174006,0.00003175663,0.00001103367,0.000008448487,0.00001831552,0.8261019,0.00002419598,0.159623,0.01313167,0.00006708065],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001396883,0.0007963637,0.9927365,0.0002498869,0.000688829,0.00004097315,0.000005390971,0.00007100234,0.004014161],"genre_scores_gemma":[0.8728279,0.000007605451,0.1267795,0.0000234585,0.0002900488,0.000001187219,0.000005342521,0.000005648674,0.00005925868],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8714311,"threshold_uncertainty_score":0.1968976,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01130154070976787,"score_gpt":0.251264422587314,"score_spread":0.2399628818775461,"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."}}