{"id":"W6998800864","doi":"","title":"Automatic annotation of the Penn-treebank with LFG f-structure\\ninformation","year":2002,"lang":"en","type":"other","venue":"Arrow@dit (Dublin Institute of Technology)","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Advanced Research Projects Agency; Atomic Energy of Canada Limited; University of Oxford; Enterprise Ireland; University of Pennsylvania","keywords":"Treebank; Annotation; Unification; Grammar; Information extraction; Section (typography); Training set","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002325292,0.0007545182,0.001052772,0.003265113,0.0001415963,0.00003887561,0.001919238,0.001537755,0.001697616],"category_scores_gemma":[0.0004385142,0.0005366051,0.0002083324,0.00353706,0.002186901,0.0006932843,0.0002767246,0.0009067289,0.0005241432],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002132239,"about_ca_system_score_gemma":0.0002955748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001798178,"about_ca_topic_score_gemma":0.0009971512,"domain_scores_codex":[0.9966221,0.00004950269,0.001190882,0.0005685645,0.001039127,0.0005297677],"domain_scores_gemma":[0.9937665,0.00002375535,0.003479143,0.002288533,0.0003775232,0.00006456097],"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":[0.000093986,0.0004567732,0.001791481,0.002529376,0.001229701,0.00003165582,0.0005774291,0.001548661,0.007335658,0.04871636,0.8921736,0.04351531],"study_design_scores_gemma":[0.004094904,0.0004243868,0.001088614,0.004205834,0.0007939399,0.0002703533,0.000244692,0.004703411,0.02469696,0.002277398,0.9557654,0.001434114],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2981562,0.002272154,0.001155327,0.002981696,0.005610848,0.008621533,0.003968941,0.008552321,0.668681],"genre_scores_gemma":[0.8926701,0.0001243782,0.03773247,0.00009842317,0.0002800924,0.000231034,0.0007318298,0.001458595,0.06667306],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6020079,"threshold_uncertainty_score":0.9997585,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007757778029271146,"score_gpt":0.2110921206627654,"score_spread":0.2033343426334943,"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."}}