{"id":"W6894028799","doi":"10.5281/zenodo.8100419","title":"Evaluating the meaning of answers to reading comprehension questions: A semantics-based approach","year":2012,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Meaning (existential); Reading comprehension; Comprehension; Reading (process); Association (psychology)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00217547,0.00009071231,0.0001064057,0.0001535605,0.001408337,0.0003441538,0.001136461,0.00003529137,0.000125682],"category_scores_gemma":[0.0009317704,0.00007678676,0.0000390292,0.0007638433,0.00008455628,0.0003773442,0.0006499615,0.000154465,0.0003889853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009181663,"about_ca_system_score_gemma":0.000005653827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001801066,"about_ca_topic_score_gemma":7.733981e-8,"domain_scores_codex":[0.998202,0.000574483,0.0002450915,0.0002730615,0.0004273872,0.0002779997],"domain_scores_gemma":[0.9985083,0.00009623637,0.0001142522,0.0006912804,0.0004666466,0.0001232213],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008719046,0.0006573939,0.0001051783,0.0002430814,0.00004892962,8.419114e-7,0.02518422,0.01939541,0.1238694,0.3067866,0.008626724,0.514995],"study_design_scores_gemma":[0.000946512,0.001054161,0.0101124,0.0002416275,0.00005548168,0.0001232772,0.002197671,0.6330298,0.01117531,0.001656172,0.3387459,0.0006616662],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06014143,0.00005161319,0.9263477,0.001546031,0.00009442326,0.0006027006,0.00001174443,0.0005219018,0.01068247],"genre_scores_gemma":[0.962882,0.000002726317,0.03664302,0.0001469473,0.0000470765,1.002862e-7,0.00007650679,0.0001649162,0.00003667728],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9027406,"threshold_uncertainty_score":0.9998917,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1167098047272723,"score_gpt":0.3276732036295565,"score_spread":0.2109633989022842,"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."}}