{"id":"W2148189517","doi":"10.1111/j.1365-2729.2008.00290.x","title":"Peering into large lectures: examining peer and expert mark agreement using peerScholar, an online peer assessment tool","year":2008,"lang":"en","type":"article","venue":"Journal of Computer Assisted Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":114,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"","keywords":"Peer assessment; Peering; Class (philosophy); Computer science; Accountability; Class size; Peer evaluation; Rank (graph theory); Peer feedback; Mathematics education; Online assessment; World Wide Web; Multimedia; Higher education; The Internet; Psychology; Artificial intelligence; Formative assessment; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.003487561,0.0002630577,0.0004797551,0.0003134316,0.001547417,0.0004896019,0.0004042166,0.0001508458,0.0001959985],"category_scores_gemma":[0.0002572032,0.0002443668,0.0001462094,0.0003158753,0.000116081,0.001090377,0.0001988812,0.001039869,0.000002033338],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003926846,"about_ca_system_score_gemma":0.0003218343,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001254003,"about_ca_topic_score_gemma":0.00005878198,"domain_scores_codex":[0.9954913,0.0007052255,0.0006921841,0.0003058628,0.002289351,0.0005160747],"domain_scores_gemma":[0.9976903,0.0002415302,0.000611992,0.000151911,0.001031623,0.000272602],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001446852,0.001023064,0.7131329,0.00004812596,0.0006550683,0.000651986,0.1885707,0.006100516,0.004975659,0.000266344,0.002909601,0.0815213],"study_design_scores_gemma":[0.002504215,0.0007788959,0.8532051,0.000280025,0.0001054738,0.0002424302,0.03213751,0.02155172,0.00002010852,0.00003010984,0.08853702,0.0006073761],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9415874,0.0002942947,0.05482085,0.0009054405,0.0009196801,0.000139583,8.33965e-7,0.00004708664,0.00128475],"genre_scores_gemma":[0.8733247,0.0001152987,0.1231871,0.0002644648,0.001839224,0.000001395246,0.000009288213,0.00002859543,0.001229984],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1564332,"threshold_uncertainty_score":0.9997525,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08174915342893448,"score_gpt":0.3820792831741884,"score_spread":0.3003301297452539,"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."}}