{"id":"W4221123674","doi":"10.1016/j.patrec.2022.03.018","title":"Hyper-graph-based attention curriculum learning using a lexical algorithm for mental health","year":2022,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Mental Health via Writing","field":"Psychology","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brandon University","funders":"","keywords":"Computer science; Lexicon; Natural language processing; Word embedding; Artificial intelligence; Graph; Vocabulary; Embedding; Mental lexicon; Hypergraph; Representation (politics); Algorithm; Theoretical computer science; Linguistics; 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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009965964,0.0002176142,0.000262176,0.0002900909,0.001252296,0.00003775333,0.000112899,0.00005156479,0.001820999],"category_scores_gemma":[0.00001075528,0.0002713653,0.0002052605,0.0002610911,0.00004951372,0.00009811477,0.00005959732,0.0005100177,0.0001058038],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005093243,"about_ca_system_score_gemma":0.00004018543,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008134976,"about_ca_topic_score_gemma":0.00001334584,"domain_scores_codex":[0.9968897,0.0009087325,0.0005520696,0.0005693464,0.0003725524,0.0007076136],"domain_scores_gemma":[0.9991505,0.000121215,0.0003741464,0.0001484984,0.00003602779,0.0001695809],"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":[0.00007242925,0.0005903421,0.03565453,0.000162368,0.00006031717,0.00002493217,0.0007985777,0.000148815,0.002961612,0.000003665177,0.005829313,0.9536931],"study_design_scores_gemma":[0.04203729,0.006924332,0.03810295,0.001523977,0.0003730431,0.002158964,0.04814756,0.7963283,0.0009420106,0.0002987426,0.05809159,0.005071245],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7433394,0.00008634349,0.24611,0.006704612,0.001857558,0.001253355,0.000425424,0.0001687067,0.00005463447],"genre_scores_gemma":[0.9378735,0.000003230961,0.01559123,0.04088517,0.0006004152,0.001309221,0.003574168,0.0001159108,0.0000471696],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9486219,"threshold_uncertainty_score":0.9999738,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0626509453268886,"score_gpt":0.3605151372306984,"score_spread":0.2978641919038098,"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."}}