{"id":"W4327645767","doi":"10.1007/978-3-031-28244-7_1","title":"Self-supervised Contrastive BERT Fine-tuning for Fusion-Based Reviewed-Item Retrieval","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Ranking (information retrieval); Artificial intelligence; Matching (statistics); Selection (genetic algorithm); Natural language processing; Information retrieval; Task (project management); Embedding; Machine learning","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"],"consensus_categories":[],"category_scores_codex":[0.00203951,0.0007145278,0.0009266,0.0008473042,0.0004500041,0.0005452419,0.003834302,0.0004441467,0.00001242233],"category_scores_gemma":[0.0008210701,0.0006627823,0.0003135808,0.0009827777,0.0002909188,0.0004519883,0.001152743,0.0008684901,0.0000443035],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004209107,"about_ca_system_score_gemma":0.001205051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001207118,"about_ca_topic_score_gemma":0.0000398827,"domain_scores_codex":[0.9945043,0.00006370958,0.000893862,0.002288927,0.001265007,0.0009841871],"domain_scores_gemma":[0.9938903,0.003078593,0.0004016201,0.001725553,0.0006461192,0.0002578287],"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":[0.00004464286,0.00005554767,0.00007115833,0.0006436746,0.00004835768,0.0001588725,0.001372081,0.0496707,0.0004250724,0.0272015,0.0001044917,0.9202039],"study_design_scores_gemma":[0.0006033439,0.0001816671,0.00001981128,0.00116197,0.00002093272,0.00001329958,1.595813e-7,0.9640191,0.0004372891,0.03090188,0.001928145,0.0007123691],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00004280868,0.0006516021,0.9919459,0.001654684,0.003014355,0.001372655,0.00001740859,0.0006565113,0.0006440796],"genre_scores_gemma":[0.01208508,0.00007777254,0.9836004,0.002570122,0.000979468,0.00004014348,0.00002102848,0.00009467018,0.0005312721],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9194915,"threshold_uncertainty_score":0.9995824,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03059425526710696,"score_gpt":0.2597612823452757,"score_spread":0.2291670270781688,"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."}}