{"id":"W4406064005","doi":"10.1016/j.ipm.2024.104058","title":"A semantic framework for enhancing pseudo-relevance feedback with soft negative sampling and contrastive learning","year":2025,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; Western University","funders":"Natural Science Foundation of Hubei Province; National Natural Science Foundation of China; Hubei Provincial Department of Education","keywords":"Relevance (law); Computer science; Sampling (signal processing); Natural language processing; Psychology; Artificial intelligence; Linguistics; Political science; Philosophy; Computer vision","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004402031,0.001481916,0.001574424,0.001864713,0.0006183576,0.001383694,0.002808835,0.001968987,0.001916217],"category_scores_gemma":[0.0148846,0.0004850941,0.00100706,0.001349732,0.002078138,0.00406354,0.002269286,0.001934661,0.0008480141],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001339762,"about_ca_system_score_gemma":0.001492942,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002380281,"about_ca_topic_score_gemma":0.002393196,"domain_scores_codex":[0.9968351,0.001261925,0.0001620945,0.0006086099,0.000974288,0.0001580448],"domain_scores_gemma":[0.9957572,0.002334577,0.0003331215,0.0004783163,0.0009427979,0.0001541156],"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":[0.0006684252,0.000746136,0.002450791,0.0005447823,0.0001506942,0.0004008037,0.0006525857,0.260164,0.03563102,0.08589139,0.006482641,0.6062167],"study_design_scores_gemma":[0.00004206631,0.0001745142,0.0002159987,0.00002007749,0.00002429687,0.0001170541,0.00002215663,0.9684415,0.003313478,0.0259334,0.001668177,0.00002716821],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00780751,0.0004529925,0.9900129,0.0001858158,0.00004396931,0.00009299599,0.00003921411,0.0004624962,0.0009020669],"genre_scores_gemma":[0.5173928,0.0007098721,0.4755385,0.0009079593,0.0003976398,0.0005924335,0.0003515546,0.0002511662,0.003858106],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004402031,"threshold_uncertainty_score":0.02328044,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01007160982246063,"score_gpt":0.2650852752459006,"score_spread":0.25501366542344,"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."}}