{"id":"W4405906730","doi":"10.1038/s41598-024-82871-0","title":"A multi-dimensional semantic pseudo-relevance feedback framework for information retrieval","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Information Retrieval and Search Behavior","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; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Information retrieval; Ranking (information retrieval); Query expansion; Relevance (law); Relevance feedback; Sentence; Concept search; Field (mathematics); Set (abstract data type); Search engine; Web search query; Artificial intelligence; Image retrieval","routes":{"ca_aff":true,"ca_fund":true,"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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002153535,0.0001704176,0.0001649452,0.0003996781,0.0005021248,0.002564173,0.0004231419,0.0001233611,0.00004390188],"category_scores_gemma":[0.0007156958,0.0001419906,0.0001713207,0.001520747,0.0001414869,0.003685592,0.0002017358,0.0002454253,0.0004900087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000961973,"about_ca_system_score_gemma":0.0004701403,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004231835,"about_ca_topic_score_gemma":9.871166e-7,"domain_scores_codex":[0.9971801,0.00002593316,0.0007404733,0.0005343663,0.001059863,0.0004592791],"domain_scores_gemma":[0.9980214,0.0001967725,0.0001940764,0.0008356388,0.0005786627,0.0001734928],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002449006,0.0006906056,0.0009342541,0.002961378,0.0003019785,0.00144808,0.02482578,0.003725253,0.05038218,0.4389877,0.2434821,0.2320158],"study_design_scores_gemma":[0.0003210205,0.0001185109,0.0009326442,0.0004165851,0.00002654323,0.0007047625,0.0000788718,0.6766402,0.02375531,0.05958597,0.2368148,0.000604784],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06262489,0.00017551,0.9138424,0.0008836928,0.02087951,0.0008515018,0.00001251344,0.0005474235,0.0001825263],"genre_scores_gemma":[0.5950522,0.000005588051,0.4001873,0.0003555764,0.0001606468,0.00006376325,0.0001417384,0.00001773068,0.004015555],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6729149,"threshold_uncertainty_score":0.9984713,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02343741958684139,"score_gpt":0.2935850799618369,"score_spread":0.2701476603749955,"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."}}