{"id":"W3204615515","doi":"10.1016/j.ipm.2021.102746","title":"A semantic approach to post-retrieval query performance prediction","year":2021,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Information retrieval; Semantic similarity; Cohesion (chemistry); Query expansion; Graph; Semantics (computer science); Relevance (law); Natural language processing; Theoretical computer science","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005143846,0.0001626262,0.0001349847,0.0003928554,0.0003685263,0.001148619,0.0005236614,0.00005796588,0.00001718775],"category_scores_gemma":[0.00003950108,0.000154457,0.00005321381,0.001418003,0.00002078901,0.007665143,0.0004009522,0.0001516571,0.0004453999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001312495,"about_ca_system_score_gemma":0.0001525764,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002681555,"about_ca_topic_score_gemma":1.756742e-7,"domain_scores_codex":[0.9979709,0.00002778796,0.0005615205,0.000209589,0.0008740927,0.0003560823],"domain_scores_gemma":[0.9985998,0.000008809991,0.0001530367,0.0003983661,0.0006999767,0.0001400374],"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":[0.000062983,0.0001991222,0.0003542008,0.001666767,0.00003682407,0.000008547613,0.008538534,0.005476059,0.000135269,0.02077506,0.001865245,0.9608814],"study_design_scores_gemma":[0.001642982,0.000224307,0.0652001,0.0003627675,0.00005356526,0.000158234,0.003111959,0.8341853,0.006646714,0.000288548,0.08727865,0.0008468669],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05616999,0.00002680526,0.8935589,0.0008982045,0.0003643969,0.0005502522,0.000007889792,0.0004560323,0.04796749],"genre_scores_gemma":[0.9347273,0.00002817829,0.05967727,0.003554652,0.00004778978,0.00007148514,0.0001606687,0.00000854569,0.001724145],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9600345,"threshold_uncertainty_score":0.9998883,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01312576929361862,"score_gpt":0.2335895568102155,"score_spread":0.2204637875165969,"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."}}