{"id":"W4412876920","doi":"10.1145/3711896.3737233","title":"Hierarchical Lexical Graph for Enhanced Multi-Hop Retrieval","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Graph; Hop (telecommunications); Information retrieval; Artificial intelligence; Theoretical computer science; Computer network","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":[0.001655811,0.001169143,0.001080482,0.004641921,0.0007825833,0.001675334,0.002168234,0.001647382,0.008433457],"category_scores_gemma":[0.009576448,0.0004651678,0.001278278,0.0032831,0.0007722132,0.004267349,0.002818274,0.00122989,0.004632644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001082811,"about_ca_system_score_gemma":0.001837823,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006928673,"about_ca_topic_score_gemma":0.01426631,"domain_scores_codex":[0.9985386,0.0005412832,0.000116796,0.000362312,0.0003387047,0.0001024257],"domain_scores_gemma":[0.9968864,0.001764647,0.0001604932,0.0007056565,0.0003960738,0.00008659463],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006174087,0.0003156648,0.00292249,0.00158238,0.0002644931,0.0006270881,0.00101732,0.07842958,0.02774304,0.04164293,0.08250236,0.7623352],"study_design_scores_gemma":[0.0002041771,0.0002481703,0.001178951,0.0001248112,0.0002089072,0.0005274937,0.0004750724,0.7865539,0.01571159,0.1499923,0.04467739,0.00009711735],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02288697,0.003401716,0.9284875,0.001028287,0.0001837739,0.0005030636,0.007337445,0.03144278,0.004728433],"genre_scores_gemma":[0.2787377,0.001079945,0.6838491,0.000933011,0.0002086184,0.0005654267,0.02596348,0.001743365,0.00691935],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008433457,"threshold_uncertainty_score":0.02821273,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05106226831373131,"score_gpt":0.3238981275221801,"score_spread":0.2728358592084488,"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."}}