{"id":"W4393027458","doi":"10.48550/arxiv.2403.12646","title":"Prompt-fused framework for Inductive Logical Query Answering","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Science Foundation of Ningbo; Natural Science Foundation of Zhejiang Province; National Natural Science Foundation of China; Fundamental Research Funds for the Central Universities; Institute for Catastrophic Loss Reduction","keywords":"Computer science; Question answering; Information retrieval; Query optimization","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004131762,0.001172911,0.001243114,0.002328096,0.0008814865,0.002781898,0.003074273,0.002003154,0.006041669],"category_scores_gemma":[0.01251688,0.0005998593,0.002141364,0.002568931,0.001776498,0.008296678,0.004570789,0.003452433,0.001722559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002067639,"about_ca_system_score_gemma":0.002918027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005059914,"about_ca_topic_score_gemma":0.009007982,"domain_scores_codex":[0.9961239,0.001186611,0.0002977224,0.0009276113,0.001217552,0.0002466608],"domain_scores_gemma":[0.9955843,0.002322969,0.0002130715,0.001008376,0.00070749,0.0001638666],"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":[0.0005241351,0.0004587456,0.002289599,0.0009133361,0.0001396206,0.000769141,0.001453658,0.1892256,0.01363679,0.4227764,0.02537106,0.3424419],"study_design_scores_gemma":[0.00003434579,0.00006485191,0.0001783265,0.00003184459,0.00004257142,0.0001751668,0.0001687661,0.7483555,0.003873423,0.2339268,0.01311498,0.00003337154],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002361328,0.0001797685,0.9920386,0.0004367228,0.00003105505,0.0001307791,0.0004824837,0.00326352,0.001075726],"genre_scores_gemma":[0.1384178,0.0003431007,0.8558931,0.0004657985,0.00009527491,0.0003540058,0.00187786,0.0003828431,0.002170253],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006041669,"threshold_uncertainty_score":0.02185112,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1405162479677425,"score_gpt":0.2290242234940525,"score_spread":0.0885079755263101,"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."}}