{"id":"W4388132066","doi":"10.1007/978-3-031-47240-4_28","title":"Neural Multi-hop Logical Query Answering with Concept-Level Answers","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Axiom; Question answering; Description logic; Theoretical computer science; Inference; Fuzzy logic; Knowledge representation and reasoning; Set (abstract data type); Information retrieval; Artificial intelligence; Mathematics","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":[0.001031624,0.0006810023,0.001153979,0.0009073802,0.0006609902,0.001856392,0.002630423,0.002309297,0.008640109],"category_scores_gemma":[0.005523282,0.0005790866,0.0008063129,0.001395914,0.000771222,0.004495639,0.002247762,0.001906298,0.001659983],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009570642,"about_ca_system_score_gemma":0.0008571119,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003656772,"about_ca_topic_score_gemma":0.005111937,"domain_scores_codex":[0.999258,0.0001510331,0.00006682468,0.000278148,0.0001538181,0.00009215607],"domain_scores_gemma":[0.9978968,0.001499392,0.0001015102,0.0002141552,0.0002217068,0.00006638389],"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":[0.001202479,0.0006916185,0.002744945,0.0007019352,0.0002016588,0.0003373818,0.000423703,0.2350915,0.01701142,0.04281752,0.02198527,0.6767906],"study_design_scores_gemma":[0.00002579838,0.00007096913,0.0002410525,0.00001776502,0.00003262726,0.00006921659,0.0000737495,0.9605037,0.002814848,0.03500915,0.00112922,0.00001194928],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1174985,0.002135657,0.8641841,0.001497029,0.0003131799,0.0001725248,0.001210236,0.003700164,0.009288523],"genre_scores_gemma":[0.789465,0.0005968131,0.1951935,0.0004867383,0.0002591016,0.0001636532,0.003078238,0.0001754688,0.01058141],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008640109,"threshold_uncertainty_score":0.02890402,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05907292893981171,"score_gpt":0.2709737461281931,"score_spread":0.2119008171883814,"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."}}