{"id":"W6948143068","doi":"10.48448/ztm6-3d82","title":"Neuro-symbolic Natural Logic with Introspective Revision for Natural Language Inference","year":2022,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Lichen and fungal ecology","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Interpretability; Natural language; Introspection; Inference; Non-monotonic logic; Spurious relationship; Natural (archaeology); Relation (database); Opportunistic reasoning","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003585012,0.0003328133,0.0003951456,0.0001045453,0.0005015114,0.0001394547,0.001065452,0.0001369577,0.003629615],"category_scores_gemma":[0.0004093614,0.0001208476,0.00008616775,0.001043293,0.0006018732,0.0001518172,0.0003933457,0.0005632692,0.00004656861],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000151269,"about_ca_system_score_gemma":0.0001007246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000360485,"about_ca_topic_score_gemma":0.003276567,"domain_scores_codex":[0.9977074,0.00006722804,0.0002155191,0.0008902034,0.0005029892,0.0006166319],"domain_scores_gemma":[0.998928,0.0003957195,0.0002603093,0.0001643187,0.0001228905,0.000128764],"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":[0.0006370795,0.001046009,0.01056598,0.0002461833,0.0002170676,0.0002043525,0.001601697,0.00004180371,0.1638268,0.06646755,0.2757213,0.4794241],"study_design_scores_gemma":[0.00147242,0.004694816,0.02218927,0.0001678789,0.0001266146,0.0001310291,0.003234436,0.005543019,0.0005909816,0.002073285,0.9573677,0.002408512],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2386974,0.02470335,0.0004639831,0.03181483,0.01849346,0.0182101,0.003289032,0.005471136,0.6588567],"genre_scores_gemma":[0.9102585,0.00009175868,0.00187504,0.003310376,0.001236153,0.00009382509,0.0005466859,0.00002540772,0.08256219],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6816464,"threshold_uncertainty_score":0.9972812,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01188357011416079,"score_gpt":0.2646833861537445,"score_spread":0.2527998160395837,"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."}}