{"id":"W6966211779","doi":"10.48448/jwf7-0p88","title":"FactKG: Fact Verification via Reasoning on Knowledge Graphs","year":2022,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Natural language; Knowledge graph; Reliability (semiconductor); Knowledge-based systems; Question answering; Baseline (sea); Conjunction (astronomy); Natural (archaeology); Style (visual arts)","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001571655,0.0005994975,0.0004581982,0.002891765,0.0008166297,0.0002192766,0.002023109,0.0002295093,0.01651835],"category_scores_gemma":[0.0002936306,0.0005842723,0.0001308057,0.003780789,0.001271227,0.0002729557,0.0003899322,0.0008527602,0.01369129],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001248046,"about_ca_system_score_gemma":0.0009557793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003758159,"about_ca_topic_score_gemma":0.0004212848,"domain_scores_codex":[0.9951845,0.0001932689,0.0004147633,0.001626574,0.001674989,0.0009059462],"domain_scores_gemma":[0.9972217,0.0001004134,0.0006224624,0.001598068,0.0001466321,0.0003107103],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007714141,0.00130583,0.001408036,0.000132509,0.0001335023,0.00003479105,0.001462132,0.0004060295,0.0212597,0.08569739,0.8308393,0.05724361],"study_design_scores_gemma":[0.0004562591,0.0002557493,0.001037165,0.0001527051,0.0000460321,0.00001662876,0.0002838816,0.008532769,0.0006333102,0.0008714136,0.9867242,0.0009898935],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0008306653,0.0008338314,0.0006892184,0.00007241299,0.001653798,0.0009144839,0.0004476372,0.001619622,0.9929383],"genre_scores_gemma":[0.3173017,0.0001378838,0.006144446,0.0002917348,0.0006723094,0.0002279539,0.001279512,0.002799003,0.6711455],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.3217928,"threshold_uncertainty_score":0.9996608,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02722980751033778,"score_gpt":0.3141701906284664,"score_spread":0.2869403831181286,"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."}}