{"id":"W2955281392","doi":"10.1145/3331184.3331311","title":"On Tradeoffs Between Document Signature Methods for a Legal Due Diligence Corpus","year":2019,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Cisco Systems (Canada)","funders":"","keywords":"Due diligence; Computer science; Hash function; Context (archaeology); Diligence; Signature (topology); Limit (mathematics); Information retrieval; Computer security; Political science; Mathematics; Law; Geography","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":["insufficient_payload"],"category_scores_codex":[0.007029541,0.0001639642,0.0003662327,0.0001662491,0.00009973646,0.0004110209,0.001187918,0.00009462094,0.001531257],"category_scores_gemma":[0.001167069,0.0001065531,0.0001699497,0.0003962169,0.00004248833,0.0005021369,0.0002334224,0.0001505204,0.001041592],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003836154,"about_ca_system_score_gemma":0.00003807522,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006442242,"about_ca_topic_score_gemma":0.00003126026,"domain_scores_codex":[0.9971402,0.0003721342,0.000553287,0.0006947402,0.0009200088,0.0003196758],"domain_scores_gemma":[0.9940513,0.004623988,0.0001625704,0.0009505136,0.00008857127,0.0001230951],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000676249,0.00005564082,0.0001883357,0.00001519,0.00003887904,0.000002107761,0.0001740019,0.00007752963,0.000251945,0.5328811,0.06147116,0.4047764],"study_design_scores_gemma":[0.0004412623,0.0003619668,0.002353489,0.0000105513,0.00002117568,7.63939e-7,0.0003804979,0.0004438716,0.003770523,0.2148816,0.777128,0.0002063549],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02862314,0.00007689004,0.9230621,0.006744638,0.001427322,0.001599271,0.0001076526,0.0001006727,0.0382583],"genre_scores_gemma":[0.784903,0.000007434994,0.1089633,0.004618889,0.0001582532,0.00007396675,0.00005332598,0.00001812417,0.1012036],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8140988,"threshold_uncertainty_score":0.9997362,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.152014877530545,"score_gpt":0.4960927056453076,"score_spread":0.3440778281147626,"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."}}