{"id":"W4412673509","doi":"10.1145/3731120.3744609","title":"Exploring the Utility of Embedding Similarity for Contract Tasks","year":2025,"lang":"en","type":"article","venue":"","topic":"Multi-Agent Systems and Negotiation","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Nuvo Pharmaceuticals (Canada)","funders":"","keywords":"Embedding; Similarity (geometry); Computer science; Artificial intelligence; Image (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":[0.005367368,0.0007946032,0.0007398246,0.001606458,0.0006793678,0.002049454,0.001264181,0.001845427,0.002728516],"category_scores_gemma":[0.02850187,0.0003769637,0.0006315305,0.001532729,0.001360451,0.006931601,0.002319632,0.001946359,0.0005560494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000852804,"about_ca_system_score_gemma":0.0006628847,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002054288,"about_ca_topic_score_gemma":0.002143623,"domain_scores_codex":[0.9973025,0.001759703,0.0001153861,0.0004387069,0.000240872,0.0001426975],"domain_scores_gemma":[0.9880159,0.009419328,0.0006169516,0.001131377,0.0004927905,0.0003235929],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001402877,0.001203286,0.02851339,0.0004792934,0.0002561119,0.0002986127,0.001669492,0.3654351,0.00694799,0.07767677,0.004140372,0.5119767],"study_design_scores_gemma":[0.00003421078,0.0001966673,0.001543822,0.00001785149,0.00001451269,0.00006805261,0.0002180443,0.9351161,0.001097338,0.06088698,0.00078658,0.00001981808],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5028587,0.001334325,0.4857566,0.001241926,0.00008530378,0.0001861649,0.0003912666,0.0009646924,0.007180977],"genre_scores_gemma":[0.9489737,0.0001176379,0.04953612,0.00007762118,0.000029995,0.00005064543,0.0003271348,0.00006134926,0.0008259545],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005367368,"threshold_uncertainty_score":0.0283857,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1500744780523252,"score_gpt":0.3348046990262432,"score_spread":0.1847302209739179,"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."}}