{"id":"W7117276983","doi":"","title":"The Limitations and Power of NP-Oracle-Based Functional Synthesis Techniques","year":2025,"lang":"","type":"article","venue":"ArXiv.org","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Oracle; Tuple; Scalability; Set (abstract data type); Boolean function; Class (philosophy); Function (biology); Construct (python library)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001635057,0.0002058065,0.0002225087,0.0002197998,0.0006742784,0.00014509,0.0006980399,0.0001499806,0.00002107905],"category_scores_gemma":[0.002500188,0.000171067,0.0001123004,0.000986423,0.000647529,0.0004570395,0.0002416168,0.0002499586,0.00002192332],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006988872,"about_ca_system_score_gemma":0.0003311019,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001570037,"about_ca_topic_score_gemma":0.000005113137,"domain_scores_codex":[0.9979163,0.0004309731,0.000591387,0.0004643784,0.0003122571,0.0002846639],"domain_scores_gemma":[0.9955624,0.002608272,0.0003165076,0.000988477,0.000459944,0.00006440422],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001893605,0.0004343387,0.1299281,0.0001801946,0.0001908127,0.00000202042,0.0007488686,0.00008220613,0.01131654,0.2442122,0.001822149,0.6108932],"study_design_scores_gemma":[0.0002198076,0.0002032451,0.7342927,0.0002513712,0.0001038425,0.000004074571,0.0002205547,0.02176446,0.2092759,0.003449685,0.02990681,0.0003074577],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1228102,0.001435663,0.8621368,0.007203985,0.00109203,0.0004527254,0.000009681192,0.0001321949,0.004726707],"genre_scores_gemma":[0.8431866,0.0003854851,0.1554229,0.0004401701,0.00003105652,0.0001218713,0.000001008838,0.00001058267,0.0004004005],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7203763,"threshold_uncertainty_score":0.6975908,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07686800602444017,"score_gpt":0.3022238584691346,"score_spread":0.2253558524446944,"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."}}