{"id":"W3214151424","doi":"10.48550/arxiv.2111.07263","title":"Code Representation Learning with Prüfer Sequences","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Automatic summarization; Sequence (biology); Representation (politics); Source code; Artificial intelligence; Encoding (memory); Syntax; Benchmark (surveying); Deep learning; Code (set theory); Program comprehension; Natural language processing; Abstract syntax; Programming language; Software; Software system","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":[0.0006616656,0.0009165861,0.0005661454,0.001358598,0.0003327397,0.0007893562,0.001437317,0.001089645,0.002269393],"category_scores_gemma":[0.00529179,0.0003006711,0.0006531429,0.001307804,0.0006645414,0.003288578,0.001001152,0.001930209,0.001107998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00115683,"about_ca_system_score_gemma":0.001550671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004890773,"about_ca_topic_score_gemma":0.006453998,"domain_scores_codex":[0.9993929,0.0001597191,0.00003964939,0.0001998946,0.0001453104,0.00006251273],"domain_scores_gemma":[0.9982725,0.000602194,0.0002144949,0.0004620551,0.0003819998,0.0000667514],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002811675,0.0001882038,0.001928049,0.0001960769,0.0000439412,0.0001464806,0.0001671555,0.4171398,0.007746907,0.02528766,0.009621258,0.5372532],"study_design_scores_gemma":[0.00001490612,0.00006770456,0.0001496897,0.00001327235,0.000008199,0.00003050825,0.00001775445,0.9723672,0.004286751,0.02090531,0.002129621,0.000009086075],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07402587,0.0005497907,0.9145074,0.0006334526,0.00007917163,0.0001022182,0.001115122,0.007007615,0.001979341],"genre_scores_gemma":[0.6257963,0.0005300131,0.3583262,0.0003637081,0.00008228712,0.000390968,0.006833058,0.0004713434,0.007206164],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004890773,"threshold_uncertainty_score":0.009724617,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08707538642658927,"score_gpt":0.2167939914713789,"score_spread":0.1297186050447896,"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."}}