{"id":"W4386576877","doi":"10.18653/v1/2023.findings-eacl.160","title":"Decipherment as Regression: Solving Historical Substitution Ciphers by Learning Symbol Recurrence Relations","year":2023,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Ministère de la Défense Nationale","keywords":"Decipherment; Ciphertext; Cipher; Computer science; Artificial intelligence; Theoretical computer science; Algorithm; Natural language processing; Encryption; Linguistics; Computer security","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0007947364,0.0007650641,0.000582652,0.0007240746,0.0003358931,0.0007552987,0.001045153,0.0008137922,0.0020823],"category_scores_gemma":[0.004045748,0.000320261,0.0008958017,0.0005735311,0.0006810435,0.002222491,0.0006794572,0.001552356,0.0007418805],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007760818,"about_ca_system_score_gemma":0.001034179,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003249772,"about_ca_topic_score_gemma":0.004670466,"domain_scores_codex":[0.9996198,0.0001049234,0.00002347172,0.0001561735,0.0000548281,0.00004069469],"domain_scores_gemma":[0.9983127,0.00109151,0.0002047521,0.0002162207,0.0001221471,0.00005282405],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003367446,0.0002554377,0.006641756,0.0002956227,0.0001070581,0.0005987542,0.0003869176,0.632019,0.01615395,0.0283071,0.005564186,0.3093335],"study_design_scores_gemma":[0.00001087198,0.00003617631,0.0002164672,0.000007423366,0.000009795984,0.00005405692,0.00002968766,0.9888285,0.00363242,0.006541203,0.0006273407,0.000005957258],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.260882,0.0009158226,0.7305689,0.0009014199,0.00007501495,0.0001227008,0.0006116277,0.002905425,0.003017077],"genre_scores_gemma":[0.8456372,0.0003808687,0.1466292,0.0001980027,0.00006941733,0.00009464807,0.001252768,0.000197684,0.005540146],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003249772,"threshold_uncertainty_score":0.006965935,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01653283092511668,"score_gpt":0.2832459613928868,"score_spread":0.2667131304677701,"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."}}