{"id":"W1563080589","doi":"10.48550/arxiv.1304.3666","title":"Sets Represented as the Length-n Factors of a Word","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Combinatorics; Word (group theory); Upper and lower bounds; Mathematics; Sigma; Set (abstract data type); Superstring theory; Binary number; Discrete mathematics; Computer science; Arithmetic; Physics","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":[],"consensus_categories":[],"category_scores_codex":[0.00017251,0.0002728164,0.0003115754,0.0001549959,0.0001613209,0.000115852,0.003338247,0.0002188834,0.00009111433],"category_scores_gemma":[0.00005991651,0.0002046555,0.0002112028,0.0004514822,0.0001469564,0.0004613991,0.005459437,0.0005508923,0.00009458101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005924991,"about_ca_system_score_gemma":0.0001410671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001733422,"about_ca_topic_score_gemma":0.00001521745,"domain_scores_codex":[0.9982749,0.000177971,0.0002198191,0.000892291,0.0001555022,0.000279563],"domain_scores_gemma":[0.9966378,0.0002130964,0.0003646277,0.002472053,0.0001824866,0.0001299417],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000170996,0.001231871,0.03125568,0.0004612766,0.00130526,0.0008815365,0.007288702,0.172859,0.0005651906,0.721364,0.02898912,0.03362728],"study_design_scores_gemma":[0.0005617152,0.00008624998,0.01457168,0.0002496392,0.00008503514,0.000007647473,0.0003753642,0.8875941,0.0009511863,0.08780047,0.00700347,0.0007134628],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7909291,0.00008850986,0.2049016,0.0001722924,0.0006834338,0.0003902951,0.00003056904,0.0001645477,0.002639687],"genre_scores_gemma":[0.9969305,0.0001459886,0.001105549,0.00004684836,0.00003426773,9.31799e-7,0.00002554384,0.00001183148,0.001698551],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.714735,"threshold_uncertainty_score":0.834561,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07740893054860999,"score_gpt":0.203233405862492,"score_spread":0.125824475313882,"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."}}