{"id":"W4415315888","doi":"10.48550/arxiv.2510.06557","title":"The Markovian Thinker: Architecture-Agnostic Linear Scaling of Reasoning","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Samsung; Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research; Microsoft Research","keywords":"Initialization; Reinforcement learning; Context (archaeology); Decoupling (probability); Matching (statistics); Continuation; Constant (computer programming); Markov process","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001921911,0.0009856734,0.0006813798,0.0003452019,0.0004778072,0.001430024,0.002300949,0.0009504828,0.007485691],"category_scores_gemma":[0.01200326,0.000777924,0.0008334821,0.0002907873,0.001297916,0.003804483,0.001985449,0.004161983,0.001518687],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001650741,"about_ca_system_score_gemma":0.001967584,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004770303,"about_ca_topic_score_gemma":0.00747702,"domain_scores_codex":[0.9990183,0.0003232355,0.00004539305,0.0003008493,0.0001633225,0.0001489731],"domain_scores_gemma":[0.9958218,0.002058807,0.0002836496,0.001194632,0.0003741148,0.0002670212],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001286163,0.000598919,0.005998404,0.0003435555,0.0001734375,0.0002449009,0.0004225684,0.7361932,0.02086517,0.04964486,0.01130188,0.1729269],"study_design_scores_gemma":[0.00005564901,0.00008829552,0.0003210131,0.00001422598,0.00001882369,0.00002022924,0.0000197087,0.9663827,0.003282165,0.02872513,0.001059072,0.00001295567],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2446436,0.000695608,0.725519,0.002221991,0.0002590051,0.0001683632,0.0005192267,0.01255003,0.01342322],"genre_scores_gemma":[0.8641142,0.0001671613,0.1296125,0.0005012575,0.00005086651,0.0002010202,0.0005091696,0.000713918,0.004129843],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007485691,"threshold_uncertainty_score":0.02504212,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02605805089703114,"score_gpt":0.2681770662058424,"score_spread":0.2421190153088113,"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."}}