{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/mathematical-reasoning","name":"Mathematical Reasoning","slug":"mathematical-reasoning","description_markdown":null,"categories":[{"name":"Knowledge Base","url":"/area/knowledge-base"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"},{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":805,"papers_with_code":395,"benchmarks":10,"benchmark_tables_in_archive":11,"benchmark_tables_shown":11,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":26,"subtasks":7,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/mathematical-reasoning-on-aime24","slug":"mathematical-reasoning-on-aime24","dataset":"AIME24","dataset_url":null,"rows_in_archive":9,"metrics":["Acc"],"first_row_in_archive_order":{"model":"Xolver","paper_title":"Xolver: Multi-Agent Reasoning with Holistic Experience Learning Just Like an Olympiad Team","paper_url":"/paper/xolver-multi-agent-reasoning-with-holistic","paper_date":"2025-06-17","arxiv_id":"2506.14234","code_links":[{"title":"kagnlp/Xolver","url":"https://github.com/kagnlp/Xolver"}],"syntology":null}},{"leaderboard":"/sota/mathematical-reasoning-on-frontiermath","slug":"mathematical-reasoning-on-frontiermath","dataset":"FrontierMath","dataset_url":null,"rows_in_archive":6,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"o3","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/mathematical-reasoning-on-lila-iid","slug":"mathematical-reasoning-on-lila-iid","dataset":"Lila (IID)","dataset_url":null,"rows_in_archive":6,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Codex (Few-Shot, 175B)","paper_title":"Lila: A Unified Benchmark for Mathematical Reasoning","paper_url":"/paper/lila-a-unified-benchmark-for-mathematical","paper_date":"2022-10-31","arxiv_id":"2210.17517","code_links":[{"title":"allenai/lila","url":"https://github.com/allenai/lila"}],"syntology":null}},{"leaderboard":"/sota/mathematical-reasoning-on-lila-ood","slug":"mathematical-reasoning-on-lila-ood","dataset":"Lila (OOD)","dataset_url":null,"rows_in_archive":6,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Codex (Few-Shot, 175B)","paper_title":"Lila: A Unified Benchmark for Mathematical Reasoning","paper_url":"/paper/lila-a-unified-benchmark-for-mathematical","paper_date":"2022-10-31","arxiv_id":"2210.17517","code_links":[{"title":"allenai/lila","url":"https://github.com/allenai/lila"}],"syntology":null}},{"leaderboard":"/sota/mathematical-reasoning-on-pgps9k","slug":"mathematical-reasoning-on-pgps9k","dataset":"PGPS9K","dataset_url":"/dataset/pgps9k","rows_in_archive":6,"metrics":["Completion accuracy"],"first_row_in_archive_order":{"model":"GOLD","paper_title":"GOLD: Geometry Problem Solver with Natural Language Description","paper_url":"/paper/gold-geometry-problem-solver-with-natural","paper_date":"2024-05-01","arxiv_id":"2405.00494","code_links":[{"title":"neurasearch/geometry-diagram-description","url":"https://github.com/neurasearch/geometry-diagram-description"}],"syntology":null}},{"leaderboard":"/sota/mathematical-reasoning-on-amc23","slug":"mathematical-reasoning-on-amc23","dataset":"AMC23","dataset_url":null,"rows_in_archive":3,"metrics":["Acc"],"first_row_in_archive_order":{"model":"QWQ-32B-preview","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/mathematical-reasoning-on-geoqa","slug":"mathematical-reasoning-on-geoqa","dataset":"GeoQA","dataset_url":"/dataset/geoqa","rows_in_archive":2,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"GOLD","paper_title":"GOLD: Geometry Problem Solver with Natural Language Description","paper_url":"/paper/gold-geometry-problem-solver-with-natural","paper_date":"2024-05-01","arxiv_id":"2405.00494","code_links":[{"title":"neurasearch/geometry-diagram-description","url":"https://github.com/neurasearch/geometry-diagram-description"}],"syntology":null}},{"leaderboard":"/sota/mathematical-reasoning-on-math500","slug":"mathematical-reasoning-on-math500","dataset":"MATH500","dataset_url":"/dataset/math500-1","rows_in_archive":1,"metrics":["Acc"],"first_row_in_archive_order":{"model":"Search-o1","paper_title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","paper_url":"/paper/search-o1-agentic-search-enhanced-large","paper_date":"2025-01-09","arxiv_id":"2501.05366","code_links":[{"title":"sunnynexus/search-o1","url":"https://github.com/sunnynexus/search-o1"},{"title":"terrierteam/pyterrier_rag","url":"https://github.com/terrierteam/pyterrier_rag"}],"syntology":null}},{"leaderboard":"/sota/mathematical-reasoning-on-unigeo","slug":"mathematical-reasoning-on-unigeo","dataset":"UniGeo","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"GOLD","paper_title":"GOLD: Geometry Problem Solver with Natural Language Description","paper_url":"/paper/gold-geometry-problem-solver-with-natural","paper_date":"2024-05-01","arxiv_id":"2405.00494","code_links":[{"title":"neurasearch/geometry-diagram-description","url":"https://github.com/neurasearch/geometry-diagram-description"}],"syntology":null}},{"leaderboard":"/sota/mathematical-reasoning-on-unigeo-prv","slug":"mathematical-reasoning-on-unigeo-prv","dataset":"UniGeo (PRV)","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"GAPS","paper_title":"GAPS: Geometry-Aware Problem Solver","paper_url":"/paper/gaps-geometry-aware-problem-solver","paper_date":"2024-01-29","arxiv_id":"2401.16287","code_links":[],"syntology":null}},{"leaderboard":null,"slug":"mathematical-reasoning-on-gsm8k","dataset":"GSM8K","dataset_url":"/dataset/gsm8k","rows_in_archive":0,"metrics":["Accuracy"],"first_row_in_archive_order":null}],"datasets":[{"url":"/dataset/gsm8k","name":"GSM8K","full_name":"","num_papers_in_archive":1881},{"url":"/dataset/svamp","name":"SVAMP","full_name":"Simple Variations on Arithmetic Math word Problems","num_papers_in_archive":362},{"url":"/dataset/mathvista","name":"MathVista","full_name":"Mathematical Reasoning of in Visual Contexts","num_papers_in_archive":242},{"url":"/dataset/prontoqa","name":"PrOntoQA","full_name":"Proof and Ontology-Generated Question-Answering","num_papers_in_archive":55},{"url":"/dataset/geoqa","name":"GeoQA","full_name":"Geometric Question Answering","num_papers_in_archive":46},{"url":"/dataset/iconqa","name":"IconQA","full_name":"Icon Question Answering","num_papers_in_archive":42},{"url":"/dataset/theoremqa","name":"TheoremQA","full_name":"TheoremQA","num_papers_in_archive":40},{"url":"/dataset/mathbench","name":"MathBench","full_name":"MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmark","num_papers_in_archive":16},{"url":"/dataset/pgps9k","name":"PGPS9K","full_name":"","num_papers_in_archive":14},{"url":"/dataset/lila","name":"Lila","full_name":"","num_papers_in_archive":12},{"url":"/dataset/math-v","name":"MATH-V","full_name":"","num_papers_in_archive":12},{"url":"/dataset/criticbench","name":"CriticBench","full_name":"","num_papers_in_archive":10},{"url":"/dataset/clevr-math","name":"CLEVR-Math","full_name":"","num_papers_in_archive":8},{"url":"/dataset/math500-1","name":"Math500","full_name":"","num_papers_in_archive":4},{"url":"/dataset/mgsm8kinstruct","name":"MGSM8KInstruct","full_name":"MGSM8KInstruct","num_papers_in_archive":2},{"url":"/dataset/paramawps","name":"ParaMAWPS","full_name":"Paraphrased Math Word Problem Solving Repository","num_papers_in_archive":2},{"url":"/dataset/quite","name":"QUITE","full_name":"Quantifying Uncertainty in natural language Text","num_papers_in_archive":2},{"url":"/dataset/asymob","name":"ASyMOB","full_name":"ASyMOB: Algebraic Symbolic Mathematical Operations Benchmark","num_papers_in_archive":1},{"url":"/dataset/champ","name":"CHAMP","full_name":"Concept and Hint-Annotated Math Problems","num_papers_in_archive":1},{"url":"/dataset/conic10k","name":"Conic10K","full_name":"","num_papers_in_archive":1},{"url":"/dataset/constructivebench","name":"ConstructiveBench","full_name":"","num_papers_in_archive":1},{"url":"/dataset/dart-math-uniform","name":"DART-Math-Uniform","full_name":"","num_papers_in_archive":1},{"url":"/dataset/mathmc","name":"MathMC","full_name":"","num_papers_in_archive":1},{"url":"/dataset/mathtof","name":"MathToF","full_name":"","num_papers_in_archive":1},{"url":"/dataset/polymath","name":"PolyMATH","full_name":"","num_papers_in_archive":1},{"url":"/dataset/vimath","name":"ViMATH","full_name":"Vietnamese MATH","num_papers_in_archive":1}],"subtasks":[{"url":"/task/abstract-algebra","name":"Abstract Algebra"},{"url":"/task/formal-logic","name":"Formal Logic"},{"url":"/task/geometry-problem-solving","name":"Geometry Problem Solving"},{"url":"/task/high-school-mathematics","name":"High School Mathematics"},{"url":"/task/math-word-problem-solving","name":"Math Word Problem Solving"},{"url":"/task/mathematical-induction","name":"Mathematical Induction"},{"url":"/task/professional-accounting","name":"Professional Accounting"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":9,"rows_per_page":100,"shown":100,"of":805,"of_with_code":395,"tagged_in_all":805,"counts":{"archive_papers_tagged":805,"with_a_code_link":395,"where_syntology_ran_a_sample":197,"not_listed_spam_title":0,"listed":805,"listed_where_code_ran":197,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":153,"every_run_a_failure_of_syntologys_instrument":44,"listed_with_a_run_with_no_instrument_failure":153,"listed_every_run_a_failure_of_syntologys_instrument":44,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/lora-low-rank-adaptation-of-large-language","slug":"lora-low-rank-adaptation-of-large-language","title":"LoRA: Low-Rank Adaptation of Large Language Models","date":"2021-06-17","arxiv_id":"2106.09685","repositories_listed":74,"syntology":{"n":84,"n_ran":51,"n_constructed":19,"n_ran_checked":43,"n_instrument":8,"n_unverified":33,"n_honours":1,"n_violates":0,"n_no_contract":42,"n_pointer_only":30,"phrase":"51 ran (of which 19 constructed an object rather than computing a result; 43 with no instrument failure: 1 honoured, 0 violated, 42 with no contract checked; 8 where Syntology's instrument failed) · 33 unverified","sample_list":"/paper/lora-low-rank-adaptation-of-large-language#ran","syntology_url":"https://syntology.ai/paper/2106.09685","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09685"}},"official":{"repos":["microsoft/LoRA"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/analysing-mathematical-reasoning-abilities-of-1","slug":"analysing-mathematical-reasoning-abilities-of-1","title":"Analysing Mathematical Reasoning Abilities of Neural Models","date":"2019-04-02","arxiv_id":"1904.01557","repositories_listed":7,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/analysing-mathematical-reasoning-abilities-of-1#ran","syntology_url":"https://syntology.ai/paper/1904.01557","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01557"}},"official":null}},{"url":"/paper/qwen2-5-technical-report","slug":"qwen2-5-technical-report","title":"Qwen2.5 Technical Report","date":"2024-12-19","arxiv_id":"2412.15115","repositories_listed":6,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/qwen2-5-technical-report#ran","syntology_url":"https://syntology.ai/paper/2412.15115","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.15115"}},"official":{"repos":["qwenlm/qwen2.5"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/mistral-7b","slug":"mistral-7b","title":"Mistral 7B","date":"2023-10-10","arxiv_id":"2310.06825","repositories_listed":6,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mistral-7b#ran","syntology_url":"https://syntology.ai/paper/2310.06825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06825"}},"official":{"repos":["mistralai/mistral-src"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/training-verifiers-to-solve-math-word","slug":"training-verifiers-to-solve-math-word","title":"Training Verifiers to Solve Math Word Problems","date":"2021-10-27","arxiv_id":"2110.14168","repositories_listed":6,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/training-verifiers-to-solve-math-word#ran","syntology_url":"https://syntology.ai/paper/2110.14168","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.14168"}},"official":{"repos":["openai/grade-school-math"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/deepseekmath-pushing-the-limits-of","slug":"deepseekmath-pushing-the-limits-of","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","date":"2024-02-05","arxiv_id":"2402.03300","repositories_listed":5,"syntology":{"n":24,"n_ran":14,"n_constructed":0,"n_ran_checked":3,"n_instrument":11,"n_unverified":10,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 11 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/deepseekmath-pushing-the-limits-of#ran","syntology_url":"https://syntology.ai/paper/2402.03300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03300"}},"official":{"repos":["deepseek-ai/deepseek-math"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/measuring-mathematical-problem-solving-with","slug":"measuring-mathematical-problem-solving-with","title":"Measuring Mathematical Problem Solving With the MATH Dataset","date":"2021-03-05","arxiv_id":"2103.03874","repositories_listed":5,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/measuring-mathematical-problem-solving-with#ran","syntology_url":"https://syntology.ai/paper/2103.03874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.03874"}},"official":{"repos":["hendrycks/math"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/qwen3-technical-report","slug":"qwen3-technical-report","title":"Qwen3 Technical Report","date":"2025-05-14","arxiv_id":"2505.09388","repositories_listed":4,"syntology":null},{"url":"/paper/deepseek-r1-incentivizing-reasoning","slug":"deepseek-r1-incentivizing-reasoning","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","date":"2025-01-22","arxiv_id":"2501.12948","repositories_listed":4,"syntology":null},{"url":"/paper/absolute-zero-reinforced-self-play-reasoning","slug":"absolute-zero-reinforced-self-play-reasoning","title":"Absolute Zero: Reinforced Self-play Reasoning with Zero Data","date":"2025-05-06","arxiv_id":"2505.03335","repositories_listed":3,"syntology":{"n":12,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":6,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/absolute-zero-reinforced-self-play-reasoning#ran","syntology_url":"https://syntology.ai/paper/2505.03335","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.03335"}},"official":{"repos":["LeapLabTHU/Absolute-Zero-Reasoner","volcengine/verl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/eccos-efficient-capability-and-cost","slug":"eccos-efficient-capability-and-cost","title":"OmniRouter: Budget and Performance Controllable Multi-LLM Routing","date":"2025-02-27","arxiv_id":"2502.20576","repositories_listed":3,"syntology":null},{"url":"/paper/reasonflux-hierarchical-llm-reasoning-via","slug":"reasonflux-hierarchical-llm-reasoning-via","title":"ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templates","date":"2025-02-10","arxiv_id":"2502.06772","repositories_listed":3,"syntology":null},{"url":"/paper/limo-less-is-more-for-reasoning","slug":"limo-less-is-more-for-reasoning","title":"LIMO: Less is More for Reasoning","date":"2025-02-05","arxiv_id":"2502.03387","repositories_listed":3,"syntology":null},{"url":"/paper/mavis-mathematical-visual-instruction-tuning","slug":"mavis-mathematical-visual-instruction-tuning","title":"MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine","date":"2024-07-11","arxiv_id":"2407.08739","repositories_listed":3,"syntology":null},{"url":"/paper/mathodyssey-benchmarking-mathematical-problem","slug":"mathodyssey-benchmarking-mathematical-problem","title":"MathOdyssey: Benchmarking Mathematical Problem-Solving Skills in Large Language Models Using Odyssey Math Data","date":"2024-06-26","arxiv_id":"2406.18321","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mathodyssey-benchmarking-mathematical-problem#ran","syntology_url":"https://syntology.ai/paper/2406.18321","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18321"}},"official":null}},{"url":"/paper/knowledge-fusion-of-large-language-models","slug":"knowledge-fusion-of-large-language-models","title":"Knowledge Fusion of Large Language Models","date":"2024-01-19","arxiv_id":"2401.10491","repositories_listed":3,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/knowledge-fusion-of-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2401.10491","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10491"}},"official":{"repos":["fanqiwan/fusellm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/math-shepherd-a-label-free-step-by-step","slug":"math-shepherd-a-label-free-step-by-step","title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations","date":"2023-12-14","arxiv_id":"2312.08935","repositories_listed":3,"syntology":null},{"url":"/paper/factool-factuality-detection-in-generative-ai","slug":"factool-factuality-detection-in-generative-ai","title":"FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios","date":"2023-07-25","arxiv_id":"2307.13528","repositories_listed":3,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/factool-factuality-detection-in-generative-ai#ran","syntology_url":"https://syntology.ai/paper/2307.13528","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.13528"}},"official":{"repos":["gair-nlp/factool"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/self-refine-iterative-refinement-with-self-1","slug":"self-refine-iterative-refinement-with-self-1","title":"Self-Refine: Iterative Refinement with Self-Feedback","date":"2023-03-30","arxiv_id":"2303.17651","repositories_listed":3,"syntology":null},{"url":"/paper/sparks-of-artificial-general-intelligence","slug":"sparks-of-artificial-general-intelligence","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","date":"2023-03-22","arxiv_id":"2303.12712","repositories_listed":3,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/sparks-of-artificial-general-intelligence#ran","syntology_url":"https://syntology.ai/paper/2303.12712","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.12712"}},"official":null}},{"url":"/paper/pal-program-aided-language-models","slug":"pal-program-aided-language-models","title":"PAL: Program-aided Language Models","date":"2022-11-18","arxiv_id":"2211.10435","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pal-program-aided-language-models#ran","syntology_url":"https://syntology.ai/paper/2211.10435","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.10435"}},"official":null}},{"url":"/paper/scaling-language-models-methods-analysis-1","slug":"scaling-language-models-methods-analysis-1","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","date":"2021-12-08","arxiv_id":"2112.11446","repositories_listed":3,"syntology":null},{"url":"/paper/memory-augmented-recursive-neural-networks","slug":"memory-augmented-recursive-neural-networks","title":"Compositional Generalization with Tree Stack Memory Units","date":"2019-11-05","arxiv_id":"1911.01545","repositories_listed":3,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/memory-augmented-recursive-neural-networks#ran","syntology_url":"https://syntology.ai/paper/1911.01545","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.01545"}},"official":{"repos":["ForoughA/recursiveMemNet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/skywork-r1v3-technical-report","slug":"skywork-r1v3-technical-report","title":"Skywork-R1V3 Technical Report","date":"2025-07-08","arxiv_id":"2507.06167","repositories_listed":2,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":2,"n_instrument":9,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":12,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 9 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/skywork-r1v3-technical-report#ran","syntology_url":"https://syntology.ai/paper/2507.06167","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.06167"}},"official":{"repos":["SkyworkAI/Skywork-R1V"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/deeptheorem-advancing-llm-reasoning-for","slug":"deeptheorem-advancing-llm-reasoning-for","title":"DeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement Learning","date":"2025-05-29","arxiv_id":"2505.23754","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deeptheorem-advancing-llm-reasoning-for#ran","syntology_url":"https://syntology.ai/paper/2505.23754","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.23754"}},"official":{"repos":["jiahao004/deeptheorem"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mm-prm-enhancing-multimodal-mathematical","slug":"mm-prm-enhancing-multimodal-mathematical","title":"MM-PRM: Enhancing Multimodal Mathematical Reasoning with Scalable Step-Level Supervision","date":"2025-05-19","arxiv_id":"2505.13427","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mm-prm-enhancing-multimodal-mathematical#ran","syntology_url":"https://syntology.ai/paper/2505.13427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.13427"}},"official":{"repos":["modalminds/mm-prm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/agent-rl-scaling-law-agent-rl-with","slug":"agent-rl-scaling-law-agent-rl-with","title":"Agent RL Scaling Law: Agent RL with Spontaneous Code Execution for Mathematical Problem Solving","date":"2025-05-12","arxiv_id":"2505.07773","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/agent-rl-scaling-law-agent-rl-with#ran","syntology_url":"https://syntology.ai/paper/2505.07773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.07773"}},"official":{"repos":["anonymize-author/agentrl","yyht/openrlhf_async_pipline"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/challenging-the-boundaries-of-reasoning-an","slug":"challenging-the-boundaries-of-reasoning-an","title":"Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models","date":"2025-03-27","arxiv_id":"2503.21380","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/challenging-the-boundaries-of-reasoning-an#ran","syntology_url":"https://syntology.ai/paper/2503.21380","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.21380"}},"official":{"repos":["RUCAIBox/Slow_Thinking_with_LLMs","rucaibox/olymmath"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/self-rewarding-correction-for-mathematical","slug":"self-rewarding-correction-for-mathematical","title":"Self-rewarding correction for mathematical reasoning","date":"2025-02-26","arxiv_id":"2502.19613","repositories_listed":2,"syntology":{"n":16,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":6,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":9,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/self-rewarding-correction-for-mathematical#ran","syntology_url":"https://syntology.ai/paper/2502.19613","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.19613"}},"official":{"repos":["rlhflow/self-rewarding-reasoning-llm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/s1-simple-test-time-scaling","slug":"s1-simple-test-time-scaling","title":"s1: Simple test-time scaling","date":"2025-01-31","arxiv_id":"2501.19393","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/s1-simple-test-time-scaling#ran","syntology_url":"https://syntology.ai/paper/2501.19393","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.19393"}},"official":{"repos":["simplescaling/s1"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/search-o1-agentic-search-enhanced-large","slug":"search-o1-agentic-search-enhanced-large","title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","date":"2025-01-09","arxiv_id":"2501.05366","repositories_listed":2,"syntology":null},{"url":"/paper/offline-reinforcement-learning-for-llm-multi","slug":"offline-reinforcement-learning-for-llm-multi","title":"Offline Reinforcement Learning for LLM Multi-Step Reasoning","date":"2024-12-20","arxiv_id":"2412.16145","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/offline-reinforcement-learning-for-llm-multi#ran","syntology_url":"https://syntology.ai/paper/2412.16145","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.16145"}},"official":{"repos":["jwhj/oreo"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mc-nest-enhancing-mathematical-reasoning-in","slug":"mc-nest-enhancing-mathematical-reasoning-in","title":"MC-NEST -- Enhancing Mathematical Reasoning in Large Language Models with a Monte Carlo Nash Equilibrium Self-Refine Tree","date":"2024-11-23","arxiv_id":"2411.15645","repositories_listed":2,"syntology":null},{"url":"/paper/procedural-knowledge-in-pretraining-drives","slug":"procedural-knowledge-in-pretraining-drives","title":"Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models","date":"2024-11-19","arxiv_id":"2411.12580","repositories_listed":2,"syntology":null},{"url":"/paper/technical-report-enhancing-llm-reasoning-with","slug":"technical-report-enhancing-llm-reasoning-with","title":"Enhancing LLM Reasoning with Reward-guided Tree Search","date":"2024-11-18","arxiv_id":"2411.11694","repositories_listed":2,"syntology":null},{"url":"/paper/mod-a-distribution-based-approach-for-merging","slug":"mod-a-distribution-based-approach-for-merging","title":"MoD: A Distribution-Based Approach for Merging Large Language Models","date":"2024-11-01","arxiv_id":"2411.00406","repositories_listed":2,"syntology":null},{"url":"/paper/supercorrect-supervising-and-correcting","slug":"supercorrect-supervising-and-correcting","title":"SuperCorrect: Supervising and Correcting Language Models with Error-Driven Insights","date":"2024-10-11","arxiv_id":"2410.09008","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/supercorrect-supervising-and-correcting#ran","syntology_url":"https://syntology.ai/paper/2410.09008","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09008"}},"official":{"repos":["yangling0818/supercorrect-llm"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/omni-math-a-universal-olympiad-level","slug":"omni-math-a-universal-olympiad-level","title":"Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models","date":"2024-10-10","arxiv_id":"2410.07985","repositories_listed":2,"syntology":{"n":19,"n_ran":13,"n_constructed":0,"n_ran_checked":6,"n_instrument":7,"n_unverified":6,"n_honours":1,"n_violates":5,"n_no_contract":0,"n_pointer_only":19,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 5 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/omni-math-a-universal-olympiad-level#ran","syntology_url":"https://syntology.ai/paper/2410.07985","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07985"}},"official":{"repos":["kbsdjames/omni-math","kbsdjames/omni-math-rule"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/gsm-symbolic-understanding-the-limitations-of","slug":"gsm-symbolic-understanding-the-limitations-of","title":"GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models","date":"2024-10-07","arxiv_id":"2410.05229","repositories_listed":2,"syntology":null},{"url":"/paper/godel-agent-a-self-referential-agent","slug":"godel-agent-a-self-referential-agent","title":"Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement","date":"2024-10-06","arxiv_id":"2410.04444","repositories_listed":2,"syntology":null},{"url":"/paper/codeplan-unlocking-reasoning-potential-in","slug":"codeplan-unlocking-reasoning-potential-in","title":"Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planning","date":"2024-09-19","arxiv_id":"2409.12452","repositories_listed":2,"syntology":null},{"url":"/paper/seallms-3-open-foundation-and-chat","slug":"seallms-3-open-foundation-and-chat","title":"SeaLLMs 3: Open Foundation and Chat Multilingual Large Language Models for Southeast Asian Languages","date":"2024-07-29","arxiv_id":"2407.19672","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/seallms-3-open-foundation-and-chat#ran","syntology_url":"https://syntology.ai/paper/2407.19672","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.19672"}},"official":{"repos":["DAMO-NLP-SG/SeaExam"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/needlebench-can-llms-do-retrieval-and","slug":"needlebench-can-llms-do-retrieval-and","title":"NeedleBench: Can LLMs Do Retrieval and Reasoning in Information-Dense Context?","date":"2024-07-16","arxiv_id":"2407.11963","repositories_listed":2,"syntology":null},{"url":"/paper/buffer-of-thoughts-thought-augmented","slug":"buffer-of-thoughts-thought-augmented","title":"Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models","date":"2024-06-06","arxiv_id":"2406.04271","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_constructed":1,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/buffer-of-thoughts-thought-augmented#ran","syntology_url":"https://syntology.ai/paper/2406.04271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04271"}},"official":{"repos":["yangling0818/buffer-of-thought-llm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/process-driven-autoformalization-in-lean-4","slug":"process-driven-autoformalization-in-lean-4","title":"Process-Driven Autoformalization in Lean 4","date":"2024-06-04","arxiv_id":"2406.01940","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":0,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/process-driven-autoformalization-in-lean-4#ran","syntology_url":"https://syntology.ai/paper/2406.01940","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.01940"}},"official":{"repos":["rookie-joe/pda"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/automathtext-autonomous-data-selection-with","slug":"automathtext-autonomous-data-selection-with","title":"Autonomous Data Selection with Zero-shot Generative Classifiers for Mathematical Texts","date":"2024-02-12","arxiv_id":"2402.07625","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/automathtext-autonomous-data-selection-with#ran","syntology_url":"https://syntology.ai/paper/2402.07625","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07625"}},"official":{"repos":["hiyouga/llama-factory","yifanzhang-pro/automathtext"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mario-math-reasoning-with-code-interpreter","slug":"mario-math-reasoning-with-code-interpreter","title":"MARIO: MAth Reasoning with code Interpreter Output -- A Reproducible Pipeline","date":"2024-01-16","arxiv_id":"2401.08190","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mario-math-reasoning-with-code-interpreter#ran","syntology_url":"https://syntology.ai/paper/2401.08190","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.08190"}},"official":{"repos":["mario-math-reasoning/mario"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/breaking-language-barriers-in-multilingual","slug":"breaking-language-barriers-in-multilingual","title":"Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and Observations","date":"2023-10-31","arxiv_id":"2310.20246","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/breaking-language-barriers-in-multilingual#ran","syntology_url":"https://syntology.ai/paper/2310.20246","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.20246"}},"official":{"repos":["microsoft/MathOctopus"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/how-abilities-in-large-language-models-are","slug":"how-abilities-in-large-language-models-are","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","date":"2023-10-09","arxiv_id":"2310.05492","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/how-abilities-in-large-language-models-are#ran","syntology_url":"https://syntology.ai/paper/2310.05492","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.05492"}},"official":{"repos":["ofa-sys/gsm8k-screl"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/snip-bridging-mathematical-symbolic-and","slug":"snip-bridging-mathematical-symbolic-and","title":"SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-training","date":"2023-10-03","arxiv_id":"2310.02227","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/snip-bridging-mathematical-symbolic-and#ran","syntology_url":"https://syntology.ai/paper/2310.02227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.02227"}},"official":{"repos":["deep-symbolic-mathematics/Multimodal-Math-Pretraining","deep-symbolic-mathematics/Multimodal-Symbolic-Regression"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/craft-customizing-llms-by-creating-and","slug":"craft-customizing-llms-by-creating-and","title":"CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets","date":"2023-09-29","arxiv_id":"2309.17428","repositories_listed":2,"syntology":{"n":5,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"0 ran · 5 unverified","sample_list":"/paper/craft-customizing-llms-by-creating-and#ran","syntology_url":"https://syntology.ai/paper/2309.17428","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17428"}},"official":{"repos":["lifan-yuan/craft"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":[]}}},{"url":"/paper/mathematical-capabilities-of-chatgpt-1","slug":"mathematical-capabilities-of-chatgpt-1","title":"Mathematical Capabilities of ChatGPT","date":"2023-01-31","arxiv_id":"2301.13867","repositories_listed":2,"syntology":null},{"url":"/paper/reasoning-with-language-model-prompting-a","slug":"reasoning-with-language-model-prompting-a","title":"Reasoning with Language Model Prompting: A Survey","date":"2022-12-19","arxiv_id":"2212.09597","repositories_listed":2,"syntology":null},{"url":"/paper/unigeo-unifying-geometry-logical-reasoning","slug":"unigeo-unifying-geometry-logical-reasoning","title":"UniGeo: Unifying Geometry Logical Reasoning via Reformulating Mathematical Expression","date":"2022-12-06","arxiv_id":"2212.02746","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/unigeo-unifying-geometry-logical-reasoning#ran","syntology_url":"https://syntology.ai/paper/2212.02746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.02746"}},"official":{"repos":["chen-judge/unigeo"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/language-models-are-greedy-reasoners-a","slug":"language-models-are-greedy-reasoners-a","title":"Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought","date":"2022-10-03","arxiv_id":"2210.01240","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/language-models-are-greedy-reasoners-a#ran","syntology_url":"https://syntology.ai/paper/2210.01240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.01240"}},"official":{"repos":["asaparov/prontoqa"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/dynamic-prompt-learning-via-policy-gradient","slug":"dynamic-prompt-learning-via-policy-gradient","title":"Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning","date":"2022-09-29","arxiv_id":"2209.14610","repositories_listed":2,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/dynamic-prompt-learning-via-policy-gradient#ran","syntology_url":"https://syntology.ai/paper/2209.14610","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.14610"}},"official":null}},{"url":"/paper/training-compute-optimal-large-language","slug":"training-compute-optimal-large-language","title":"Training Compute-Optimal Large Language Models","date":"2022-03-29","arxiv_id":"2203.15556","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":3,"n_ran_checked":5,"n_instrument":3,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"8 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/training-compute-optimal-large-language#ran","syntology_url":"https://syntology.ai/paper/2203.15556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15556"}},"official":null}},{"url":"/paper/modelling-high-level-mathematical-reasoning","slug":"modelling-high-level-mathematical-reasoning","title":"IsarStep: a Benchmark for High-level Mathematical Reasoning","date":"2020-06-13","arxiv_id":"2006.09265","repositories_listed":2,"syntology":{"n":8,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/modelling-high-level-mathematical-reasoning#ran","syntology_url":"https://syntology.ai/paper/2006.09265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.09265"}},"official":null}},{"url":"/paper/reasoning-or-memorization-unreliable-results","slug":"reasoning-or-memorization-unreliable-results","title":"Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination","date":"2025-07-14","arxiv_id":"2507.10532","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/reasoning-or-memorization-unreliable-results#ran","syntology_url":"https://syntology.ai/paper/2507.10532","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.10532"}},"official":{"repos":["wumingqi/LLM-Math-Evaluation"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-practical-two-stage-recipe-for-mathematical","slug":"a-practical-two-stage-recipe-for-mathematical","title":"A Practical Two-Stage Recipe for Mathematical LLMs: Maximizing Accuracy with SFT and Efficiency with Reinforcement Learning","date":"2025-07-11","arxiv_id":"2507.08267","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-practical-two-stage-recipe-for-mathematical#ran","syntology_url":"https://syntology.ai/paper/2507.08267","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.08267"}},"official":{"repos":["analokmaus/kaggle-aimo2-fast-math-r1"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/criticlean-critic-guided-reinforcement","slug":"criticlean-critic-guided-reinforcement","title":"CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization","date":"2025-07-08","arxiv_id":"2507.06181","repositories_listed":1,"syntology":null},{"url":"/paper/confucius3-math-a-lightweight-high","slug":"confucius3-math-a-lightweight-high","title":"Confucius3-Math: A Lightweight High-Performance Reasoning LLM for Chinese K-12 Mathematics Learning","date":"2025-06-23","arxiv_id":"2506.18330","repositories_listed":1,"syntology":null},{"url":"/paper/xolver-multi-agent-reasoning-with-holistic","slug":"xolver-multi-agent-reasoning-with-holistic","title":"Xolver: Multi-Agent Reasoning with Holistic Experience Learning Just Like an Olympiad Team","date":"2025-06-17","arxiv_id":"2506.14234","repositories_listed":1,"syntology":null},{"url":"/paper/discovering-hierarchical-latent-capabilities","slug":"discovering-hierarchical-latent-capabilities","title":"Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning","date":"2025-06-12","arxiv_id":"2506.10378","repositories_listed":1,"syntology":null},{"url":"/paper/neuralnexus-at-bea-2025-shared-task-retrieval","slug":"neuralnexus-at-bea-2025-shared-task-retrieval","title":"NeuralNexus at BEA 2025 Shared Task: Retrieval-Augmented Prompting for Mistake Identification in AI Tutors","date":"2025-06-12","arxiv_id":"2506.10627","repositories_listed":1,"syntology":null},{"url":"/paper/spurious-rewards-rethinking-training-signals","slug":"spurious-rewards-rethinking-training-signals","title":"Spurious Rewards: Rethinking Training Signals in RLVR","date":"2025-06-12","arxiv_id":"2506.10947","repositories_listed":1,"syntology":null},{"url":"/paper/cort-code-integrated-reasoning-within","slug":"cort-code-integrated-reasoning-within","title":"CoRT: Code-integrated Reasoning within Thinking","date":"2025-06-11","arxiv_id":"2506.09820","repositories_listed":1,"syntology":null},{"url":"/paper/repo-replay-enhanced-policy-optimization","slug":"repo-replay-enhanced-policy-optimization","title":"RePO: Replay-Enhanced Policy Optimization","date":"2025-06-11","arxiv_id":"2506.09340","repositories_listed":1,"syntology":null},{"url":"/paper/vision-matters-simple-visual-perturbations","slug":"vision-matters-simple-visual-perturbations","title":"Vision Matters: Simple Visual Perturbations Can Boost Multimodal Math Reasoning","date":"2025-06-11","arxiv_id":"2506.09736","repositories_listed":1,"syntology":null},{"url":"/paper/can-a-gamer-train-a-mathematical-reasoning","slug":"can-a-gamer-train-a-mathematical-reasoning","title":"Can A Gamer Train A Mathematical Reasoning Model?","date":"2025-06-10","arxiv_id":"2506.08935","repositories_listed":1,"syntology":null},{"url":"/paper/vrest-enhancing-reasoning-in-large-vision","slug":"vrest-enhancing-reasoning-in-large-vision","title":"VReST: Enhancing Reasoning in Large Vision-Language Models through Tree Search and Self-Reward Mechanism","date":"2025-06-10","arxiv_id":"2506.08691","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":4,"n_instrument":8,"n_unverified":3,"n_honours":3,"n_violates":1,"n_no_contract":0,"n_pointer_only":15,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 1 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/vrest-enhancing-reasoning-in-large-vision#ran","syntology_url":"https://syntology.ai/paper/2506.08691","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.08691"}},"official":{"repos":["garyjiajia/vrest"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/wethink-toward-general-purpose-vision","slug":"wethink-toward-general-purpose-vision","title":"WeThink: Toward General-purpose Vision-Language Reasoning via Reinforcement Learning","date":"2025-06-09","arxiv_id":"2506.07905","repositories_listed":1,"syntology":null},{"url":"/paper/logicpuzzlerl-cultivating-robust-mathematical","slug":"logicpuzzlerl-cultivating-robust-mathematical","title":"LogicPuzzleRL: Cultivating Robust Mathematical Reasoning in LLMs via Reinforcement Learning","date":"2025-06-05","arxiv_id":"2506.04821","repositories_listed":1,"syntology":null},{"url":"/paper/mathematical-reasoning-for-unmanned-aerial","slug":"mathematical-reasoning-for-unmanned-aerial","title":"Mathematical Reasoning for Unmanned Aerial Vehicles: A RAG-Based Approach for Complex Arithmetic Reasoning","date":"2025-06-05","arxiv_id":"2506.04998","repositories_listed":1,"syntology":null},{"url":"/paper/mint-cot-enabling-interleaved-visual-tokens","slug":"mint-cot-enabling-interleaved-visual-tokens","title":"MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning","date":"2025-06-05","arxiv_id":"2506.05331","repositories_listed":1,"syntology":null},{"url":"/paper/safe-enhancing-mathematical-reasoning-in","slug":"safe-enhancing-mathematical-reasoning-in","title":"Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification","date":"2025-06-05","arxiv_id":"2506.04592","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-graph-pruning-for-multi-agent","slug":"adaptive-graph-pruning-for-multi-agent","title":"Adaptive Graph Pruning for Multi-Agent Communication","date":"2025-06-03","arxiv_id":"2506.02951","repositories_listed":1,"syntology":null},{"url":"/paper/the-surprising-effectiveness-of-negative","slug":"the-surprising-effectiveness-of-negative","title":"The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning","date":"2025-06-02","arxiv_id":"2506.01347","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/the-surprising-effectiveness-of-negative#ran","syntology_url":"https://syntology.ai/paper/2506.01347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.01347"}},"official":{"repos":["tianhongzxy/rlvr-decomposed"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/speculative-reward-model-boosts-decision","slug":"speculative-reward-model-boosts-decision","title":"Speculative Reward Model Boosts Decision Making Ability of LLMs Cost-Effectively","date":"2025-05-31","arxiv_id":"2506.00396","repositories_listed":1,"syntology":null},{"url":"/paper/harnessing-negative-signals-reinforcement","slug":"harnessing-negative-signals-reinforcement","title":"Harnessing Negative Signals: Reinforcement Distillation from Teacher Data for LLM Reasoning","date":"2025-05-30","arxiv_id":"2505.24850","repositories_listed":1,"syntology":null},{"url":"/paper/r-kv-redundancy-aware-kv-cache-compression","slug":"r-kv-redundancy-aware-kv-cache-compression","title":"R-KV: Redundancy-aware KV Cache Compression for Training-Free Reasoning Models Acceleration","date":"2025-05-30","arxiv_id":"2505.24133","repositories_listed":1,"syntology":null},{"url":"/paper/rmoa-optimizing-mixture-of-agents-through","slug":"rmoa-optimizing-mixture-of-agents-through","title":"RMoA: Optimizing Mixture-of-Agents through Diversity Maximization and Residual Compensation","date":"2025-05-30","arxiv_id":"2505.24442","repositories_listed":1,"syntology":null},{"url":"/paper/the-hallucination-dilemma-factuality-aware","slug":"the-hallucination-dilemma-factuality-aware","title":"The Hallucination Dilemma: Factuality-Aware Reinforcement Learning for Large Reasoning Models","date":"2025-05-30","arxiv_id":"2505.24630","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/the-hallucination-dilemma-factuality-aware#ran","syntology_url":"https://syntology.ai/paper/2505.24630","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.24630"}},"official":{"repos":["nusnlp/fspo"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/towards-effective-code-integrated-reasoning","slug":"towards-effective-code-integrated-reasoning","title":"Towards Effective Code-Integrated Reasoning","date":"2025-05-30","arxiv_id":"2505.24480","repositories_listed":1,"syntology":null},{"url":"/paper/unifying-language-agent-algorithms-with-graph","slug":"unifying-language-agent-algorithms-with-graph","title":"Unifying Language Agent Algorithms with Graph-based Orchestration Engine for Reproducible Agent Research","date":"2025-05-30","arxiv_id":"2505.24354","repositories_listed":1,"syntology":null},{"url":"/paper/discriminative-policy-optimization-for-token","slug":"discriminative-policy-optimization-for-token","title":"Discriminative Policy Optimization for Token-Level Reward Models","date":"2025-05-29","arxiv_id":"2505.23363","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/discriminative-policy-optimization-for-token#ran","syntology_url":"https://syntology.ai/paper/2505.23363","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.23363"}},"official":{"repos":["homzer/q-rm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/matharena-evaluating-llms-on-uncontaminated","slug":"matharena-evaluating-llms-on-uncontaminated","title":"MathArena: Evaluating LLMs on Uncontaminated Math Competitions","date":"2025-05-29","arxiv_id":"2505.23281","repositories_listed":1,"syntology":{"n":19,"n_ran":15,"n_constructed":0,"n_ran_checked":13,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/matharena-evaluating-llms-on-uncontaminated#ran","syntology_url":"https://syntology.ai/paper/2505.23281","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.23281"}},"official":{"repos":["eth-sri/matharena"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/on-policy-rl-with-optimal-reward-baseline","slug":"on-policy-rl-with-optimal-reward-baseline","title":"On-Policy RL with Optimal Reward Baseline","date":"2025-05-29","arxiv_id":"2505.23585","repositories_listed":1,"syntology":null},{"url":"/paper/probability-consistent-preference","slug":"probability-consistent-preference","title":"Probability-Consistent Preference Optimization for Enhanced LLM Reasoning","date":"2025-05-29","arxiv_id":"2505.23540","repositories_listed":1,"syntology":null},{"url":"/paper/scaling-up-the-think-aloud-method","slug":"scaling-up-the-think-aloud-method","title":"Scaling up the think-aloud method","date":"2025-05-29","arxiv_id":"2505.23931","repositories_listed":1,"syntology":null},{"url":"/paper/decomposing-elements-of-problem-solving-what","slug":"decomposing-elements-of-problem-solving-what","title":"Decomposing Elements of Problem Solving: What \"Math\" Does RL Teach?","date":"2025-05-28","arxiv_id":"2505.22756","repositories_listed":1,"syntology":null},{"url":"/paper/vision-language-action-model-with-open-world","slug":"vision-language-action-model-with-open-world","title":"ChatVLA-2: Vision-Language-Action Model with Open-World Embodied Reasoning from Pretrained Knowledge","date":"2025-05-28","arxiv_id":"2505.21906","repositories_listed":1,"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":2,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/vision-language-action-model-with-open-world#ran","syntology_url":"https://syntology.ai/paper/2505.21906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.21906"}},"official":null}},{"url":"/paper/real-prover-retrieval-augmented-lean-prover","slug":"real-prover-retrieval-augmented-lean-prover","title":"REAL-Prover: Retrieval Augmented Lean Prover for Mathematical Reasoning","date":"2025-05-27","arxiv_id":"2505.20613","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcing-general-reasoning-without","slug":"reinforcing-general-reasoning-without","title":"Reinforcing General Reasoning without Verifiers","date":"2025-05-27","arxiv_id":"2505.21493","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/reinforcing-general-reasoning-without#ran","syntology_url":"https://syntology.ai/paper/2505.21493","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.21493"}},"official":{"repos":["sail-sg/verifree"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/error-typing-for-smarter-rewards-improving","slug":"error-typing-for-smarter-rewards-improving","title":"Error Typing for Smarter Rewards: Improving Process Reward Models with Error-Aware Hierarchical Supervision","date":"2025-05-26","arxiv_id":"2505.19706","repositories_listed":1,"syntology":null},{"url":"/paper/limopro-reasoning-refinement-for-efficient","slug":"limopro-reasoning-refinement-for-efficient","title":"LIMOPro: Reasoning Refinement for Efficient and Effective Test-time Scaling","date":"2025-05-25","arxiv_id":"2505.19187","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/limopro-reasoning-refinement-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2505.19187","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19187"}},"official":{"repos":["gair-nlp/limopro"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/mmath-a-multilingual-benchmark-for","slug":"mmath-a-multilingual-benchmark-for","title":"MMATH: A Multilingual Benchmark for Mathematical Reasoning","date":"2025-05-25","arxiv_id":"2505.19126","repositories_listed":1,"syntology":null},{"url":"/paper/situatedthinker-grounding-llm-reasoning-with","slug":"situatedthinker-grounding-llm-reasoning-with","title":"SituatedThinker: Grounding LLM Reasoning with Real-World through Situated Thinking","date":"2025-05-25","arxiv_id":"2505.19300","repositories_listed":1,"syntology":null},{"url":"/paper/universal-reasoner-a-single-composable-plug","slug":"universal-reasoner-a-single-composable-plug","title":"Universal Reasoner: A Single, Composable Plug-and-Play Reasoner for Frozen LLMs","date":"2025-05-25","arxiv_id":"2505.19075","repositories_listed":1,"syntology":null},{"url":"/paper/enumerate-conjecture-prove-formally-solving","slug":"enumerate-conjecture-prove-formally-solving","title":"Enumerate-Conjecture-Prove: Formally Solving Answer-Construction Problems in Math Competitions","date":"2025-05-24","arxiv_id":"2505.18492","repositories_listed":1,"syntology":null}],"syntology_records":48,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":68,"papers_placed":6,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/mathematical-reasoning-on-aime24","since_archive":"/sota/mathematical-reasoning-on-aime24#since-judged","papers_judged":42,"placed":2},{"leaderboard":"/sota/mathematical-reasoning-on-pgps9k","since_archive":"/sota/mathematical-reasoning-on-pgps9k#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/mathematical-reasoning-on-amc23","since_archive":"/sota/mathematical-reasoning-on-amc23#since-judged","papers_judged":17,"placed":0},{"leaderboard":"/sota/mathematical-reasoning-on-geoqa","since_archive":"/sota/mathematical-reasoning-on-geoqa#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/mathematical-reasoning-on-math500","since_archive":"/sota/mathematical-reasoning-on-math500#since-judged","papers_judged":48,"placed":6}]},"papers_where_code_ran":197,"papers_where_code_ran_first_page":"/task/mathematical-reasoning/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":9,"url":"/task/mathematical-reasoning/papers/2","json":"/task/mathematical-reasoning/papers/2.json","rows":100},{"order":"archive","page":3,"of":9,"url":"/task/mathematical-reasoning/papers/3","json":"/task/mathematical-reasoning/papers/3.json","rows":100},{"order":"archive","page":4,"of":9,"url":"/task/mathematical-reasoning/papers/4","json":"/task/mathematical-reasoning/papers/4.json","rows":100},{"order":"archive","page":5,"of":9,"url":"/task/mathematical-reasoning/papers/5","json":"/task/mathematical-reasoning/papers/5.json","rows":100},{"order":"archive","page":6,"of":9,"url":"/task/mathematical-reasoning/papers/6","json":"/task/mathematical-reasoning/papers/6.json","rows":100},{"order":"archive","page":7,"of":9,"url":"/task/mathematical-reasoning/papers/7","json":"/task/mathematical-reasoning/papers/7.json","rows":100},{"order":"archive","page":8,"of":9,"url":"/task/mathematical-reasoning/papers/8","json":"/task/mathematical-reasoning/papers/8.json","rows":100},{"order":"archive","page":9,"of":9,"url":"/task/mathematical-reasoning/papers/9","json":"/task/mathematical-reasoning/papers/9.json","rows":5},{"order":"ran","page":1,"of":2,"url":"/task/mathematical-reasoning/papers/ran/1","json":"/task/mathematical-reasoning/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":2,"url":"/task/mathematical-reasoning/papers/ran/2","json":"/task/mathematical-reasoning/papers/ran/2.json","rows":97}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"43594e977a21d5f0df7733fbccd1b875c6fadcdfbb1bbec73b369d0134514425","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}