{"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-problem-solving/papers/ran/1","list_of":"/task/mathematical-problem-solving","task":"Mathematical Problem-Solving","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","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.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":1,"pages_in_order":1,"rows_per_page":100,"rows":[1,25],"of":25,"counts":{"archive_papers_tagged":106,"with_a_code_link":55,"where_syntology_ran_a_sample":25,"not_listed_spam_title":0,"listed":106,"listed_where_code_ran":25,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":18,"every_run_a_failure_of_syntologys_instrument":7,"listed_with_a_run_with_no_instrument_failure":18,"listed_every_run_a_failure_of_syntologys_instrument":7,"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"},"first_page":"/task/mathematical-problem-solving/papers/ran/1","prev":null,"next":null,"papers":[{"url":"/paper/evoagentx-an-automated-framework-for-evolving","slug":"evoagentx-an-automated-framework-for-evolving","title":"EvoAgentX: An Automated Framework for Evolving Agentic Workflows","date":"2025-07-04","arxiv_id":"2507.03616","repositories_listed":1,"syntology":{"n":20,"n_ran":19,"n_constructed":0,"n_ran_checked":19,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":19,"n_pointer_only":16,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/evoagentx-an-automated-framework-for-evolving#ran","syntology_url":"https://syntology.ai/paper/2507.03616","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.03616"}},"official":{"repos":["evoagentx/evoagentx"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/locationreasoner-evaluating-llms-on-real","slug":"locationreasoner-evaluating-llms-on-real","title":"LocationReasoner: Evaluating LLMs on Real-World Site Selection Reasoning","date":"2025-06-16","arxiv_id":"2506.13841","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":11,"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) · 2 unverified","sample_list":"/paper/locationreasoner-evaluating-llms-on-real#ran","syntology_url":"https://syntology.ai/paper/2506.13841","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.13841"}},"official":{"repos":["miho-koda/locationreasoner"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/sws-self-aware-weakness-driven-problem","slug":"sws-self-aware-weakness-driven-problem","title":"SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning","date":"2025-06-10","arxiv_id":"2506.08989","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/sws-self-aware-weakness-driven-problem#ran","syntology_url":"https://syntology.ai/paper/2506.08989","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.08989"}},"official":{"repos":["mastervito/sws"],"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/solving-inequality-proofs-with-large-language","slug":"solving-inequality-proofs-with-large-language","title":"Solving Inequality Proofs with Large Language Models","date":"2025-06-09","arxiv_id":"2506.07927","repositories_listed":2,"syntology":{"n":10,"n_ran":9,"n_constructed":1,"n_ran_checked":5,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":4,"n_no_contract":1,"n_pointer_only":0,"phrase":"9 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 4 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/solving-inequality-proofs-with-large-language#ran","syntology_url":"https://syntology.ai/paper/2506.07927","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.07927"}},"official":{"repos":["lupantech/ineqmath"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":1,"n_ran_no_instrument_failure":5,"n_unverified":1,"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/entropy-based-adaptive-weighting-for-self","slug":"entropy-based-adaptive-weighting-for-self","title":"Entropy-Based Adaptive Weighting for Self-Training","date":"2025-03-31","arxiv_id":"2503.23913","repositories_listed":1,"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/entropy-based-adaptive-weighting-for-self#ran","syntology_url":"https://syntology.ai/paper/2503.23913","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.23913"}},"official":{"repos":["mandyyyyii/east"],"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/mathfusion-enhancing-mathematic-problem","slug":"mathfusion-enhancing-mathematic-problem","title":"MathFusion: Enhancing Mathematic Problem-solving of LLM through Instruction Fusion","date":"2025-03-20","arxiv_id":"2503.16212","repositories_listed":1,"syntology":{"n":18,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":3,"phrase":"13 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; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/mathfusion-enhancing-mathematic-problem#ran","syntology_url":"https://syntology.ai/paper/2503.16212","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.16212"}},"official":{"repos":["qizhipei/mathfusion"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/forgotten-polygons-multimodal-large-language","slug":"forgotten-polygons-multimodal-large-language","title":"Forgotten Polygons: Multimodal Large Language Models are Shape-Blind","date":"2025-02-21","arxiv_id":"2502.15969","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/forgotten-polygons-multimodal-large-language#ran","syntology_url":"https://syntology.ai/paper/2502.15969","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.15969"}},"official":{"repos":["rsinghlab/shape-blind"],"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","unlocated"]}}},{"url":"/paper/voxeval-benchmarking-the-knowledge","slug":"voxeval-benchmarking-the-knowledge","title":"VoxEval: Benchmarking the Knowledge Understanding Capabilities of End-to-End Spoken Language Models","date":"2025-01-09","arxiv_id":"2501.04962","repositories_listed":1,"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":2,"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/voxeval-benchmarking-the-knowledge#ran","syntology_url":"https://syntology.ai/paper/2501.04962","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.04962"}},"official":{"repos":["dreamtheater123/voxeval"],"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/training-and-evaluating-language-models-with","slug":"training-and-evaluating-language-models-with","title":"Training and Evaluating Language Models with Template-based Data Generation","date":"2024-11-27","arxiv_id":"2411.18104","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"3 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/training-and-evaluating-language-models-with#ran","syntology_url":"https://syntology.ai/paper/2411.18104","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.18104"}},"official":{"repos":["iiis-ai/templatemath"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/llama-berry-pairwise-optimization-for-o1-like","slug":"llama-berry-pairwise-optimization-for-o1-like","title":"LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning","date":"2024-10-03","arxiv_id":"2410.02884","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":1,"n_no_contract":0,"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, 1 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/llama-berry-pairwise-optimization-for-o1-like#ran","syntology_url":"https://syntology.ai/paper/2410.02884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02884"}},"official":null}},{"url":"/paper/mathcamps-fine-grained-synthesis-of","slug":"mathcamps-fine-grained-synthesis-of","title":"MathCAMPS: Fine-grained Synthesis of Mathematical Problems From Human Curricula","date":"2024-07-01","arxiv_id":"2407.00900","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mathcamps-fine-grained-synthesis-of#ran","syntology_url":"https://syntology.ai/paper/2407.00900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.00900"}},"official":{"repos":["gpoesia/mathcamps"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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/math-llava-bootstrapping-mathematical","slug":"math-llava-bootstrapping-mathematical","title":"Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models","date":"2024-06-25","arxiv_id":"2406.17294","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/math-llava-bootstrapping-mathematical#ran","syntology_url":"https://syntology.ai/paper/2406.17294","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17294"}},"official":{"repos":["hzq950419/math-llava"],"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/dart-math-difficulty-aware-rejection-tuning-1","slug":"dart-math-difficulty-aware-rejection-tuning-1","title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","date":"2024-06-18","arxiv_id":"2407.13690","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"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) · 2 unverified","sample_list":"/paper/dart-math-difficulty-aware-rejection-tuning-1#ran","syntology_url":"https://syntology.ai/paper/2407.13690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.13690"}},"official":{"repos":["hkust-nlp/dart-math"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/mathchat-benchmarking-mathematical-reasoning","slug":"mathchat-benchmarking-mathematical-reasoning","title":"MathChat: Benchmarking Mathematical Reasoning and Instruction Following in Multi-Turn Interactions","date":"2024-05-29","arxiv_id":"2405.19444","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":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/mathchat-benchmarking-mathematical-reasoning#ran","syntology_url":"https://syntology.ai/paper/2405.19444","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19444"}},"official":{"repos":["zhenwen-nlp/mathchat"],"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/mathify-evaluating-large-language-models-on","slug":"mathify-evaluating-large-language-models-on","title":"Mathify: Evaluating Large Language Models on Mathematical Problem Solving Tasks","date":"2024-04-19","arxiv_id":"2404.13099","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mathify-evaluating-large-language-models-on#ran","syntology_url":"https://syntology.ai/paper/2404.13099","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.13099"}},"official":{"repos":["midas-research/mathify"],"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"]}}},{"url":"/paper/chatglm-math-improving-math-problem-solving","slug":"chatglm-math-improving-math-problem-solving","title":"ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline","date":"2024-04-03","arxiv_id":"2404.02893","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":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) · 3 unverified","sample_list":"/paper/chatglm-math-improving-math-problem-solving#ran","syntology_url":"https://syntology.ai/paper/2404.02893","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.02893"}},"official":{"repos":["thudm/chatglm-math"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/can-llms-master-math-investigating-large","slug":"can-llms-master-math-investigating-large","title":"Can LLMs Master Math? Investigating Large Language Models on Math Stack Exchange","date":"2024-03-30","arxiv_id":"2404.00344","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/can-llms-master-math-investigating-large#ran","syntology_url":"https://syntology.ai/paper/2404.00344","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00344"}},"official":{"repos":["gipplab/llm-investig-mathstackexchange"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/smalltolarge-s2l-scalable-data-selection-for","slug":"smalltolarge-s2l-scalable-data-selection-for","title":"SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models","date":"2024-03-12","arxiv_id":"2403.07384","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":3,"phrase":"4 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/smalltolarge-s2l-scalable-data-selection-for#ran","syntology_url":"https://syntology.ai/paper/2403.07384","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07384"}},"official":{"repos":["bigml-cs-ucla/s2l"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/g-llava-solving-geometric-problem-with-multi","slug":"g-llava-solving-geometric-problem-with-multi","title":"G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model","date":"2023-12-18","arxiv_id":"2312.11370","repositories_listed":3,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"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) · 2 unverified","sample_list":"/paper/g-llava-solving-geometric-problem-with-multi#ran","syntology_url":"https://syntology.ai/paper/2312.11370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.11370"}},"official":{"repos":["pipilurj/g-llava"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/data-contamination-through-the-lens-of-time","slug":"data-contamination-through-the-lens-of-time","title":"Data Contamination Through the Lens of Time","date":"2023-10-16","arxiv_id":"2310.10628","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/data-contamination-through-the-lens-of-time#ran","syntology_url":"https://syntology.ai/paper/2310.10628","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.10628"}},"official":{"repos":["abacusai/to-the-cutoff"],"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/tora-a-tool-integrated-reasoning-agent-for","slug":"tora-a-tool-integrated-reasoning-agent-for","title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","date":"2023-09-29","arxiv_id":"2309.17452","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":9,"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) · 1 unverified","sample_list":"/paper/tora-a-tool-integrated-reasoning-agent-for#ran","syntology_url":"https://syntology.ai/paper/2309.17452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17452"}},"official":{"repos":["microsoft/tora"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/abstractors-transformer-modules-for-symbolic","slug":"abstractors-transformer-modules-for-symbolic","title":"Abstractors and relational cross-attention: An inductive bias for explicit relational reasoning in Transformers","date":"2023-04-01","arxiv_id":"2304.00195","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":5,"n_ran_checked":6,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":12,"phrase":"9 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/abstractors-transformer-modules-for-symbolic#ran","syntology_url":"https://syntology.ai/paper/2304.00195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.00195"}},"official":{"repos":["awni00/abstractor"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":5,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["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"]}}}],"record_sha256":"32b7f1b48e6e0e7298a7a4268433ad6a5f4d37fb29103fd6c345f4fba2c9d0bf","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}