{"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/papers/ran/2","list_of":"/task/mathematical-reasoning","task":"Mathematical Reasoning","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":2,"pages_in_order":2,"rows_per_page":100,"rows":[101,197],"of":197,"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":159,"every_run_a_failure_of_syntologys_instrument":38,"listed_with_a_run_with_no_instrument_failure":159,"listed_every_run_a_failure_of_syntologys_instrument":38,"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-reasoning/papers/ran/1","prev":"/task/mathematical-reasoning/papers/ran/1","next":null,"papers":[{"url":"/paper/we-math-does-your-large-multimodal-model","slug":"we-math-does-your-large-multimodal-model","title":"We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?","date":"2024-07-01","arxiv_id":"2407.01284","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 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; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/we-math-does-your-large-multimodal-model#ran","syntology_url":"https://syntology.ai/paper/2407.01284","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01284"}},"official":{"repos":["we-math/we-math"],"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"]}}},{"url":"/paper/step-controlled-dpo-leveraging-stepwise-error","slug":"step-controlled-dpo-leveraging-stepwise-error","title":"Step-Controlled DPO: Leveraging Stepwise Error for Enhanced Mathematical Reasoning","date":"2024-06-30","arxiv_id":"2407.00782","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"phrase":"6 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/step-controlled-dpo-leveraging-stepwise-error#ran","syntology_url":"https://syntology.ai/paper/2407.00782","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.00782"}},"official":{"repos":["mathllm/Step-Controlled_DPO"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/h-star-llm-driven-hybrid-sql-text-adaptive","slug":"h-star-llm-driven-hybrid-sql-text-adaptive","title":"H-STAR: LLM-driven Hybrid SQL-Text Adaptive Reasoning on Tables","date":"2024-06-29","arxiv_id":"2407.05952","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":1,"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; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/h-star-llm-driven-hybrid-sql-text-adaptive#ran","syntology_url":"https://syntology.ai/paper/2407.05952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.05952"}},"official":{"repos":["nikhilsab/h-star"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"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/step-dpo-step-wise-preference-optimization","slug":"step-dpo-step-wise-preference-optimization","title":"Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs","date":"2024-06-26","arxiv_id":"2406.18629","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":12,"phrase":"11 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/step-dpo-step-wise-preference-optimization#ran","syntology_url":"https://syntology.ai/paper/2406.18629","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18629"}},"official":{"repos":["dvlab-research/step-dpo"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"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/the-reason-behind-good-or-bad-towards-a","slug":"the-reason-behind-good-or-bad-towards-a","title":"LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback","date":"2024-06-20","arxiv_id":"2406.14024","repositories_listed":1,"syntology":{"n":23,"n_ran":22,"n_constructed":0,"n_ran_checked":18,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":17,"n_pointer_only":23,"phrase":"22 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 1 violated, 17 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/the-reason-behind-good-or-bad-towards-a#ran","syntology_url":"https://syntology.ai/paper/2406.14024","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14024"}},"official":{"repos":["kbsdjames/math-minos"],"state":"official (archive's flag): 22 ran","n_ran":22,"n_constructed":0,"n_ran_no_instrument_failure":18,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mathador-lm-a-dynamic-benchmark-for","slug":"mathador-lm-a-dynamic-benchmark-for","title":"Mathador-LM: A Dynamic Benchmark for Mathematical Reasoning on Large Language Models","date":"2024-06-18","arxiv_id":"2406.12572","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/mathador-lm-a-dynamic-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2406.12572","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12572"}},"official":{"repos":["ist-daslab/mathador-lm"],"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/step-level-value-preference-optimization-for","slug":"step-level-value-preference-optimization-for","title":"Step-level Value Preference Optimization for Mathematical Reasoning","date":"2024-06-16","arxiv_id":"2406.10858","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/step-level-value-preference-optimization-for#ran","syntology_url":"https://syntology.ai/paper/2406.10858","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10858"}},"official":{"repos":["MARIO-Math-Reasoning/Super_MARIO"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/living-in-the-moment-can-large-language","slug":"living-in-the-moment-can-large-language","title":"Living in the Moment: Can Large Language Models Grasp Co-Temporal Reasoning?","date":"2024-06-13","arxiv_id":"2406.09072","repositories_listed":1,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":13,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/living-in-the-moment-can-large-language#ran","syntology_url":"https://syntology.ai/paper/2406.09072","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09072"}},"official":{"repos":["zhaochen0110/cotempqa"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/accessing-gpt-4-level-mathematical-olympiad","slug":"accessing-gpt-4-level-mathematical-olympiad","title":"Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B","date":"2024-06-11","arxiv_id":"2406.07394","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/accessing-gpt-4-level-mathematical-olympiad#ran","syntology_url":"https://syntology.ai/paper/2406.07394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07394"}},"official":{"repos":["trotsky1997/mathblackbox"],"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/flow-of-reasoning-efficient-training-of-llm","slug":"flow-of-reasoning-efficient-training-of-llm","title":"Flow of Reasoning:Training LLMs for Divergent Problem Solving with Minimal Examples","date":"2024-06-09","arxiv_id":"2406.05673","repositories_listed":1,"syntology":{"n":15,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/flow-of-reasoning-efficient-training-of-llm#ran","syntology_url":"https://syntology.ai/paper/2406.05673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.05673"}},"official":{"repos":["yu-fangxu/for"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":4,"ran_from_kinds":["official"]}}},{"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":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"5 ran (of which 1 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/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":4,"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/evaluating-mathematical-reasoning-of-large","slug":"evaluating-mathematical-reasoning-of-large","title":"Evaluating Mathematical Reasoning of Large Language Models: A Focus on Error Identification and Correction","date":"2024-06-02","arxiv_id":"2406.00755","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":3,"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/evaluating-mathematical-reasoning-of-large#ran","syntology_url":"https://syntology.ai/paper/2406.00755","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00755"}},"official":{"repos":["littlecirc1e/eic"],"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/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/stride-a-tool-assisted-llm-agent-framework","slug":"stride-a-tool-assisted-llm-agent-framework","title":"STRIDE: A Tool-Assisted LLM Agent Framework for Strategic and Interactive Decision-Making","date":"2024-05-25","arxiv_id":"2405.16376","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":4,"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/stride-a-tool-assisted-llm-agent-framework#ran","syntology_url":"https://syntology.ai/paper/2405.16376","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16376"}},"official":{"repos":["cyrilli/stride"],"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/intelligent-go-explore-standing-on-the","slug":"intelligent-go-explore-standing-on-the","title":"Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models","date":"2024-05-24","arxiv_id":"2405.15143","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":0,"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/intelligent-go-explore-standing-on-the#ran","syntology_url":"https://syntology.ai/paper/2405.15143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15143"}},"official":{"repos":["conglu1997/intelligent-go-explore"],"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/vb-lora-extreme-parameter-efficient-fine","slug":"vb-lora-extreme-parameter-efficient-fine","title":"VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks","date":"2024-05-24","arxiv_id":"2405.15179","repositories_listed":1,"syntology":{"n":17,"n_ran":17,"n_constructed":0,"n_ran_checked":11,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":10,"n_pointer_only":17,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vb-lora-extreme-parameter-efficient-fine#ran","syntology_url":"https://syntology.ai/paper/2405.15179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15179"}},"official":{"repos":["leo-yangli/vb-lora"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/jiuzhang3-0-efficiently-improving","slug":"jiuzhang3-0-efficiently-improving","title":"JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models","date":"2024-05-23","arxiv_id":"2405.14365","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":12,"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) · 3 unverified","sample_list":"/paper/jiuzhang3-0-efficiently-improving#ran","syntology_url":"https://syntology.ai/paper/2405.14365","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14365"}},"official":{"repos":["rucaibox/jiuzhang3.0"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/can-llms-solve-longer-math-word-problems","slug":"can-llms-solve-longer-math-word-problems","title":"Can LLMs Solve longer Math Word Problems Better?","date":"2024-05-23","arxiv_id":"2405.14804","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":5,"n_ran_checked":6,"n_instrument":6,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":9,"phrase":"12 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; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/can-llms-solve-longer-math-word-problems#ran","syntology_url":"https://syntology.ai/paper/2405.14804","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14804"}},"official":{"repos":["xinxu-ustc/coleg-math"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["community","found_in_text","official","unlocated"]}}},{"url":"/paper/trajectory-volatility-for-out-of-distribution","slug":"trajectory-volatility-for-out-of-distribution","title":"Embedding Trajectory for Out-of-Distribution Detection in Mathematical Reasoning","date":"2024-05-22","arxiv_id":"2405.14039","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/trajectory-volatility-for-out-of-distribution#ran","syntology_url":"https://syntology.ai/paper/2405.14039","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14039"}},"official":{"repos":["alsace08/ood-math-reasoning"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mora-high-rank-updating-for-parameter","slug":"mora-high-rank-updating-for-parameter","title":"MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning","date":"2024-05-20","arxiv_id":"2405.12130","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"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) · 3 unverified","sample_list":"/paper/mora-high-rank-updating-for-parameter#ran","syntology_url":"https://syntology.ai/paper/2405.12130","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.12130"}},"official":{"repos":["kongds/mora"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/mumath-code-combining-tool-use-large-language","slug":"mumath-code-combining-tool-use-large-language","title":"MuMath-Code: Combining Tool-Use Large Language Models with Multi-perspective Data Augmentation for Mathematical Reasoning","date":"2024-05-13","arxiv_id":"2405.07551","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":1,"n_no_contract":1,"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, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mumath-code-combining-tool-use-large-language#ran","syntology_url":"https://syntology.ai/paper/2405.07551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.07551"}},"official":null}},{"url":"/paper/visiongraph-leveraging-large-multimodal","slug":"visiongraph-leveraging-large-multimodal","title":"VisionGraph: Leveraging Large Multimodal Models for Graph Theory Problems in Visual Context","date":"2024-05-08","arxiv_id":"2405.04950","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/visiongraph-leveraging-large-multimodal#ran","syntology_url":"https://syntology.ai/paper/2405.04950","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.04950"}},"official":{"repos":["hitsz-tmg/visiongraph"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/exploring-the-compositional-deficiency-of","slug":"exploring-the-compositional-deficiency-of","title":"Exploring the Compositional Deficiency of Large Language Models in Mathematical Reasoning","date":"2024-05-05","arxiv_id":"2405.06680","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":3,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/exploring-the-compositional-deficiency-of#ran","syntology_url":"https://syntology.ai/paper/2405.06680","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.06680"}},"official":{"repos":["tongjingqi/MathTrap"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/benchmarking-benchmark-leakage-in-large","slug":"benchmarking-benchmark-leakage-in-large","title":"Benchmarking Benchmark Leakage in Large Language Models","date":"2024-04-29","arxiv_id":"2404.18824","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"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) · 1 unverified","sample_list":"/paper/benchmarking-benchmark-leakage-in-large#ran","syntology_url":"https://syntology.ai/paper/2404.18824","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.18824"}},"official":{"repos":["gair-nlp/benbench"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/calc-cmu-at-semeval-2024-task-7-pre-calc","slug":"calc-cmu-at-semeval-2024-task-7-pre-calc","title":"Pre-Calc: Learning to Use the Calculator Improves Numeracy in Language Models","date":"2024-04-22","arxiv_id":"2404.14355","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/calc-cmu-at-semeval-2024-task-7-pre-calc#ran","syntology_url":"https://syntology.ai/paper/2404.14355","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.14355"}},"official":{"repos":["calc-cmu/pre-calc"],"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/toward-self-improvement-of-llms-via","slug":"toward-self-improvement-of-llms-via","title":"Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing","date":"2024-04-18","arxiv_id":"2404.12253","repositories_listed":1,"syntology":{"n":18,"n_ran":14,"n_constructed":1,"n_ran_checked":12,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":11,"n_pointer_only":18,"phrase":"14 ran (of which 1 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/toward-self-improvement-of-llms-via#ran","syntology_url":"https://syntology.ai/paper/2404.12253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.12253"}},"official":{"repos":["yetianjhu/alphallm"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":1,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/paraphrase-and-solve-exploring-and-exploiting","slug":"paraphrase-and-solve-exploring-and-exploiting","title":"Paraphrase and Solve: Exploring and Exploiting the Impact of Surface Form on Mathematical Reasoning in Large Language Models","date":"2024-04-17","arxiv_id":"2404.11500","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/paraphrase-and-solve-exploring-and-exploiting#ran","syntology_url":"https://syntology.ai/paper/2404.11500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.11500"}},"official":{"repos":["yue-llm-pit/scop"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/self-explore-to-avoid-the-pit-improving-the","slug":"self-explore-to-avoid-the-pit-improving-the","title":"Self-Explore: Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards","date":"2024-04-16","arxiv_id":"2404.10346","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"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) · 1 unverified","sample_list":"/paper/self-explore-to-avoid-the-pit-improving-the#ran","syntology_url":"https://syntology.ai/paper/2404.10346","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.10346"}},"official":{"repos":["hbin0701/Self-Explore"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/compression-represents-intelligence-linearly","slug":"compression-represents-intelligence-linearly","title":"Compression Represents Intelligence Linearly","date":"2024-04-15","arxiv_id":"2404.09937","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":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/compression-represents-intelligence-linearly#ran","syntology_url":"https://syntology.ai/paper/2404.09937","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09937"}},"official":{"repos":["hkust-nlp/llm-compression-intelligence"],"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/evaluating-mathematical-reasoning-beyond","slug":"evaluating-mathematical-reasoning-beyond","title":"Evaluating Mathematical Reasoning Beyond Accuracy","date":"2024-04-08","arxiv_id":"2404.05692","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/evaluating-mathematical-reasoning-beyond#ran","syntology_url":"https://syntology.ai/paper/2404.05692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05692"}},"official":{"repos":["gair-nlp/reasoneval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"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/masked-thought-simply-masking-partial","slug":"masked-thought-simply-masking-partial","title":"Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models","date":"2024-03-04","arxiv_id":"2403.02178","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/masked-thought-simply-masking-partial#ran","syntology_url":"https://syntology.ai/paper/2403.02178","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.02178"}},"official":{"repos":["changyuchen347/maskedthought"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/stepwise-self-consistent-mathematical","slug":"stepwise-self-consistent-mathematical","title":"Stepwise Self-Consistent Mathematical Reasoning with Large Language Models","date":"2024-02-24","arxiv_id":"2402.17786","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/stepwise-self-consistent-mathematical#ran","syntology_url":"https://syntology.ai/paper/2402.17786","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17786"}},"official":{"repos":["zhao-zilong/ssc-cot"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/conceptmath-a-bilingual-concept-wise","slug":"conceptmath-a-bilingual-concept-wise","title":"ConceptMath: A Bilingual Concept-wise Benchmark for Measuring Mathematical Reasoning of Large Language Models","date":"2024-02-22","arxiv_id":"2402.14660","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":8,"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/conceptmath-a-bilingual-concept-wise#ran","syntology_url":"https://syntology.ai/paper/2402.14660","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14660"}},"official":{"repos":["conceptmath/conceptmath"],"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/reformatted-alignment","slug":"reformatted-alignment","title":"Reformatted Alignment","date":"2024-02-19","arxiv_id":"2402.12219","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":8,"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/reformatted-alignment#ran","syntology_url":"https://syntology.ai/paper/2402.12219","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12219"}},"official":{"repos":["gair-nlp/realign"],"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/perils-of-self-feedback-self-bias-amplifies","slug":"perils-of-self-feedback-self-bias-amplifies","title":"Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement","date":"2024-02-18","arxiv_id":"2402.11436","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":4,"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/perils-of-self-feedback-self-bias-amplifies#ran","syntology_url":"https://syntology.ai/paper/2402.11436","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11436"}},"official":{"repos":["xu1998hz/llm_self_bias"],"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/learning-from-failure-integrating-negative","slug":"learning-from-failure-integrating-negative","title":"Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents","date":"2024-02-18","arxiv_id":"2402.11651","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"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) · 1 unverified","sample_list":"/paper/learning-from-failure-integrating-negative#ran","syntology_url":"https://syntology.ai/paper/2402.11651","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11651"}},"official":{"repos":["reason-wang/nat"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mustard-mastering-uniform-synthesis-of","slug":"mustard-mastering-uniform-synthesis-of","title":"MUSTARD: Mastering Uniform Synthesis of Theorem and Proof Data","date":"2024-02-14","arxiv_id":"2402.08957","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/mustard-mastering-uniform-synthesis-of#ran","syntology_url":"https://syntology.ai/paper/2402.08957","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.08957"}},"official":{"repos":["eleanor-h/mustard"],"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/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":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"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/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/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":10,"n_instrument":4,"n_unverified":10,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":3,"phrase":"14 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; 4 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":8,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"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":1,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"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/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":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/langbridge-multilingual-reasoning-without","slug":"langbridge-multilingual-reasoning-without","title":"LangBridge: Multilingual Reasoning Without Multilingual Supervision","date":"2024-01-19","arxiv_id":"2401.10695","repositories_listed":1,"syntology":{"n":12,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":12,"phrase":"5 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; 2 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/langbridge-multilingual-reasoning-without#ran","syntology_url":"https://syntology.ai/paper/2401.10695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10695"}},"official":{"repos":["kaistAI/LangBridge"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/augmenting-math-word-problems-via-iterative","slug":"augmenting-math-word-problems-via-iterative","title":"Augmenting Math Word Problems via Iterative Question Composing","date":"2024-01-17","arxiv_id":"2401.09003","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":4,"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/augmenting-math-word-problems-via-iterative#ran","syntology_url":"https://syntology.ai/paper/2401.09003","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.09003"}},"official":{"repos":["iiis-ai/iterativequestioncomposing"],"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/stuck-in-the-quicksand-of-numeracy-far-from","slug":"stuck-in-the-quicksand-of-numeracy-far-from","title":"Evaluating LLMs' Mathematical and Coding Competency through Ontology-guided Interventions","date":"2024-01-17","arxiv_id":"2401.09395","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/stuck-in-the-quicksand-of-numeracy-far-from#ran","syntology_url":"https://syntology.ai/paper/2401.09395","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.09395"}},"official":{"repos":["declare-lab/llm-reasoningtest"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"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/sciglm-training-scientific-language-models","slug":"sciglm-training-scientific-language-models","title":"SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models","date":"2024-01-15","arxiv_id":"2401.07950","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"phrase":"7 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/sciglm-training-scientific-language-models#ran","syntology_url":"https://syntology.ai/paper/2401.07950","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.07950"}},"official":{"repos":["thudm/sciglm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mapo-advancing-multilingual-reasoning-through","slug":"mapo-advancing-multilingual-reasoning-through","title":"MAPO: Advancing Multilingual Reasoning through Multilingual Alignment-as-Preference Optimization","date":"2024-01-12","arxiv_id":"2401.06838","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":10,"phrase":"6 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; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/mapo-advancing-multilingual-reasoning-through#ran","syntology_url":"https://syntology.ai/paper/2401.06838","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.06838"}},"official":{"repos":["njunlp/mapo"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/generative-ai-for-math-part-i-mathpile-a","slug":"generative-ai-for-math-part-i-mathpile-a","title":"MathPile: A Billion-Token-Scale Pretraining Corpus for Math","date":"2023-12-28","arxiv_id":"2312.17120","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/generative-ai-for-math-part-i-mathpile-a#ran","syntology_url":"https://syntology.ai/paper/2312.17120","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.17120"}},"official":{"repos":["gair-nlp/mathpile"],"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/an-in-depth-look-at-gemini-s-language","slug":"an-in-depth-look-at-gemini-s-language","title":"An In-depth Look at Gemini's Language Abilities","date":"2023-12-18","arxiv_id":"2312.11444","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":12,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/an-in-depth-look-at-gemini-s-language#ran","syntology_url":"https://syntology.ai/paper/2312.11444","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.11444"}},"official":{"repos":["neulab/gemini-benchmark"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/frugal-lms-trained-to-invoke-symbolic-solvers","slug":"frugal-lms-trained-to-invoke-symbolic-solvers","title":"Frugal LMs Trained to Invoke Symbolic Solvers Achieve Parameter-Efficient Arithmetic Reasoning","date":"2023-12-09","arxiv_id":"2312.05571","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/frugal-lms-trained-to-invoke-symbolic-solvers#ran","syntology_url":"https://syntology.ai/paper/2312.05571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.05571"}},"official":{"repos":["joykirat18/syrelm"],"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/outcome-supervised-verifiers-for-planning-in","slug":"outcome-supervised-verifiers-for-planning-in","title":"OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoning","date":"2023-11-16","arxiv_id":"2311.09724","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/outcome-supervised-verifiers-for-planning-in#ran","syntology_url":"https://syntology.ai/paper/2311.09724","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09724"}},"official":{"repos":["freedomintelligence/ovm"],"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/veritymath-advancing-mathematical-reasoning","slug":"veritymath-advancing-mathematical-reasoning","title":"VerityMath: Advancing Mathematical Reasoning by Self-Verification Through Unit Consistency","date":"2023-11-13","arxiv_id":"2311.07172","repositories_listed":1,"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":1,"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/veritymath-advancing-mathematical-reasoning#ran","syntology_url":"https://syntology.ai/paper/2311.07172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.07172"}},"official":{"repos":["vernontoh/veritymath"],"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/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":8,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":3,"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) · 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":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-from-mistakes-makes-llm-better","slug":"learning-from-mistakes-makes-llm-better","title":"Learning From Mistakes Makes LLM Better Reasoner","date":"2023-10-31","arxiv_id":"2310.20689","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-from-mistakes-makes-llm-better#ran","syntology_url":"https://syntology.ai/paper/2310.20689","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.20689"}},"official":{"repos":["microsoft/lema"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mcc-kd-multi-cot-consistent-knowledge","slug":"mcc-kd-multi-cot-consistent-knowledge","title":"MCC-KD: Multi-CoT Consistent Knowledge Distillation","date":"2023-10-23","arxiv_id":"2310.14747","repositories_listed":1,"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":7,"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/mcc-kd-multi-cot-consistent-knowledge#ran","syntology_url":"https://syntology.ai/paper/2310.14747","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.14747"}},"official":{"repos":["homzer/MCC-KD"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/maf-multi-aspect-feedback-for-improving","slug":"maf-multi-aspect-feedback-for-improving","title":"MAF: Multi-Aspect Feedback for Improving Reasoning in Large Language Models","date":"2023-10-19","arxiv_id":"2310.12426","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/maf-multi-aspect-feedback-for-improving#ran","syntology_url":"https://syntology.ai/paper/2310.12426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.12426"}},"official":{"repos":["deepakn97/maf"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/trigo-benchmarking-formal-mathematical-proof","slug":"trigo-benchmarking-formal-mathematical-proof","title":"TRIGO: Benchmarking Formal Mathematical Proof Reduction for Generative Language Models","date":"2023-10-16","arxiv_id":"2310.10180","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":11,"phrase":"7 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; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/trigo-benchmarking-formal-mathematical-proof#ran","syntology_url":"https://syntology.ai/paper/2310.10180","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.10180"}},"official":{"repos":["menik1126/TRIGO"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"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/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/mathcoder-seamless-code-integration-in-llms","slug":"mathcoder-seamless-code-integration-in-llms","title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","date":"2023-10-05","arxiv_id":"2310.03731","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":0,"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/mathcoder-seamless-code-integration-in-llms#ran","syntology_url":"https://syntology.ai/paper/2310.03731","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03731"}},"official":{"repos":["mathllm/mathcoder"],"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/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/mathvista-evaluating-mathematical-reasoning","slug":"mathvista-evaluating-mathematical-reasoning","title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","date":"2023-10-03","arxiv_id":"2310.02255","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mathvista-evaluating-mathematical-reasoning#ran","syntology_url":"https://syntology.ai/paper/2310.02255","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.02255"}},"official":null}},{"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/code-soliloquies-for-accurate-calculations-in","slug":"code-soliloquies-for-accurate-calculations-in","title":"Code Soliloquies for Accurate Calculations in Large Language Models","date":"2023-09-21","arxiv_id":"2309.12161","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"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) · 1 unverified","sample_list":"/paper/code-soliloquies-for-accurate-calculations-in#ran","syntology_url":"https://syntology.ai/paper/2309.12161","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.12161"}},"official":{"repos":["luffycodes/tutorbot-spock-phys"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/metamath-bootstrap-your-own-mathematical","slug":"metamath-bootstrap-your-own-mathematical","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","date":"2023-09-21","arxiv_id":"2309.12284","repositories_listed":1,"syntology":{"n":22,"n_ran":15,"n_constructed":0,"n_ran_checked":1,"n_instrument":14,"n_unverified":7,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"15 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; 14 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/metamath-bootstrap-your-own-mathematical#ran","syntology_url":"https://syntology.ai/paper/2309.12284","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.12284"}},"official":{"repos":["meta-math/MetaMath"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/auto-regressive-next-token-predictors-are","slug":"auto-regressive-next-token-predictors-are","title":"Auto-Regressive Next-Token Predictors are Universal Learners","date":"2023-09-13","arxiv_id":"2309.06979","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/auto-regressive-next-token-predictors-are#ran","syntology_url":"https://syntology.ai/paper/2309.06979","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.06979"}},"official":{"repos":["emalach/linearlm"],"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/mammoth-building-math-generalist-models","slug":"mammoth-building-math-generalist-models","title":"MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning","date":"2023-09-11","arxiv_id":"2309.05653","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/mammoth-building-math-generalist-models#ran","syntology_url":"https://syntology.ai/paper/2309.05653","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.05653"}},"official":null}},{"url":"/paper/wizardmath-empowering-mathematical-reasoning","slug":"wizardmath-empowering-mathematical-reasoning","title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","date":"2023-08-18","arxiv_id":"2308.09583","repositories_listed":1,"syntology":{"n":16,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":16,"phrase":"10 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; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/wizardmath-empowering-mathematical-reasoning#ran","syntology_url":"https://syntology.ai/paper/2308.09583","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09583"}},"official":null}},{"url":"/paper/separate-the-wheat-from-the-chaff-model","slug":"separate-the-wheat-from-the-chaff-model","title":"Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation","date":"2023-08-16","arxiv_id":"2308.08090","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/separate-the-wheat-from-the-chaff-model#ran","syntology_url":"https://syntology.ai/paper/2308.08090","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.08090"}},"official":{"repos":["hitsz-tmg/ext-sub"],"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/scaling-relationship-on-learning-mathematical","slug":"scaling-relationship-on-learning-mathematical","title":"Scaling Relationship on Learning Mathematical Reasoning with Large Language Models","date":"2023-08-03","arxiv_id":"2308.01825","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/scaling-relationship-on-learning-mathematical#ran","syntology_url":"https://syntology.ai/paper/2308.01825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.01825"}},"official":{"repos":["ofa-sys/gsm8k-screl"],"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/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/understanding-arithmetic-reasoning-in","slug":"understanding-arithmetic-reasoning-in","title":"A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis","date":"2023-05-24","arxiv_id":"2305.15054","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":3,"n_ran_checked":3,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"7 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/understanding-arithmetic-reasoning-in#ran","syntology_url":"https://syntology.ai/paper/2305.15054","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.15054"}},"official":{"repos":["alestolfo/lm-arithmetic"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"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/mathprompter-mathematical-reasoning-using","slug":"mathprompter-mathematical-reasoning-using","title":"MathPrompter: Mathematical Reasoning using Large Language Models","date":"2023-03-04","arxiv_id":"2303.05398","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"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, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mathprompter-mathematical-reasoning-using#ran","syntology_url":"https://syntology.ai/paper/2303.05398","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.05398"}},"official":null}},{"url":"/paper/a-multi-modal-neural-geometric-solver-with","slug":"a-multi-modal-neural-geometric-solver-with","title":"A Multi-Modal Neural Geometric Solver with Textual Clauses Parsed from Diagram","date":"2023-02-22","arxiv_id":"2302.11097","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":4,"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 4 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/a-multi-modal-neural-geometric-solver-with#ran","syntology_url":"https://syntology.ai/paper/2302.11097","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.11097"}},"official":{"repos":["mingliangzhang2018/pgps"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"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/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/lemma-bootstrapping-high-level-mathematical","slug":"lemma-bootstrapping-high-level-mathematical","title":"LEMMA: Bootstrapping High-Level Mathematical Reasoning with Learned Symbolic Abstractions","date":"2022-11-16","arxiv_id":"2211.08671","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":0,"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/lemma-bootstrapping-high-level-mathematical#ran","syntology_url":"https://syntology.ai/paper/2211.08671","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.08671"}},"official":{"repos":["uranium11010/lemma"],"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/galactica-a-large-language-model-for-science-1","slug":"galactica-a-large-language-model-for-science-1","title":"Galactica: A Large Language Model for Science","date":"2022-11-16","arxiv_id":"2211.09085","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/galactica-a-large-language-model-for-science-1#ran","syntology_url":"https://syntology.ai/paper/2211.09085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09085"}},"official":{"repos":["paperswithcode/galai"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-view-reasoning-consistent-contrastive","slug":"multi-view-reasoning-consistent-contrastive","title":"Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problem","date":"2022-10-21","arxiv_id":"2210.11694","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"9 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; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/multi-view-reasoning-consistent-contrastive#ran","syntology_url":"https://syntology.ai/paper/2210.11694","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.11694"}},"official":{"repos":["zwq2018/multi-view-consistency-for-mwp"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/a-causal-framework-to-quantify-the-robustness","slug":"a-causal-framework-to-quantify-the-robustness","title":"A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models","date":"2022-10-21","arxiv_id":"2210.12023","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":2,"n_ran_checked":3,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-causal-framework-to-quantify-the-robustness#ran","syntology_url":"https://syntology.ai/paper/2210.12023","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.12023"}},"official":{"repos":["alestolfo/causal-math"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":3,"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/a-neural-network-solves-and-generates","slug":"a-neural-network-solves-and-generates","title":"A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Level","date":"2021-12-31","arxiv_id":"2112.15594","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":0,"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/a-neural-network-solves-and-generates#ran","syntology_url":"https://syntology.ai/paper/2112.15594","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.15594"}},"official":{"repos":["idrori/mathq"],"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/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/iconqa-a-new-benchmark-for-abstract-diagram","slug":"iconqa-a-new-benchmark-for-abstract-diagram","title":"IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning","date":"2021-10-25","arxiv_id":"2110.13214","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":10,"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) · 2 unverified","sample_list":"/paper/iconqa-a-new-benchmark-for-abstract-diagram#ran","syntology_url":"https://syntology.ai/paper/2110.13214","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.13214"}},"official":{"repos":["lupantech/iconqa"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"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":44,"n_instrument":7,"n_unverified":33,"n_honours":1,"n_violates":0,"n_no_contract":43,"n_pointer_only":30,"phrase":"51 ran (of which 19 constructed an object rather than computing a result; 44 with no instrument failure: 1 honoured, 0 violated, 43 with no contract checked; 7 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/inter-gps-interpretable-geometry-problem","slug":"inter-gps-interpretable-geometry-problem","title":"Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning","date":"2021-05-10","arxiv_id":"2105.04165","repositories_listed":1,"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":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) · 1 unverified","sample_list":"/paper/inter-gps-interpretable-geometry-problem#ran","syntology_url":"https://syntology.ai/paper/2105.04165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.04165"}},"official":{"repos":["lupantech/InterGPS"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"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"]}}},{"url":"/paper/lime-learning-inductive-bias-for-primitives-1","slug":"lime-learning-inductive-bias-for-primitives-1","title":"LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning","date":"2021-01-15","arxiv_id":"2101.06223","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 1 unverified","sample_list":"/paper/lime-learning-inductive-bias-for-primitives-1#ran","syntology_url":"https://syntology.ai/paper/2101.06223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.06223"}},"official":{"repos":["tonywu95/lime"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"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/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/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}}],"record_sha256":"25e91304f3c558289d8f4623baa2e9706ebf9cdf3082465070cea47d3c9bfd4a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}