{"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/math/papers/ran/3","list_of":"/task/math","task":"Math","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":3,"pages_in_order":4,"rows_per_page":100,"rows":[201,300],"of":349,"counts":{"archive_papers_tagged":1596,"with_a_code_link":765,"where_syntology_ran_a_sample":349,"not_listed_spam_title":0,"listed":1596,"listed_where_code_ran":349,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":286,"every_run_a_failure_of_syntologys_instrument":63,"listed_with_a_run_with_no_instrument_failure":286,"listed_every_run_a_failure_of_syntologys_instrument":63,"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/math/papers/ran/1","prev":"/task/math/papers/ran/2","next":"/task/math/papers/ran/4","papers":[{"url":"/paper/autoformalizing-euclidean-geometry","slug":"autoformalizing-euclidean-geometry","title":"Autoformalizing Euclidean Geometry","date":"2024-05-27","arxiv_id":"2405.17216","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":4,"n_honours":1,"n_violates":2,"n_no_contract":1,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/autoformalizing-euclidean-geometry#ran","syntology_url":"https://syntology.ai/paper/2405.17216","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17216"}},"official":{"repos":["loganrjmurphy/leaneuclid"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/lora-xs-low-rank-adaptation-with-extremely","slug":"lora-xs-low-rank-adaptation-with-extremely","title":"LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters","date":"2024-05-27","arxiv_id":"2405.17604","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"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; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lora-xs-low-rank-adaptation-with-extremely#ran","syntology_url":"https://syntology.ai/paper/2405.17604","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17604"}},"official":{"repos":["mohammadrezabanaei/lora-xs"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/meteor-mamba-based-traversal-of-rationale-for","slug":"meteor-mamba-based-traversal-of-rationale-for","title":"Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models","date":"2024-05-24","arxiv_id":"2405.15574","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/meteor-mamba-based-traversal-of-rationale-for#ran","syntology_url":"https://syntology.ai/paper/2405.15574","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15574"}},"official":{"repos":["byungkwanlee/meteor"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"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/multiple-choice-questions-are-efficient-and","slug":"multiple-choice-questions-are-efficient-and","title":"Multiple-Choice Questions are Efficient and Robust LLM Evaluators","date":"2024-05-20","arxiv_id":"2405.11966","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/multiple-choice-questions-are-efficient-and#ran","syntology_url":"https://syntology.ai/paper/2405.11966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.11966"}},"official":{"repos":["geralt-targaryen/mc-evaluation"],"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/a-safety-realignment-framework-via-subspace","slug":"a-safety-realignment-framework-via-subspace","title":"A safety realignment framework via subspace-oriented model fusion for large language models","date":"2024-05-15","arxiv_id":"2405.09055","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/a-safety-realignment-framework-via-subspace#ran","syntology_url":"https://syntology.ai/paper/2405.09055","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.09055"}},"official":{"repos":["xinykou/safety_realignment"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"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/monte-carlo-tree-search-boosts-reasoning-via","slug":"monte-carlo-tree-search-boosts-reasoning-via","title":"Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning","date":"2024-05-01","arxiv_id":"2405.00451","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":1,"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/monte-carlo-tree-search-boosts-reasoning-via#ran","syntology_url":"https://syntology.ai/paper/2405.00451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.00451"}},"official":{"repos":["YuxiXie/MCTS-DPO"],"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/layer-skip-enabling-early-exit-inference-and","slug":"layer-skip-enabling-early-exit-inference-and","title":"LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding","date":"2024-04-25","arxiv_id":"2404.16710","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":1,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"4 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/layer-skip-enabling-early-exit-inference-and#ran","syntology_url":"https://syntology.ai/paper/2404.16710","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.16710"}},"official":{"repos":["facebookresearch/layerskip"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mario-eval-evaluate-your-math-llm-with-your","slug":"mario-eval-evaluate-your-math-llm-with-your","title":"MARIO Eval: Evaluate Your Math LLM with your Math LLM--A mathematical dataset evaluation toolkit","date":"2024-04-22","arxiv_id":"2404.13925","repositories_listed":4,"syntology":{"n":13,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":13,"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) · 5 unverified","sample_list":"/paper/mario-eval-evaluate-your-math-llm-with-your#ran","syntology_url":"https://syntology.ai/paper/2404.13925","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.13925"}},"official":{"repos":["mario-math-reasoning/math_evaluation"],"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/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/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/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/badam-a-memory-efficient-full-parameter","slug":"badam-a-memory-efficient-full-parameter","title":"BAdam: A Memory Efficient Full Parameter Optimization Method for Large Language Models","date":"2024-04-03","arxiv_id":"2404.02827","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/badam-a-memory-efficient-full-parameter#ran","syntology_url":"https://syntology.ai/paper/2404.02827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.02827"}},"official":{"repos":["ledzy/badam"],"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/chatglm-math-improving-math-problem-solving","slug":"chatglm-math-improving-math-problem-solving","title":"ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline","date":"2024-04-03","arxiv_id":"2404.02893","repositories_listed":3,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/chatglm-math-improving-math-problem-solving#ran","syntology_url":"https://syntology.ai/paper/2404.02893","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.02893"}},"official":{"repos":["thudm/chatglm-math"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/what-s-in-your-safe-data-identifying-benign","slug":"what-s-in-your-safe-data-identifying-benign","title":"What is in Your Safe Data? Identifying Benign Data that Breaks Safety","date":"2024-04-01","arxiv_id":"2404.01099","repositories_listed":1,"syntology":{"n":14,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":14,"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) · 7 unverified","sample_list":"/paper/what-s-in-your-safe-data-identifying-benign#ran","syntology_url":"https://syntology.ai/paper/2404.01099","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01099"}},"official":{"repos":["princeton-nlp/benign-data-breaks-safety"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":7,"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/don-t-trust-verify-grounding-llm-quantitative","slug":"don-t-trust-verify-grounding-llm-quantitative","title":"Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization","date":"2024-03-26","arxiv_id":"2403.18120","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":2,"n_instrument":8,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"10 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; 8 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/don-t-trust-verify-grounding-llm-quantitative#ran","syntology_url":"https://syntology.ai/paper/2403.18120","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18120"}},"official":{"repos":["jinpz/dtv"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/evolutionary-optimization-of-model-merging","slug":"evolutionary-optimization-of-model-merging","title":"Evolutionary Optimization of Model Merging Recipes","date":"2024-03-19","arxiv_id":"2403.13187","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"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: 0 honoured, 1 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/evolutionary-optimization-of-model-merging#ran","syntology_url":"https://syntology.ai/paper/2403.13187","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13187"}},"official":{"repos":["sakanaai/evolutionary-model-merge"],"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/easy-to-hard-generalization-scalable","slug":"easy-to-hard-generalization-scalable","title":"Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision","date":"2024-03-14","arxiv_id":"2403.09472","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/easy-to-hard-generalization-scalable#ran","syntology_url":"https://syntology.ai/paper/2403.09472","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09472"}},"official":{"repos":["edward-sun/easy-to-hard"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/smalltolarge-s2l-scalable-data-selection-for","slug":"smalltolarge-s2l-scalable-data-selection-for","title":"SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models","date":"2024-03-12","arxiv_id":"2403.07384","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/smalltolarge-s2l-scalable-data-selection-for#ran","syntology_url":"https://syntology.ai/paper/2403.07384","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07384"}},"official":{"repos":["bigml-cs-ucla/s2l"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/common-7b-language-models-already-possess","slug":"common-7b-language-models-already-possess","title":"Common 7B Language Models Already Possess Strong Math Capabilities","date":"2024-03-07","arxiv_id":"2403.04706","repositories_listed":2,"syntology":{"n":28,"n_ran":21,"n_constructed":0,"n_ran_checked":20,"n_instrument":1,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":20,"n_pointer_only":12,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 0 violated, 20 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/common-7b-language-models-already-possess#ran","syntology_url":"https://syntology.ai/paper/2403.04706","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04706"}},"official":{"repos":["xwin-lm/xwin-lm"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["listed","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/improving-the-validity-of-automatically","slug":"improving-the-validity-of-automatically","title":"Improving the Validity of Automatically Generated Feedback via Reinforcement Learning","date":"2024-03-02","arxiv_id":"2403.01304","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":13,"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) · 4 unverified","sample_list":"/paper/improving-the-validity-of-automatically#ran","syntology_url":"https://syntology.ai/paper/2403.01304","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01304"}},"official":{"repos":["umass-ml4ed/feedback-gen-dpo"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/functional-benchmarks-for-robust-evaluation","slug":"functional-benchmarks-for-robust-evaluation","title":"Functional Benchmarks for Robust Evaluation of Reasoning Performance, and the Reasoning Gap","date":"2024-02-29","arxiv_id":"2402.19450","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"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; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/functional-benchmarks-for-robust-evaluation#ran","syntology_url":"https://syntology.ai/paper/2402.19450","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.19450"}},"official":{"repos":["consequentai/fneval"],"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/case-based-or-rule-based-how-do-transformers","slug":"case-based-or-rule-based-how-do-transformers","title":"Case-Based or Rule-Based: How Do Transformers Do the Math?","date":"2024-02-27","arxiv_id":"2402.17709","repositories_listed":1,"syntology":{"n":13,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/case-based-or-rule-based-how-do-transformers#ran","syntology_url":"https://syntology.ai/paper/2402.17709","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17709"}},"official":{"repos":["graphpku/case_or_rule"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"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/language-models-are-homer-simpson-safety-re","slug":"language-models-are-homer-simpson-safety-re","title":"Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic","date":"2024-02-19","arxiv_id":"2402.11746","repositories_listed":3,"syntology":{"n":16,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":9,"phrase":"13 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; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/language-models-are-homer-simpson-safety-re#ran","syntology_url":"https://syntology.ai/paper/2402.11746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11746"}},"official":{"repos":["declare-lab/resta","hiyouga/llama-factory"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["listed","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/geoeval-benchmark-for-evaluating-llms-and","slug":"geoeval-benchmark-for-evaluating-llms-and","title":"GeoEval: Benchmark for Evaluating LLMs and Multi-Modal Models on Geometry Problem-Solving","date":"2024-02-15","arxiv_id":"2402.10104","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":14,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/geoeval-benchmark-for-evaluating-llms-and#ran","syntology_url":"https://syntology.ai/paper/2402.10104","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10104"}},"official":{"repos":["geoeval/geoeval"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"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/scaling-the-authoring-of-autotutors-with","slug":"scaling-the-authoring-of-autotutors-with","title":"AutoTutor meets Large Language Models: A Language Model Tutor with Rich Pedagogy and Guardrails","date":"2024-02-14","arxiv_id":"2402.09216","repositories_listed":1,"syntology":{"n":10,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":10,"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) · 6 unverified","sample_list":"/paper/scaling-the-authoring-of-autotutors-with#ran","syntology_url":"https://syntology.ai/paper/2402.09216","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09216"}},"official":{"repos":["eth-lre/mwptutor"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":6,"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/diffusion-of-thoughts-chain-of-thought","slug":"diffusion-of-thoughts-chain-of-thought","title":"Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models","date":"2024-02-12","arxiv_id":"2402.07754","repositories_listed":1,"syntology":{"n":17,"n_ran":16,"n_constructed":0,"n_ran_checked":14,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":13,"n_pointer_only":17,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/diffusion-of-thoughts-chain-of-thought#ran","syntology_url":"https://syntology.ai/paper/2402.07754","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07754"}},"official":{"repos":["hkunlp/diffusion-of-thoughts"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/noise-contrastive-alignment-of-language","slug":"noise-contrastive-alignment-of-language","title":"Noise Contrastive Alignment of Language Models with Explicit Rewards","date":"2024-02-08","arxiv_id":"2402.05369","repositories_listed":3,"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/noise-contrastive-alignment-of-language#ran","syntology_url":"https://syntology.ai/paper/2402.05369","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05369"}},"official":{"repos":["thu-ml/noise-contrastive-alignment"],"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/understanding-the-reasoning-ability-of","slug":"understanding-the-reasoning-ability-of","title":"Understanding Reasoning Ability of Language Models From the Perspective of Reasoning Paths Aggregation","date":"2024-02-05","arxiv_id":"2402.03268","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":2,"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/understanding-the-reasoning-ability-of#ran","syntology_url":"https://syntology.ai/paper/2402.03268","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03268"}},"official":{"repos":["wangxinyilinda/lm_random_walk"],"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/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/magdi-structured-distillation-of-multi-agent","slug":"magdi-structured-distillation-of-multi-agent","title":"MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models","date":"2024-02-02","arxiv_id":"2402.01620","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":0,"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/magdi-structured-distillation-of-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2402.01620","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01620"}},"official":{"repos":["dinobby/magdi"],"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/regal-refactoring-programs-to-discover","slug":"regal-refactoring-programs-to-discover","title":"ReGAL: Refactoring Programs to Discover Generalizable Abstractions","date":"2024-01-29","arxiv_id":"2401.16467","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/regal-refactoring-programs-to-discover#ran","syntology_url":"https://syntology.ai/paper/2401.16467","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.16467"}},"official":{"repos":["esteng/regal_program_learning"],"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-ai-assistants-know-what-they-don-t-know","slug":"can-ai-assistants-know-what-they-don-t-know","title":"Can AI Assistants Know What They Don't Know?","date":"2024-01-24","arxiv_id":"2401.13275","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":12,"phrase":"9 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; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/can-ai-assistants-know-what-they-don-t-know#ran","syntology_url":"https://syntology.ai/paper/2401.13275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.13275"}},"official":{"repos":["openmoss/say-i-dont-know"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/trove-inducing-verifiable-and-efficient","slug":"trove-inducing-verifiable-and-efficient","title":"TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Tasks","date":"2024-01-23","arxiv_id":"2401.12869","repositories_listed":1,"syntology":{"n":19,"n_ran":16,"n_constructed":0,"n_ran_checked":16,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":19,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/trove-inducing-verifiable-and-efficient#ran","syntology_url":"https://syntology.ai/paper/2401.12869","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.12869"}},"official":{"repos":["zorazrw/trove"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/escape-sky-high-cost-early-stopping-self","slug":"escape-sky-high-cost-early-stopping-self","title":"Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning","date":"2024-01-19","arxiv_id":"2401.10480","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":8,"phrase":"7 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/escape-sky-high-cost-early-stopping-self#ran","syntology_url":"https://syntology.ai/paper/2401.10480","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10480"}},"official":{"repos":["yiwei98/esc"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/reft-reasoning-with-reinforced-fine-tuning","slug":"reft-reasoning-with-reinforced-fine-tuning","title":"ReFT: Reasoning with Reinforced Fine-Tuning","date":"2024-01-17","arxiv_id":"2401.08967","repositories_listed":1,"syntology":{"n":14,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":13,"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) · 9 unverified","sample_list":"/paper/reft-reasoning-with-reinforced-fine-tuning#ran","syntology_url":"https://syntology.ai/paper/2401.08967","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.08967"}},"official":{"repos":["lqtrung1998/mwp_reft"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":9,"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/large-language-models-are-neurosymbolic","slug":"large-language-models-are-neurosymbolic","title":"Large Language Models Are Neurosymbolic Reasoners","date":"2024-01-17","arxiv_id":"2401.09334","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/large-language-models-are-neurosymbolic#ran","syntology_url":"https://syntology.ai/paper/2401.09334","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.09334"}},"official":{"repos":["hyintell/llmsymbolic"],"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/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/tuning-language-models-by-proxy","slug":"tuning-language-models-by-proxy","title":"Tuning Language Models by Proxy","date":"2024-01-16","arxiv_id":"2401.08565","repositories_listed":2,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":10,"phrase":"9 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tuning-language-models-by-proxy#ran","syntology_url":"https://syntology.ai/paper/2401.08565","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.08565"}},"official":{"repos":["alisawuffles/proxy-tuning"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"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/the-benefits-of-a-concise-chain-of-thought-on","slug":"the-benefits-of-a-concise-chain-of-thought-on","title":"The Benefits of a Concise Chain of Thought on Problem-Solving in Large Language Models","date":"2024-01-11","arxiv_id":"2401.05618","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/the-benefits-of-a-concise-chain-of-thought-on#ran","syntology_url":"https://syntology.ai/paper/2401.05618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.05618"}},"official":{"repos":["matthewrenze/jhu-concise-cot"],"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/rosa-accurate-parameter-efficient-fine-tuning","slug":"rosa-accurate-parameter-efficient-fine-tuning","title":"RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust Adaptation","date":"2024-01-09","arxiv_id":"2401.04679","repositories_listed":2,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"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) · 3 unverified","sample_list":"/paper/rosa-accurate-parameter-efficient-fine-tuning#ran","syntology_url":"https://syntology.ai/paper/2401.04679","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.04679"}},"official":{"repos":["ist-daslab/rosa"],"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":["listed","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/get-an-a-in-math-progressive-rectification","slug":"get-an-a-in-math-progressive-rectification","title":"Get an A in Math: Progressive Rectification Prompting","date":"2023-12-11","arxiv_id":"2312.06867","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/get-an-a-in-math-progressive-rectification#ran","syntology_url":"https://syntology.ai/paper/2312.06867","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06867"}},"official":{"repos":["wzy6642/PRP"],"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/beyond-surface-probing-llama-across-scales","slug":"beyond-surface-probing-llama-across-scales","title":"Is Bigger and Deeper Always Better? Probing LLaMA Across Scales and Layers","date":"2023-12-07","arxiv_id":"2312.04333","repositories_listed":1,"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":6,"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/beyond-surface-probing-llama-across-scales#ran","syntology_url":"https://syntology.ai/paper/2312.04333","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.04333"}},"official":{"repos":["nuochenpku/llama_analysis"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/eliciting-latent-knowledge-from-quirky","slug":"eliciting-latent-knowledge-from-quirky","title":"Eliciting Latent Knowledge from Quirky Language Models","date":"2023-12-02","arxiv_id":"2312.01037","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"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) · 2 unverified","sample_list":"/paper/eliciting-latent-knowledge-from-quirky#ran","syntology_url":"https://syntology.ai/paper/2312.01037","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.01037"}},"official":{"repos":["eleutherai/elk-generalization"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/reds-resource-efficient-deep-subnetworks-for","slug":"reds-resource-efficient-deep-subnetworks-for","title":"REDS: Resource-Efficient Deep Subnetworks for Dynamic Resource Constraints","date":"2023-11-22","arxiv_id":"2311.13349","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":7,"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/reds-resource-efficient-deep-subnetworks-for#ran","syntology_url":"https://syntology.ai/paper/2311.13349","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13349"}},"official":{"repos":["FraCorti/Deep_Subnetworks_for_Dynamic_Resource_Constraints"],"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/meta-prompting-for-agi-systems","slug":"meta-prompting-for-agi-systems","title":"Meta Prompting for AI Systems","date":"2023-11-20","arxiv_id":"2311.11482","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/meta-prompting-for-agi-systems#ran","syntology_url":"https://syntology.ai/paper/2311.11482","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.11482"}},"official":{"repos":["meta-prompting/meta-prompting"],"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/knowledgemath-knowledge-intensive-math-word","slug":"knowledgemath-knowledge-intensive-math-word","title":"FinanceMath: Knowledge-Intensive Math Reasoning in Finance Domains","date":"2023-11-16","arxiv_id":"2311.09797","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":15,"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) · 3 unverified","sample_list":"/paper/knowledgemath-knowledge-intensive-math-word#ran","syntology_url":"https://syntology.ai/paper/2311.09797","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09797"}},"official":{"repos":["yale-nlp/knowledgemath"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/docmath-eval-evaluating-numerical-reasoning","slug":"docmath-eval-evaluating-numerical-reasoning","title":"DocMath-Eval: Evaluating Math Reasoning Capabilities of LLMs in Understanding Long and Specialized Documents","date":"2023-11-16","arxiv_id":"2311.09805","repositories_listed":1,"syntology":{"n":15,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":15,"phrase":"10 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; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/docmath-eval-evaluating-numerical-reasoning#ran","syntology_url":"https://syntology.ai/paper/2311.09805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09805"}},"official":{"repos":["yale-nlp/docmath-eval"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/strategyllm-large-language-models-as-strategy","slug":"strategyllm-large-language-models-as-strategy","title":"StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving","date":"2023-11-15","arxiv_id":"2311.08803","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":1,"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/strategyllm-large-language-models-as-strategy#ran","syntology_url":"https://syntology.ai/paper/2311.08803","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.08803"}},"official":{"repos":["gao-xiao-bai/strategyllm"],"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/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/lumos-learning-agents-with-unified-data","slug":"lumos-learning-agents-with-unified-data","title":"Agent Lumos: Unified and Modular Training for Open-Source Language Agents","date":"2023-11-09","arxiv_id":"2311.05657","repositories_listed":2,"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":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) · 1 unverified","sample_list":"/paper/lumos-learning-agents-with-unified-data#ran","syntology_url":"https://syntology.ai/paper/2311.05657","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.05657"}},"official":{"repos":["allenai/lumos"],"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/locating-cross-task-sequence-continuation","slug":"locating-cross-task-sequence-continuation","title":"Towards Interpretable Sequence Continuation: Analyzing Shared Circuits in Large Language Models","date":"2023-11-07","arxiv_id":"2311.04131","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/locating-cross-task-sequence-continuation#ran","syntology_url":"https://syntology.ai/paper/2311.04131","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.04131"}},"official":{"repos":["apartresearch/seqcont_circuits"],"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/implicit-chain-of-thought-reasoning-via","slug":"implicit-chain-of-thought-reasoning-via","title":"Implicit Chain of Thought Reasoning via Knowledge Distillation","date":"2023-11-02","arxiv_id":"2311.01460","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/implicit-chain-of-thought-reasoning-via#ran","syntology_url":"https://syntology.ai/paper/2311.01460","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.01460"}},"official":{"repos":["da03/implicit_chain_of_thought"],"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/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/collaborative-evaluation-exploring-the","slug":"collaborative-evaluation-exploring-the","title":"Exploring the Reliability of Large Language Models as Customized Evaluators for Diverse NLP Tasks","date":"2023-10-30","arxiv_id":"2310.19740","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":2,"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) · 4 unverified","sample_list":"/paper/collaborative-evaluation-exploring-the#ran","syntology_url":"https://syntology.ai/paper/2310.19740","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.19740"}},"official":{"repos":["qtli/coeval"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/expression-syntax-information-bottleneck-for","slug":"expression-syntax-information-bottleneck-for","title":"Expression Syntax Information Bottleneck for Math Word Problems","date":"2023-10-24","arxiv_id":"2310.15664","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"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) · 1 unverified","sample_list":"/paper/expression-syntax-information-bottleneck-for#ran","syntology_url":"https://syntology.ai/paper/2310.15664","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.15664"}},"official":{"repos":["menik1126/math_esib"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/plan-verify-and-switch-integrated-reasoning","slug":"plan-verify-and-switch-integrated-reasoning","title":"Plan, Verify and Switch: Integrated Reasoning with Diverse X-of-Thoughts","date":"2023-10-23","arxiv_id":"2310.14628","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/plan-verify-and-switch-integrated-reasoning#ran","syntology_url":"https://syntology.ai/paper/2310.14628","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.14628"}},"official":{"repos":["tengxiaoliu/xot"],"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/teaching-language-models-to-self-improve","slug":"teaching-language-models-to-self-improve","title":"Teaching Language Models to Self-Improve through Interactive Demonstrations","date":"2023-10-20","arxiv_id":"2310.13522","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/teaching-language-models-to-self-improve#ran","syntology_url":"https://syntology.ai/paper/2310.13522","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.13522"}},"official":{"repos":["jasonyux/tripost"],"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/llemma-an-open-language-model-for-mathematics","slug":"llemma-an-open-language-model-for-mathematics","title":"Llemma: An Open Language Model For Mathematics","date":"2023-10-16","arxiv_id":"2310.10631","repositories_listed":4,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/llemma-an-open-language-model-for-mathematics#ran","syntology_url":"https://syntology.ai/paper/2310.10631","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.10631"}},"official":{"repos":["EleutherAI/math-lm","eleutherai/gpt-neox","wellecks/llmstep"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/step-by-step-remediation-of-students","slug":"step-by-step-remediation-of-students","title":"Bridging the Novice-Expert Gap via Models of Decision-Making: A Case Study on Remediating Math Mistakes","date":"2023-10-16","arxiv_id":"2310.10648","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/step-by-step-remediation-of-students#ran","syntology_url":"https://syntology.ai/paper/2310.10648","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.10648"}},"official":{"repos":["rosewang2008/bridge"],"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/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/language-agent-tree-search-unifies-reasoning","slug":"language-agent-tree-search-unifies-reasoning","title":"Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models","date":"2023-10-06","arxiv_id":"2310.04406","repositories_listed":2,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/language-agent-tree-search-unifies-reasoning#ran","syntology_url":"https://syntology.ai/paper/2310.04406","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04406"}},"official":{"repos":["lapisrocks/languageagenttreesearch","andyz245/LanguageAgentTreeSearch"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dspy-compiling-declarative-language-model","slug":"dspy-compiling-declarative-language-model","title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","date":"2023-10-05","arxiv_id":"2310.03714","repositories_listed":3,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/dspy-compiling-declarative-language-model#ran","syntology_url":"https://syntology.ai/paper/2310.03714","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03714"}},"official":{"repos":["stanfordnlp/dspy"],"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/retrieval-augmented-generation-to-improve","slug":"retrieval-augmented-generation-to-improve","title":"Retrieval-augmented Generation to Improve Math Question-Answering: Trade-offs Between Groundedness and Human Preference","date":"2023-10-04","arxiv_id":"2310.03184","repositories_listed":2,"syntology":{"n":20,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"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) · 8 unverified","sample_list":"/paper/retrieval-augmented-generation-to-improve#ran","syntology_url":"https://syntology.ai/paper/2310.03184","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03184"}},"official":{"repos":["digitalharborfoundation/rag-for-math-qa"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":8,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/instance-needs-more-care-rewriting-prompts","slug":"instance-needs-more-care-rewriting-prompts","title":"Instances Need More Care: Rewriting Prompts for Instances with LLMs in the Loop Yields Better Zero-Shot Performance","date":"2023-10-03","arxiv_id":"2310.02107","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/instance-needs-more-care-rewriting-prompts#ran","syntology_url":"https://syntology.ai/paper/2310.02107","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.02107"}},"official":{"repos":["salokr/propmted"],"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/dynamic-llm-agent-network-an-llm-agent","slug":"dynamic-llm-agent-network-an-llm-agent","title":"A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration","date":"2023-10-03","arxiv_id":"2310.02170","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":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) · 0 unverified","sample_list":"/paper/dynamic-llm-agent-network-an-llm-agent#ran","syntology_url":"https://syntology.ai/paper/2310.02170","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.02170"}},"official":{"repos":["salt-nlp/dylan"],"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/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/qwen-technical-report","slug":"qwen-technical-report","title":"Qwen Technical Report","date":"2023-09-28","arxiv_id":"2309.16609","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/qwen-technical-report#ran","syntology_url":"https://syntology.ai/paper/2309.16609","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.16609"}},"official":{"repos":["QwenLM/Qwen-7B","qwenlm/qwen"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/reconcile-round-table-conference-improves","slug":"reconcile-round-table-conference-improves","title":"ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs","date":"2023-09-22","arxiv_id":"2309.13007","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/reconcile-round-table-conference-improves#ran","syntology_url":"https://syntology.ai/paper/2309.13007","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.13007"}},"official":{"repos":["dinobby/reconcile"],"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/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/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/gpt-can-solve-mathematical-problems-without-a","slug":"gpt-can-solve-mathematical-problems-without-a","title":"GPT Can Solve Mathematical Problems Without a Calculator","date":"2023-09-06","arxiv_id":"2309.03241","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/gpt-can-solve-mathematical-problems-without-a#ran","syntology_url":"https://syntology.ai/paper/2309.03241","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.03241"}},"official":{"repos":["thudm/mathglm"],"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/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/towards-an-ai-to-win-ghana-s-national-science","slug":"towards-an-ai-to-win-ghana-s-national-science","title":"Towards an AI to Win Ghana's National Science and Maths Quiz","date":"2023-08-08","arxiv_id":"2308.04333","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/towards-an-ai-to-win-ghana-s-national-science#ran","syntology_url":"https://syntology.ai/paper/2308.04333","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.04333"}},"official":{"repos":["nsmq-ai/nsmqai"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/cumulative-reasoning-with-large-language","slug":"cumulative-reasoning-with-large-language","title":"Cumulative Reasoning with Large Language Models","date":"2023-08-08","arxiv_id":"2308.04371","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":6,"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) · 1 unverified","sample_list":"/paper/cumulative-reasoning-with-large-language#ran","syntology_url":"https://syntology.ai/paper/2308.04371","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.04371"}},"official":{"repos":["iiis-ai/cumulative-reasoning"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mm-vet-evaluating-large-multimodal-models-for","slug":"mm-vet-evaluating-large-multimodal-models-for","title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","date":"2023-08-04","arxiv_id":"2308.02490","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/mm-vet-evaluating-large-multimodal-models-for#ran","syntology_url":"https://syntology.ai/paper/2308.02490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.02490"}},"official":{"repos":["yuweihao/mm-vet"],"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/selfcheck-using-llms-to-zero-shot-check-their","slug":"selfcheck-using-llms-to-zero-shot-check-their","title":"SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning","date":"2023-08-01","arxiv_id":"2308.00436","repositories_listed":1,"syntology":{"n":16,"n_ran":14,"n_constructed":0,"n_ran_checked":14,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":16,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/selfcheck-using-llms-to-zero-shot-check-their#ran","syntology_url":"https://syntology.ai/paper/2308.00436","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.00436"}},"official":{"repos":["ningmiao/selfcheck"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/how-is-chatgpt-s-behavior-changing-over-time","slug":"how-is-chatgpt-s-behavior-changing-over-time","title":"How is ChatGPT's behavior changing over time?","date":"2023-07-18","arxiv_id":"2307.09009","repositories_listed":4,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"6 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/how-is-chatgpt-s-behavior-changing-over-time#ran","syntology_url":"https://syntology.ai/paper/2307.09009","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09009"}},"official":{"repos":["lchen001/llmdrift"],"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":["listed","official"]}}},{"url":"/paper/leandojo-theorem-proving-with-retrieval-1","slug":"leandojo-theorem-proving-with-retrieval-1","title":"LeanDojo: Theorem Proving with Retrieval-Augmented Language Models","date":"2023-06-27","arxiv_id":"2306.15626","repositories_listed":3,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"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) · 1 unverified","sample_list":"/paper/leandojo-theorem-proving-with-retrieval-1#ran","syntology_url":"https://syntology.ai/paper/2306.15626","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.15626"}},"official":{"repos":["lean-dojo/leandojo","lean-dojo/leandojochatgpt","lean-dojo/reprover"],"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":["official"]}}}],"record_sha256":"0a66861da7686cfd7acedf0ef7143ca9dbfad5b08617568adbc23bc90b5fcd23","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}