{"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/4","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":4,"pages_in_order":4,"rows_per_page":100,"rows":[301,349],"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/3","next":null,"papers":[{"url":"/paper/awq-activation-aware-weight-quantization-for","slug":"awq-activation-aware-weight-quantization-for","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","date":"2023-06-01","arxiv_id":"2306.00978","repositories_listed":12,"syntology":{"n":18,"n_ran":16,"n_constructed":1,"n_ran_checked":14,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":4,"phrase":"16 ran (of which 1 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/awq-activation-aware-weight-quantization-for#ran","syntology_url":"https://syntology.ai/paper/2306.00978","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00978"}},"official":{"repos":["internlm/lmdeploy","mit-han-lab/llm-awq","nvidia/tensorrt-llm","vllm-project/vllm"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["found_in_text","listed","official"]}}},{"url":"/paper/let-s-verify-step-by-step-1","slug":"let-s-verify-step-by-step-1","title":"Let's Verify Step by Step","date":"2023-05-31","arxiv_id":"2305.20050","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/let-s-verify-step-by-step-1#ran","syntology_url":"https://syntology.ai/paper/2305.20050","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.20050"}},"official":{"repos":["openai/prm800k"],"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/reasoning-with-language-model-is-planning","slug":"reasoning-with-language-model-is-planning","title":"Reasoning with Language Model is Planning with World Model","date":"2023-05-24","arxiv_id":"2305.14992","repositories_listed":3,"syntology":{"n":7,"n_ran":4,"n_constructed":2,"n_ran_checked":2,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/reasoning-with-language-model-is-planning#ran","syntology_url":"https://syntology.ai/paper/2305.14992","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14992"}},"official":null}},{"url":"/paper/the-art-of-socratic-questioning-zero-shot","slug":"the-art-of-socratic-questioning-zero-shot","title":"The Art of SOCRATIC QUESTIONING: Recursive Thinking with Large Language Models","date":"2023-05-24","arxiv_id":"2305.14999","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"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 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/the-art-of-socratic-questioning-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2305.14999","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14999"}},"official":{"repos":["vt-nlp/socratic-questioning"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mathdial-a-dialogue-tutoring-dataset-with","slug":"mathdial-a-dialogue-tutoring-dataset-with","title":"MathDial: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problems","date":"2023-05-23","arxiv_id":"2305.14536","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":1,"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; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mathdial-a-dialogue-tutoring-dataset-with#ran","syntology_url":"https://syntology.ai/paper/2305.14536","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14536"}},"official":{"repos":["eth-nlped/mathdial"],"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"]}}},{"url":"/paper/theoremqa-a-theorem-driven-question-answering","slug":"theoremqa-a-theorem-driven-question-answering","title":"TheoremQA: A Theorem-driven Question Answering dataset","date":"2023-05-21","arxiv_id":"2305.12524","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/theoremqa-a-theorem-driven-question-answering#ran","syntology_url":"https://syntology.ai/paper/2305.12524","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.12524"}},"official":{"repos":["wenhuchen/theoremqa"],"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":["found_in_text","official"]}}},{"url":"/paper/codet5-open-code-large-language-models-for","slug":"codet5-open-code-large-language-models-for","title":"CodeT5+: Open Code Large Language Models for Code Understanding and Generation","date":"2023-05-13","arxiv_id":"2305.07922","repositories_listed":2,"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/codet5-open-code-large-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2305.07922","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.07922"}},"official":{"repos":["salesforce/codet5"],"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/non-autoregressive-math-word-problem-solver","slug":"non-autoregressive-math-word-problem-solver","title":"Non-Autoregressive Math Word Problem Solver with Unified Tree Structure","date":"2023-05-08","arxiv_id":"2305.04556","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":2,"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 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/non-autoregressive-math-word-problem-solver#ran","syntology_url":"https://syntology.ai/paper/2305.04556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.04556"}},"official":{"repos":["mengqunhan/mwp-nas"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/progressive-hint-prompting-improves-reasoning","slug":"progressive-hint-prompting-improves-reasoning","title":"Progressive-Hint Prompting Improves Reasoning in Large Language Models","date":"2023-04-19","arxiv_id":"2304.09797","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/progressive-hint-prompting-improves-reasoning#ran","syntology_url":"https://syntology.ai/paper/2304.09797","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.09797"}},"official":{"repos":["chuanyang-Zheng/Progressive-Hint"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/agieval-a-human-centric-benchmark-for","slug":"agieval-a-human-centric-benchmark-for","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","date":"2023-04-13","arxiv_id":"2304.06364","repositories_listed":3,"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/agieval-a-human-centric-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2304.06364","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.06364"}},"official":{"repos":["ruixiangcui/agieval"],"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/gpt-4-technical-report-1","slug":"gpt-4-technical-report-1","title":"GPT-4 Technical Report","date":"2023-03-15","arxiv_id":"2303.08774","repositories_listed":11,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gpt-4-technical-report-1#ran","syntology_url":"https://syntology.ai/paper/2303.08774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08774"}},"official":{"repos":["openai/evals"],"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/mathprompter-mathematical-reasoning-using","slug":"mathprompter-mathematical-reasoning-using","title":"MathPrompter: Mathematical Reasoning using Large Language Models","date":"2023-03-04","arxiv_id":"2303.05398","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mathprompter-mathematical-reasoning-using#ran","syntology_url":"https://syntology.ai/paper/2303.05398","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.05398"}},"official":null}},{"url":"/paper/an-independent-evaluation-of-chatgpt-on","slug":"an-independent-evaluation-of-chatgpt-on","title":"An Independent Evaluation of ChatGPT on Mathematical Word Problems (MWP)","date":"2023-02-23","arxiv_id":"2302.13814","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/an-independent-evaluation-of-chatgpt-on#ran","syntology_url":"https://syntology.ai/paper/2302.13814","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13814"}},"official":{"repos":["lab-v2/chatgpt_mwp_eval"],"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/lever-learning-to-verify-language-to-code","slug":"lever-learning-to-verify-language-to-code","title":"LEVER: Learning to Verify Language-to-Code Generation with Execution","date":"2023-02-16","arxiv_id":"2302.08468","repositories_listed":1,"syntology":{"n":22,"n_ran":18,"n_constructed":0,"n_ran_checked":18,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":17,"n_pointer_only":1,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 1 violated, 17 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/lever-learning-to-verify-language-to-code#ran","syntology_url":"https://syntology.ai/paper/2302.08468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.08468"}},"official":{"repos":["niansong1996/lever"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":0,"n_ran_no_instrument_failure":18,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/faithful-chain-of-thought-reasoning","slug":"faithful-chain-of-thought-reasoning","title":"Faithful Chain-of-Thought Reasoning","date":"2023-01-31","arxiv_id":"2301.13379","repositories_listed":1,"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/faithful-chain-of-thought-reasoning#ran","syntology_url":"https://syntology.ai/paper/2301.13379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.13379"}},"official":{"repos":["veronica320/faithful-cot"],"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"]}}},{"url":"/paper/specializing-smaller-language-models-towards","slug":"specializing-smaller-language-models-towards","title":"Specializing Smaller Language Models towards Multi-Step Reasoning","date":"2023-01-30","arxiv_id":"2301.12726","repositories_listed":2,"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/specializing-smaller-language-models-towards#ran","syntology_url":"https://syntology.ai/paper/2301.12726","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12726"}},"official":{"repos":["FranxYao/FlanT5-CoT-Specialization"],"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/thoughtsource-a-central-hub-for-large","slug":"thoughtsource-a-central-hub-for-large","title":"ThoughtSource: A central hub for large language model reasoning data","date":"2023-01-27","arxiv_id":"2301.11596","repositories_listed":1,"syntology":{"n":7,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/thoughtsource-a-central-hub-for-large#ran","syntology_url":"https://syntology.ai/paper/2301.11596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.11596"}},"official":{"repos":["openbiolink/thoughtsource"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-models-are-latent-variable-1","slug":"large-language-models-are-latent-variable-1","title":"Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning","date":"2023-01-27","arxiv_id":"2301.11916","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/large-language-models-are-latent-variable-1#ran","syntology_url":"https://syntology.ai/paper/2301.11916","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.11916"}},"official":{"repos":["wangxinyilinda/concept-based-demonstration-selection"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/unigeo-unifying-geometry-logical-reasoning","slug":"unigeo-unifying-geometry-logical-reasoning","title":"UniGeo: Unifying Geometry Logical Reasoning via Reformulating Mathematical Expression","date":"2022-12-06","arxiv_id":"2212.02746","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/unigeo-unifying-geometry-logical-reasoning#ran","syntology_url":"https://syntology.ai/paper/2212.02746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.02746"}},"official":{"repos":["chen-judge/unigeo"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/program-of-thoughts-prompting-disentangling","slug":"program-of-thoughts-prompting-disentangling","title":"Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks","date":"2022-11-22","arxiv_id":"2211.12588","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/program-of-thoughts-prompting-disentangling#ran","syntology_url":"https://syntology.ai/paper/2211.12588","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.12588"}},"official":{"repos":["wenhuchen/program-of-thoughts"],"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/pal-program-aided-language-models","slug":"pal-program-aided-language-models","title":"PAL: Program-aided Language Models","date":"2022-11-18","arxiv_id":"2211.10435","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pal-program-aided-language-models#ran","syntology_url":"https://syntology.ai/paper/2211.10435","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.10435"}},"official":null}},{"url":"/paper/galactica-a-large-language-model-for-science-1","slug":"galactica-a-large-language-model-for-science-1","title":"Galactica: A Large Language Model for Science","date":"2022-11-16","arxiv_id":"2211.09085","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/galactica-a-large-language-model-for-science-1#ran","syntology_url":"https://syntology.ai/paper/2211.09085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09085"}},"official":{"repos":["paperswithcode/galai"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/broken-neural-scaling-laws","slug":"broken-neural-scaling-laws","title":"Broken Neural Scaling Laws","date":"2022-10-26","arxiv_id":"2210.14891","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":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/broken-neural-scaling-laws#ran","syntology_url":"https://syntology.ai/paper/2210.14891","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.14891"}},"official":{"repos":["ethancaballero/broken_neural_scaling_laws"],"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/multi-view-reasoning-consistent-contrastive","slug":"multi-view-reasoning-consistent-contrastive","title":"Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problem","date":"2022-10-21","arxiv_id":"2210.11694","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/multi-view-reasoning-consistent-contrastive#ran","syntology_url":"https://syntology.ai/paper/2210.11694","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.11694"}},"official":{"repos":["zwq2018/multi-view-consistency-for-mwp"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/a-causal-framework-to-quantify-the-robustness","slug":"a-causal-framework-to-quantify-the-robustness","title":"A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models","date":"2022-10-21","arxiv_id":"2210.12023","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":2,"n_ran_checked":3,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-causal-framework-to-quantify-the-robustness#ran","syntology_url":"https://syntology.ai/paper/2210.12023","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.12023"}},"official":{"repos":["alestolfo/causal-math"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/dynamic-prompt-learning-via-policy-gradient","slug":"dynamic-prompt-learning-via-policy-gradient","title":"Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning","date":"2022-09-29","arxiv_id":"2209.14610","repositories_listed":2,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/dynamic-prompt-learning-via-policy-gradient#ran","syntology_url":"https://syntology.ai/paper/2209.14610","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.14610"}},"official":null}},{"url":"/paper/efficient-non-parametric-optimizer-search-for","slug":"efficient-non-parametric-optimizer-search-for","title":"Efficient Non-Parametric Optimizer Search for Diverse Tasks","date":"2022-09-27","arxiv_id":"2209.13575","repositories_listed":1,"syntology":{"n":9,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/efficient-non-parametric-optimizer-search-for#ran","syntology_url":"https://syntology.ai/paper/2209.13575","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.13575"}},"official":{"repos":["ruocwang/efficient-optimizer-search"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/beyond-the-imitation-game-quantifying-and","slug":"beyond-the-imitation-game-quantifying-and","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","date":"2022-06-09","arxiv_id":"2206.04615","repositories_listed":6,"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/beyond-the-imitation-game-quantifying-and#ran","syntology_url":"https://syntology.ai/paper/2206.04615","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.04615"}},"official":{"repos":["google/BIG-bench"],"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/learning-from-self-sampled-correct-and","slug":"learning-from-self-sampled-correct-and","title":"Learning Math Reasoning from Self-Sampled Correct and Partially-Correct Solutions","date":"2022-05-28","arxiv_id":"2205.14318","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":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) · 4 unverified","sample_list":"/paper/learning-from-self-sampled-correct-and#ran","syntology_url":"https://syntology.ai/paper/2205.14318","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14318"}},"official":{"repos":["microsoft/tracecodegen"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/unbiased-math-word-problems-benchmark-for-1","slug":"unbiased-math-word-problems-benchmark-for-1","title":"Unbiased Math Word Problems Benchmark for Mitigating Solving Bias","date":"2022-05-17","arxiv_id":"2205.08108","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unbiased-math-word-problems-benchmark-for-1#ran","syntology_url":"https://syntology.ai/paper/2205.08108","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.08108"}},"official":{"repos":["yangzhch6/unbiasedmwp"],"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/math-kg-construction-and-applications-of","slug":"math-kg-construction-and-applications-of","title":"Math-KG: Construction and Applications of Mathematical Knowledge Graph","date":"2022-05-08","arxiv_id":"2205.03772","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":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/math-kg-construction-and-applications-of#ran","syntology_url":"https://syntology.ai/paper/2205.03772","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.03772"}},"official":{"repos":["wjn1996/mathematical-knowledge-entity-recognition"],"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/palm-scaling-language-modeling-with-pathways-1","slug":"palm-scaling-language-modeling-with-pathways-1","title":"PaLM: Scaling Language Modeling with Pathways","date":"2022-04-05","arxiv_id":"2204.02311","repositories_listed":7,"syntology":{"n":37,"n_ran":32,"n_constructed":16,"n_ran_checked":24,"n_instrument":8,"n_unverified":5,"n_honours":2,"n_violates":1,"n_no_contract":21,"n_pointer_only":0,"phrase":"32 ran (of which 16 constructed an object rather than computing a result; 24 with no instrument failure: 2 honoured, 1 violated, 21 with no contract checked; 8 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/palm-scaling-language-modeling-with-pathways-1#ran","syntology_url":"https://syntology.ai/paper/2204.02311","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02311"}},"official":null}},{"url":"/paper/self-consistency-improves-chain-of-thought","slug":"self-consistency-improves-chain-of-thought","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","date":"2022-03-21","arxiv_id":"2203.11171","repositories_listed":3,"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":0,"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/self-consistency-improves-chain-of-thought#ran","syntology_url":"https://syntology.ai/paper/2203.11171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.11171"}},"official":null}},{"url":"/paper/learning-to-reason-deductively-math-word","slug":"learning-to-reason-deductively-math-word","title":"Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction","date":"2022-03-19","arxiv_id":"2203.10316","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-to-reason-deductively-math-word#ran","syntology_url":"https://syntology.ai/paper/2203.10316","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.10316"}},"official":{"repos":["allanj/deductive-mwp"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/memorizing-transformers-1","slug":"memorizing-transformers-1","title":"Memorizing Transformers","date":"2022-03-16","arxiv_id":"2203.08913","repositories_listed":4,"syntology":{"n":34,"n_ran":23,"n_constructed":6,"n_ran_checked":18,"n_instrument":5,"n_unverified":11,"n_honours":3,"n_violates":1,"n_no_contract":14,"n_pointer_only":2,"phrase":"23 ran (of which 6 constructed an object rather than computing a result; 18 with no instrument failure: 3 honoured, 1 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/memorizing-transformers-1#ran","syntology_url":"https://syntology.ai/paper/2203.08913","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.08913"}},"official":{"repos":["lucidrains/memorizing-transformers-pytorch"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":6,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/chain-of-thought-prompting-elicits-reasoning","slug":"chain-of-thought-prompting-elicits-reasoning","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","date":"2022-01-28","arxiv_id":"2201.11903","repositories_listed":19,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/chain-of-thought-prompting-elicits-reasoning#ran","syntology_url":"https://syntology.ai/paper/2201.11903","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.11903"}},"official":null}},{"url":"/paper/a-neural-network-solves-and-generates","slug":"a-neural-network-solves-and-generates","title":"A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Level","date":"2021-12-31","arxiv_id":"2112.15594","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-neural-network-solves-and-generates#ran","syntology_url":"https://syntology.ai/paper/2112.15594","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.15594"}},"official":{"repos":["idrori/mathq"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/training-verifiers-to-solve-math-word","slug":"training-verifiers-to-solve-math-word","title":"Training Verifiers to Solve Math Word Problems","date":"2021-10-27","arxiv_id":"2110.14168","repositories_listed":6,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/training-verifiers-to-solve-math-word#ran","syntology_url":"https://syntology.ai/paper/2110.14168","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.14168"}},"official":{"repos":["openai/grade-school-math"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/pretrained-language-models-are-symbolic","slug":"pretrained-language-models-are-symbolic","title":"Pretrained Language Models are Symbolic Mathematics Solvers too!","date":"2021-10-07","arxiv_id":"2110.03501","repositories_listed":1,"syntology":{"n":14,"n_ran":9,"n_constructed":1,"n_ran_checked":7,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":3,"phrase":"9 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/pretrained-language-models-are-symbolic#ran","syntology_url":"https://syntology.ai/paper/2110.03501","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.03501"}},"official":{"repos":["softsys4ai/differentiable-proving"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":1,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/mwptoolkit-an-open-source-framework-for-deep","slug":"mwptoolkit-an-open-source-framework-for-deep","title":"MWPToolkit: An Open-Source Framework for Deep Learning-Based Math Word Problem Solvers","date":"2021-09-02","arxiv_id":"2109.00799","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":1,"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/mwptoolkit-an-open-source-framework-for-deep#ran","syntology_url":"https://syntology.ai/paper/2109.00799","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.00799"}},"official":{"repos":["lyh-yf/mwptoolkit"],"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/mwp-bert-a-strong-baseline-for-math-word","slug":"mwp-bert-a-strong-baseline-for-math-word","title":"MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem Solving","date":"2021-07-28","arxiv_id":"2107.13435","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mwp-bert-a-strong-baseline-for-math-word#ran","syntology_url":"https://syntology.ai/paper/2107.13435","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.13435"}},"official":{"repos":["lzhenwen/mwp-bert"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/neural-symbolic-solver-for-math-word-problems","slug":"neural-symbolic-solver-for-math-word-problems","title":"Neural-Symbolic Solver for Math Word Problems with Auxiliary Tasks","date":"2021-07-03","arxiv_id":"2107.01431","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"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) · 2 unverified","sample_list":"/paper/neural-symbolic-solver-for-math-word-problems#ran","syntology_url":"https://syntology.ai/paper/2107.01431","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.01431"}},"official":{"repos":["QinJinghui/NS-Solver"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/mathbert-a-pre-trained-language-model-for","slug":"mathbert-a-pre-trained-language-model-for","title":"MathBERT: A Pre-trained Language Model for General NLP Tasks in Mathematics Education","date":"2021-06-02","arxiv_id":"2106.07340","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":9,"phrase":"6 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mathbert-a-pre-trained-language-model-for#ran","syntology_url":"https://syntology.ai/paper/2106.07340","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.07340"}},"official":{"repos":["tbs17/MathBERT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/measuring-mathematical-problem-solving-with","slug":"measuring-mathematical-problem-solving-with","title":"Measuring Mathematical Problem Solving With the MATH Dataset","date":"2021-03-05","arxiv_id":"2103.03874","repositories_listed":5,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/measuring-mathematical-problem-solving-with#ran","syntology_url":"https://syntology.ai/paper/2103.03874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.03874"}},"official":{"repos":["hendrycks/math"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/semantically-aligned-universal-tree","slug":"semantically-aligned-universal-tree","title":"Semantically-Aligned Universal Tree-Structured Solver for Math Word Problems","date":"2020-10-14","arxiv_id":"2010.06823","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"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) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/semantically-aligned-universal-tree#ran","syntology_url":"https://syntology.ai/paper/2010.06823","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.06823"}},"official":{"repos":["QinJinghui/SAU-Solver"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/sipa-a-simple-framework-for-efficient","slug":"sipa-a-simple-framework-for-efficient","title":"SIPA: A Simple Framework for Efficient Networks","date":"2020-04-24","arxiv_id":"2004.14476","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":0,"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/sipa-a-simple-framework-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2004.14476","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.14476"}},"official":{"repos":["Lee-Gihun/MicroNet_OSI-AI"],"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/graph-to-tree-neural-networks-for-learning","slug":"graph-to-tree-neural-networks-for-learning","title":"Graph-to-Tree Neural Networks for Learning Structured Input-Output Translation with Applications to Semantic Parsing and Math Word Problem","date":"2020-04-07","arxiv_id":"2004.13781","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/graph-to-tree-neural-networks-for-learning#ran","syntology_url":"https://syntology.ai/paper/2004.13781","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.13781"}},"official":{"repos":["IBM/Graph2Tree"],"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/enhancing-the-transformer-with-explicit-1","slug":"enhancing-the-transformer-with-explicit-1","title":"Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving","date":"2019-10-15","arxiv_id":"1910.06611","repositories_listed":3,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"8 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; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/enhancing-the-transformer-with-explicit-1#ran","syntology_url":"https://syntology.ai/paper/1910.06611","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.06611"}},"official":{"repos":["ischlag/TP-Transformer"],"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/rethinking-floating-point-for-deep-learning","slug":"rethinking-floating-point-for-deep-learning","title":"Rethinking floating point for deep learning","date":"2018-11-01","arxiv_id":"1811.01721","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/rethinking-floating-point-for-deep-learning#ran","syntology_url":"https://syntology.ai/paper/1811.01721","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.01721"}},"official":{"repos":["facebookresearch/deepfloat"],"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"]}}}],"record_sha256":"6ba550fc3ccc69b14c77b8e434f3e88630ea783931792a7ffb59e36fdeda4e73","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}