{"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/7","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":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":7,"pages_in_order":16,"rows_per_page":100,"rows":[601,700],"of":1596,"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","prev":"/task/math/papers/6","next":"/task/math/papers/8","papers":[{"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/solving-math-word-problem-with-problem-type","slug":"solving-math-word-problem-with-problem-type","title":"Solving Math Word Problem with Problem Type Classification","date":"2023-08-26","arxiv_id":"2308.13844","repositories_listed":1,"syntology":null},{"url":"/paper/wizardmath-empowering-mathematical-reasoning","slug":"wizardmath-empowering-mathematical-reasoning","title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","date":"2023-08-18","arxiv_id":"2308.09583","repositories_listed":1,"syntology":{"n":16,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":16,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/wizardmath-empowering-mathematical-reasoning#ran","syntology_url":"https://syntology.ai/paper/2308.09583","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09583"}},"official":null}},{"url":"/paper/solving-challenging-math-word-problems-using","slug":"solving-challenging-math-word-problems-using","title":"Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification","date":"2023-08-15","arxiv_id":"2308.07921","repositories_listed":1,"syntology":null},{"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/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/exploring-automated-distractor-and-feedback","slug":"exploring-automated-distractor-and-feedback","title":"Automated Distractor and Feedback Generation for Math Multiple-choice Questions via In-context Learning","date":"2023-08-07","arxiv_id":"2308.03234","repositories_listed":1,"syntology":null},{"url":"/paper/scalable-and-equitable-math-problem-solving","slug":"scalable-and-equitable-math-problem-solving","title":"Scalable and Equitable Math Problem Solving Strategy Prediction in Big Educational Data","date":"2023-08-07","arxiv_id":"2308.03892","repositories_listed":1,"syntology":null},{"url":"/paper/a-symbolic-character-aware-model-for-solving","slug":"a-symbolic-character-aware-model-for-solving","title":"A Symbolic Character-Aware Model for Solving Geometry Problems","date":"2023-08-05","arxiv_id":"2308.02823","repositories_listed":1,"syntology":null},{"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/reasoning-in-large-language-models-through","slug":"reasoning-in-large-language-models-through","title":"Reasoning in Large Language Models Through Symbolic Math Word Problems","date":"2023-08-03","arxiv_id":"2308.01906","repositories_listed":1,"syntology":null},{"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/augmented-math-authoring-ar-based-explorable","slug":"augmented-math-authoring-ar-based-explorable","title":"Augmented Math: Authoring AR-Based Explorable Explanations by Augmenting Static Math Textbooks","date":"2023-07-30","arxiv_id":"2307.16112","repositories_listed":1,"syntology":null},{"url":"/paper/a-large-language-model-assisted-education","slug":"a-large-language-model-assisted-education","title":"A large language model-assisted education tool to provide feedback on open-ended responses","date":"2023-07-25","arxiv_id":"2308.02439","repositories_listed":1,"syntology":null},{"url":"/paper/a-mixed-policy-to-improve-performance-of","slug":"a-mixed-policy-to-improve-performance-of","title":"A mixed policy to improve performance of language models on math problems","date":"2023-07-17","arxiv_id":"2307.08767","repositories_listed":1,"syntology":null},{"url":"/paper/math-word-problem-solving-by-generating","slug":"math-word-problem-solving-by-generating","title":"Math Word Problem Solving by Generating Linguistic Variants of Problem Statements","date":"2023-06-24","arxiv_id":"2306.13899","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-on-multimodal-large-language-models","slug":"a-survey-on-multimodal-large-language-models","title":"A Survey on Multimodal Large Language Models","date":"2023-06-23","arxiv_id":"2306.13549","repositories_listed":1,"syntology":null},{"url":"/paper/tracking-public-attitudes-toward-chatgpt-on","slug":"tracking-public-attitudes-toward-chatgpt-on","title":"Public Attitudes Toward ChatGPT on Twitter: Sentiments, Topics, and Occupations","date":"2023-06-22","arxiv_id":"2306.12951","repositories_listed":1,"syntology":null},{"url":"/paper/learning-by-analogy-diverse-questions","slug":"learning-by-analogy-diverse-questions","title":"Learning by Analogy: Diverse Questions Generation in Math Word Problem","date":"2023-06-15","arxiv_id":"2306.09064","repositories_listed":1,"syntology":null},{"url":"/paper/sight-a-large-annotated-dataset-on-student","slug":"sight-a-large-annotated-dataset-on-student","title":"SIGHT: A Large Annotated Dataset on Student Insights Gathered from Higher Education Transcripts","date":"2023-06-15","arxiv_id":"2306.09343","repositories_listed":1,"syntology":null},{"url":"/paper/promptbench-towards-evaluating-the-robustness","slug":"promptbench-towards-evaluating-the-robustness","title":"PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts","date":"2023-06-07","arxiv_id":"2306.04528","repositories_listed":1,"syntology":null},{"url":"/paper/world-models-for-math-story-problems","slug":"world-models-for-math-story-problems","title":"World Models for Math Story Problems","date":"2023-06-07","arxiv_id":"2306.04347","repositories_listed":1,"syntology":null},{"url":"/paper/is-chatgpt-a-good-teacher-coach-measuring","slug":"is-chatgpt-a-good-teacher-coach-measuring","title":"Is ChatGPT a Good Teacher Coach? Measuring Zero-Shot Performance For Scoring and Providing Actionable Insights on Classroom Instruction","date":"2023-06-05","arxiv_id":"2306.03090","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-and-improving-tool-augmented-1","slug":"evaluating-and-improving-tool-augmented-1","title":"Evaluating and Improving Tool-Augmented Computation-Intensive Math Reasoning","date":"2023-06-04","arxiv_id":"2306.02408","repositories_listed":1,"syntology":null},{"url":"/paper/does-chatgpt-comprehend-the-place-value-in","slug":"does-chatgpt-comprehend-the-place-value-in","title":"Does ChatGPT Comprehend the Place Value in Numbers When Solving Math Word Problems?","date":"2023-06-03","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learning-multi-step-reasoning-from-arithmetic","slug":"learning-multi-step-reasoning-from-arithmetic","title":"Learning Multi-Step Reasoning by Solving Arithmetic Tasks","date":"2023-06-02","arxiv_id":"2306.01707","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-training-data-in-few-shot","slug":"leveraging-training-data-in-few-shot","title":"Leveraging Training Data in Few-Shot Prompting for Numerical Reasoning","date":"2023-05-29","arxiv_id":"2305.18170","repositories_listed":1,"syntology":null},{"url":"/paper/complex-mathematical-symbol-definition","slug":"complex-mathematical-symbol-definition","title":"Complex Mathematical Symbol Definition Structures: A Dataset and Model for Coordination Resolution in Definition Extraction","date":"2023-05-24","arxiv_id":"2305.14660","repositories_listed":1,"syntology":null},{"url":"/paper/discriminator-guided-multi-step-reasoning","slug":"discriminator-guided-multi-step-reasoning","title":"GRACE: Discriminator-Guided Chain-of-Thought Reasoning","date":"2023-05-24","arxiv_id":"2305.14934","repositories_listed":1,"syntology":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/unlocking-temporal-question-answering-for","slug":"unlocking-temporal-question-answering-for","title":"Unlocking Temporal Question Answering for Large Language Models with Tailor-Made Reasoning Logic","date":"2023-05-24","arxiv_id":"2305.15014","repositories_listed":1,"syntology":null},{"url":"/paper/chatcot-tool-augmented-chain-of-thought","slug":"chatcot-tool-augmented-chain-of-thought","title":"ChatCoT: Tool-Augmented Chain-of-Thought Reasoning on Chat-based Large Language Models","date":"2023-05-23","arxiv_id":"2305.14323","repositories_listed":1,"syntology":null},{"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/teimma-the-first-content-reuse-annotator-for","slug":"teimma-the-first-content-reuse-annotator-for","title":"TEIMMA: The First Content Reuse Annotator for Text, Images, and Math","date":"2023-05-22","arxiv_id":"2305.13193","repositories_listed":1,"syntology":null},{"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/a-quantitative-study-of-nlp-approaches-to","slug":"a-quantitative-study-of-nlp-approaches-to","title":"A quantitative study of NLP approaches to question difficulty estimation","date":"2023-05-17","arxiv_id":"2305.10236","repositories_listed":1,"syntology":null},{"url":"/paper/learning-non-linguistic-skills-without","slug":"learning-non-linguistic-skills-without","title":"Learning Non-linguistic Skills without Sacrificing Linguistic Proficiency","date":"2023-05-14","arxiv_id":"2305.08246","repositories_listed":1,"syntology":null},{"url":"/paper/algebra-error-classification-with-large","slug":"algebra-error-classification-with-large","title":"Algebra Error Classification with Large Language Models","date":"2023-05-08","arxiv_id":"2305.06163","repositories_listed":1,"syntology":null},{"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/enhancing-textbooks-with-visuals-from-the-web","slug":"enhancing-textbooks-with-visuals-from-the-web","title":"Enhancing Textbooks with Visuals from the Web for Improved Learning","date":"2023-04-18","arxiv_id":"2304.08931","repositories_listed":1,"syntology":null},{"url":"/paper/solving-math-word-problems-by-combining","slug":"solving-math-word-problems-by-combining","title":"Solving Math Word Problems by Combining Language Models With Symbolic Solvers","date":"2023-04-16","arxiv_id":"2304.09102","repositories_listed":1,"syntology":null},{"url":"/paper/from-zero-to-hero-convincing-with-extremely","slug":"from-zero-to-hero-convincing-with-extremely","title":"From Zero to Hero: Convincing with Extremely Complicated Math","date":"2023-04-01","arxiv_id":"2304.00399","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-the-impact-of-instruction-data","slug":"exploring-the-impact-of-instruction-data","title":"Exploring the Impact of Instruction Data Scaling on Large Language Models: An Empirical Study on Real-World Use Cases","date":"2023-03-26","arxiv_id":"2303.14742","repositories_listed":1,"syntology":null},{"url":"/paper/how-well-do-large-language-models-perform-in","slug":"how-well-do-large-language-models-perform-in","title":"How well do Large Language Models perform in Arithmetic tasks?","date":"2023-03-16","arxiv_id":"2304.02015","repositories_listed":1,"syntology":null},{"url":"/paper/salsa-picante-a-machine-learning-attack-on","slug":"salsa-picante-a-machine-learning-attack-on","title":"SALSA PICANTE: a machine learning attack on LWE with binary secrets","date":"2023-03-07","arxiv_id":"2303.04178","repositories_listed":1,"syntology":null},{"url":"/paper/mathprompter-mathematical-reasoning-using","slug":"mathprompter-mathematical-reasoning-using","title":"MathPrompter: Mathematical Reasoning using Large Language Models","date":"2023-03-04","arxiv_id":"2303.05398","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mathprompter-mathematical-reasoning-using#ran","syntology_url":"https://syntology.ai/paper/2303.05398","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.05398"}},"official":null}},{"url":"/paper/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/tree-based-representation-and-generation-of","slug":"tree-based-representation-and-generation-of","title":"Tree-Based Representation and Generation of Natural and Mathematical Language","date":"2023-02-15","arxiv_id":"2302.07974","repositories_listed":1,"syntology":null},{"url":"/paper/a-categorical-archive-of-chatgpt-failures","slug":"a-categorical-archive-of-chatgpt-failures","title":"A Categorical Archive of ChatGPT Failures","date":"2023-02-06","arxiv_id":"2302.03494","repositories_listed":1,"syntology":null},{"url":"/paper/techniques-to-improve-neural-math-word","slug":"techniques-to-improve-neural-math-word","title":"Techniques to Improve Neural Math Word Problem Solvers","date":"2023-02-06","arxiv_id":"2302.03145","repositories_listed":1,"syntology":null},{"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/large-language-models-can-be-easily","slug":"large-language-models-can-be-easily","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","date":"2023-01-31","arxiv_id":"2302.00093","repositories_listed":1,"syntology":null},{"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/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/tracing-and-manipulating-intermediate-values","slug":"tracing-and-manipulating-intermediate-values","title":"Tracing and Manipulating Intermediate Values in Neural Math Problem Solvers","date":"2023-01-17","arxiv_id":"2301.06758","repositories_listed":1,"syntology":null},{"url":"/paper/deterministic-and-nondeterministic-particle","slug":"deterministic-and-nondeterministic-particle","title":"Deterministic and Nondeterministic Particle Motion with Interaction Mechanisms","date":"2022-12-31","arxiv_id":"2301.00297","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-of-deep-learning-for-mathematical","slug":"a-survey-of-deep-learning-for-mathematical","title":"A Survey of Deep Learning for Mathematical Reasoning","date":"2022-12-20","arxiv_id":"2212.10535","repositories_listed":1,"syntology":null},{"url":"/paper/matcha-enhancing-visual-language-pretraining","slug":"matcha-enhancing-visual-language-pretraining","title":"MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derendering","date":"2022-12-19","arxiv_id":"2212.09662","repositories_listed":1,"syntology":null},{"url":"/paper/skellam-mixture-mechanism-a-novel-approach-to","slug":"skellam-mixture-mechanism-a-novel-approach-to","title":"Skellam Mixture Mechanism: a Novel Approach to Federated Learning with Differential Privacy","date":"2022-12-08","arxiv_id":"2212.04371","repositories_listed":1,"syntology":null},{"url":"/paper/analogical-math-word-problems-solving-with","slug":"analogical-math-word-problems-solving-with","title":"Analogical Math Word Problems Solving with Enhanced Problem-Solution Association","date":"2022-12-01","arxiv_id":"2212.00837","repositories_listed":1,"syntology":null},{"url":"/paper/generalizing-math-word-problem-solvers-via","slug":"generalizing-math-word-problem-solvers-via","title":"Generalizing Math Word Problem Solvers via Solution Diversification","date":"2022-12-01","arxiv_id":"2212.00833","repositories_listed":1,"syntology":null},{"url":"/paper/textual-enhanced-contrastive-learning-for","slug":"textual-enhanced-contrastive-learning-for","title":"Textual Enhanced Contrastive Learning for Solving Math Word Problems","date":"2022-11-29","arxiv_id":"2211.16022","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-generation-of-socratic-subquestions","slug":"automatic-generation-of-socratic-subquestions","title":"Automatic Generation of Socratic Subquestions for Teaching Math Word Problems","date":"2022-11-23","arxiv_id":"2211.12835","repositories_listed":1,"syntology":null},{"url":"/paper/dyrren-a-dynamic-retriever-reranker-generator","slug":"dyrren-a-dynamic-retriever-reranker-generator","title":"DyRRen: A Dynamic Retriever-Reranker-Generator Model for Numerical Reasoning over Tabular and Textual Data","date":"2022-11-23","arxiv_id":"2211.12668","repositories_listed":1,"syntology":null},{"url":"/paper/the-ncte-transcripts-a-dataset-of-elementary","slug":"the-ncte-transcripts-a-dataset-of-elementary","title":"The NCTE Transcripts: A Dataset of Elementary Math Classroom Transcripts","date":"2022-11-21","arxiv_id":"2211.11772","repositories_listed":1,"syntology":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/mining-mathematical-documents-for-question","slug":"mining-mathematical-documents-for-question","title":"Mining Mathematical Documents for Question Answering via Unsupervised Formula Labeling","date":"2022-11-12","arxiv_id":"2211.06664","repositories_listed":1,"syntology":null},{"url":"/paper/what-is-my-math-transformer-doing-three","slug":"what-is-my-math-transformer-doing-three","title":"What is my math transformer doing? -- Three results on interpretability and generalization","date":"2022-10-31","arxiv_id":"2211.00170","repositories_listed":1,"syntology":null},{"url":"/paper/solving-math-word-problem-via-cooperative","slug":"solving-math-word-problem-via-cooperative","title":"Solving Math Word Problems via Cooperative Reasoning induced Language Models","date":"2022-10-28","arxiv_id":"2210.16257","repositories_listed":1,"syntology":null},{"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/structure-unified-m-tree-coding-solver-for","slug":"structure-unified-m-tree-coding-solver-for","title":"Structure-Unified M-Tree Coding Solver for MathWord Problem","date":"2022-10-22","arxiv_id":"2210.12432","repositories_listed":1,"syntology":null},{"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/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/comsearch-equation-searching-with-2","slug":"comsearch-equation-searching-with-2","title":"ComSearch: Equation Searching with Combinatorial Strategy for Solving Math Word Problems with Weak Supervision","date":"2022-10-13","arxiv_id":"2210.07017","repositories_listed":1,"syntology":null},{"url":"/paper/warm-a-weakly-semi-supervised-math-word-1","slug":"warm-a-weakly-semi-supervised-math-word-1","title":"WARM: A Weakly (+Semi) Supervised Math Word Problem Solver","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":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/seeking-diverse-reasoning-logic-controlled","slug":"seeking-diverse-reasoning-logic-controlled","title":"Seeking Diverse Reasoning Logic: Controlled Equation Expression Generation for Solving Math Word Problems","date":"2022-09-21","arxiv_id":"2209.10310","repositories_listed":1,"syntology":null},{"url":"/paper/improving-compositional-generalization-in-2","slug":"improving-compositional-generalization-in-2","title":"Improving Compositional Generalization in Math Word Problem Solving","date":"2022-09-03","arxiv_id":"2209.01352","repositories_listed":1,"syntology":null},{"url":"/paper/can-we-use-small-models-to-investigate","slug":"can-we-use-small-models-to-investigate","title":"Can We Use Small Models to Investigate Multimodal Fusion Methods?","date":"2022-09-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/formulanet-a-benchmark-dataset-for","slug":"formulanet-a-benchmark-dataset-for","title":"FormulaNet: A Benchmark Dataset for Mathematical Formula Detection","date":"2022-08-29","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/clevr-math-a-dataset-for-compositional","slug":"clevr-math-a-dataset-for-compositional","title":"CLEVR-Math: A Dataset for Compositional Language, Visual and Mathematical Reasoning","date":"2022-08-10","arxiv_id":"2208.05358","repositories_listed":1,"syntology":null},{"url":"/paper/wide-deep-learning-for-judging-student","slug":"wide-deep-learning-for-judging-student","title":"Wide & Deep Learning for Judging Student Performance in Online One-on-one Math Classes","date":"2022-07-13","arxiv_id":"2207.10645","repositories_listed":1,"syntology":null},{"url":"/paper/computationally-identifying-funneling-and-1","slug":"computationally-identifying-funneling-and-1","title":"Computationally Identifying Funneling and Focusing Questions in Classroom Discourse","date":"2022-07-08","arxiv_id":"2208.04715","repositories_listed":1,"syntology":null},{"url":"/paper/aifb-webscience-at-semeval-2022-task-12-1","slug":"aifb-webscience-at-semeval-2022-task-12-1","title":"AIFB-WebScience at SemEval-2022 Task 12: Relation Extraction First - Using Relation Extraction to Identify Entities","date":"2022-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-robustly-optimized-long-text-to-math-models","slug":"a-robustly-optimized-long-text-to-math-models","title":"A Robustly Optimized Long Text to Math Models for Numerical Reasoning On FinQA","date":"2022-06-29","arxiv_id":"2207.06490","repositories_listed":1,"syntology":null},{"url":"/paper/jiuzhang-a-chinese-pre-trained-language-model","slug":"jiuzhang-a-chinese-pre-trained-language-model","title":"JiuZhang: A Chinese Pre-trained Language Model for Mathematical Problem Understanding","date":"2022-06-13","arxiv_id":"2206.06315","repositories_listed":1,"syntology":null},{"url":"/paper/armath-a-dataset-for-solving-arabic-math-word","slug":"armath-a-dataset-for-solving-arabic-math-word","title":"ArMATH: a Dataset for Solving Arabic Math Word Problems","date":"2022-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/building-dataset-for-grounding-of-formulae","slug":"building-dataset-for-grounding-of-formulae","title":"Building Dataset for Grounding of Formulae — Annotating Coreference Relations Among Math Identifiers","date":"2022-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/automatic-short-math-answer-grading-via-in","slug":"automatic-short-math-answer-grading-via-in","title":"Automatic Short Math Answer Grading via In-context Meta-learning","date":"2022-05-30","arxiv_id":"2205.15219","repositories_listed":1,"syntology":null},{"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/least-to-most-prompting-enables-complex","slug":"least-to-most-prompting-enables-complex","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","date":"2022-05-21","arxiv_id":"2205.10625","repositories_listed":1,"syntology":null},{"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/continual-pre-training-of-language-models-for-1","slug":"continual-pre-training-of-language-models-for-1","title":"Continual Pre-training of Language Models for Math Problem Understanding with Syntax-Aware Memory Network","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/ept-x-an-expression-pointer-transformer-model","slug":"ept-x-an-expression-pointer-transformer-model","title":"EPT-X: An Expression-Pointer Transformer model that generates eXplanations for numbers","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/practice-makes-a-solver-perfect-data","slug":"practice-makes-a-solver-perfect-data","title":"Practice Makes a Solver Perfect: Data Augmentation for Math Word Problem Solvers","date":"2022-04-30","arxiv_id":"2205.00177","repositories_listed":1,"syntology":null},{"url":"/paper/symforce-symbolic-computation-and-code","slug":"symforce-symbolic-computation-and-code","title":"SymForce: Symbolic Computation and Code Generation for Robotics","date":"2022-04-17","arxiv_id":"2204.07889","repositories_listed":1,"syntology":null},{"url":"/paper/assessing-hierarchies-by-their-consistent","slug":"assessing-hierarchies-by-their-consistent","title":"Assessing hierarchies by their consistent segmentations","date":"2022-04-11","arxiv_id":"2204.04969","repositories_listed":1,"syntology":null},{"url":"/paper/the-talkmoves-dataset-k-12-mathematics-lesson","slug":"the-talkmoves-dataset-k-12-mathematics-lesson","title":"The TalkMoves Dataset: K-12 Mathematics Lesson Transcripts Annotated for Teacher and Student Discursive Moves","date":"2022-04-06","arxiv_id":"2204.09652","repositories_listed":1,"syntology":null}],"record_sha256":"64eed27783b74fcb860a7d17e6b3f77efc1c7037187dfa4dfbdec2d6d63cb3c6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}