{"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-word-problem-solving","name":"Math Word Problem Solving","slug":"math-word-problem-solving","description_markdown":"A math word problem is a mathematical exercise (such as in a textbook, worksheet, or exam) where significant background information on the problem is presented in ordinary language rather than in mathematical notation. As most word problems involve a narrative of some sort, they are sometimes referred to as story problems and may vary in the amount of technical language used.","categories":[{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":107,"papers_with_code":80,"benchmarks":13,"benchmark_tables_in_archive":13,"benchmark_tables_shown":13,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":23,"subtasks":0,"parent_tasks":2},"benchmarks":[{"leaderboard":"/sota/math-word-problem-solving-on-math","slug":"math-word-problem-solving-on-math","dataset":"MATH","dataset_url":"/dataset/math","rows_in_archive":135,"metrics":["Accuracy","Parameters (Billions)"],"first_row_in_archive_order":{"model":"Gemini 2.0 Flash Experimental","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/math-word-problem-solving-on-svamp","slug":"math-word-problem-solving-on-svamp","dataset":"SVAMP","dataset_url":"/dataset/svamp","rows_in_archive":26,"metrics":["Execution Accuracy","Accuracy"],"first_row_in_archive_order":{"model":"GPT-4 (Teaching-Inspired)","paper_title":"Teaching-Inspired Integrated Prompting Framework: A Novel Approach for Enhancing Reasoning in Large Language Models","paper_url":"/paper/teaching-inspired-integrated-prompting","paper_date":"2024-10-10","arxiv_id":"2410.08068","code_links":[{"title":"sallytan13/teaching-inspired-prompting","url":"https://github.com/sallytan13/teaching-inspired-prompting"}],"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":8,"phrase":"8 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; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/teaching-inspired-integrated-prompting#ran","syntology_url":"https://syntology.ai/paper/2410.08068","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08068"}},"official":{"repos":["sallytan13/teaching-inspired-prompting"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/math-word-problem-solving-on-mawps","slug":"math-word-problem-solving-on-mawps","dataset":"MAWPS","dataset_url":"/dataset/mawps","rows_in_archive":25,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"OpenMath-CodeLlama-70B (w/ code)","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_url":"/paper/openmathinstruct-1-a-1-8-million-math","paper_date":"2024-02-15","arxiv_id":"2402.10176","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"syntology":null}},{"leaderboard":"/sota/math-word-problem-solving-on-math23k","slug":"math-word-problem-solving-on-math23k","dataset":"Math23K","dataset_url":"/dataset/math23k","rows_in_archive":19,"metrics":["Accuracy (5-fold)","Accuracy (training-test)","weakly-supervised"],"first_row_in_archive_order":{"model":"GPT-4 (Teaching-Inspired)","paper_title":"Teaching-Inspired Integrated Prompting Framework: A Novel Approach for Enhancing Reasoning in Large Language Models","paper_url":"/paper/teaching-inspired-integrated-prompting","paper_date":"2024-10-10","arxiv_id":"2410.08068","code_links":[{"title":"sallytan13/teaching-inspired-prompting","url":"https://github.com/sallytan13/teaching-inspired-prompting"}],"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":8,"phrase":"8 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; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/teaching-inspired-integrated-prompting#ran","syntology_url":"https://syntology.ai/paper/2410.08068","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08068"}},"official":{"repos":["sallytan13/teaching-inspired-prompting"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/math-word-problem-solving-on-alg514","slug":"math-word-problem-solving-on-alg514","dataset":"ALG514","dataset_url":"/dataset/alg514","rows_in_archive":10,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"MixedSP","paper_title":"Learning from Explicit and Implicit Supervision Jointly For Algebra Word Problems","paper_url":"/paper/learning-from-explicit-and-implicit","paper_date":"2016-11-01","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/math-word-problem-solving-on-asdiv-a","slug":"math-word-problem-solving-on-asdiv-a","dataset":"ASDiv-A","dataset_url":"/dataset/asdiv","rows_in_archive":9,"metrics":["Execution Accuracy"],"first_row_in_archive_order":{"model":"ATHENA (roberta-large)","paper_title":"ATHENA: Mathematical Reasoning with Thought Expansion","paper_url":"/paper/athena-mathematical-reasoning-with-thought","paper_date":"2023-11-02","arxiv_id":"2311.01036","code_links":[{"title":"the-jb/athena-math","url":"https://github.com/the-jb/athena-math"}],"syntology":null}},{"leaderboard":"/sota/math-word-problem-solving-on-paramawps","slug":"math-word-problem-solving-on-paramawps","dataset":"ParaMAWPS","dataset_url":"/dataset/paramawps","rows_in_archive":6,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"DeBERTa (VM)","paper_title":"Math Word Problem Solving by Generating Linguistic Variants of Problem Statements","paper_url":"/paper/math-word-problem-solving-by-generating","paper_date":"2023-06-24","arxiv_id":"2306.13899","code_links":[{"title":"starscream-11813/variational-mathematical-reasoning","url":"https://github.com/starscream-11813/variational-mathematical-reasoning"}],"syntology":null}},{"leaderboard":"/sota/math-word-problem-solving-on-draw-1k","slug":"math-word-problem-solving-on-draw-1k","dataset":"DRAW-1K","dataset_url":"/dataset/draw-1k","rows_in_archive":5,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"EPT","paper_title":"EPT-X: An Expression-Pointer Transformer model that generates eXplanations for numbers","paper_url":"/paper/ept-x-an-expression-pointer-transformer-model","paper_date":"","arxiv_id":null,"code_links":[{"title":"snucclab/ept-x","url":"https://github.com/snucclab/ept-x"}],"syntology":null}},{"leaderboard":"/sota/math-word-problem-solving-on-mathqa","slug":"math-word-problem-solving-on-mathqa","dataset":"MathQA","dataset_url":"/dataset/mathqa","rows_in_archive":5,"metrics":["Answer Accuracy"],"first_row_in_archive_order":{"model":"ELASTIC (RoBERTa-large)","paper_title":"ELASTIC: Numerical Reasoning with Adaptive Symbolic Compiler","paper_url":"/paper/elastic-numerical-reasoning-with-adaptive","paper_date":"2022-10-18","arxiv_id":"2210.10105","code_links":[{"title":"neurasearch/neurips-2022-submission-3358","url":"https://github.com/neurasearch/neurips-2022-submission-3358"}],"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/elastic-numerical-reasoning-with-adaptive#ran","syntology_url":"https://syntology.ai/paper/2210.10105","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.10105"}},"official":{"repos":["neurasearch/neurips-2022-submission-3358"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/math-word-problem-solving-on-svamp-1-n","slug":"math-word-problem-solving-on-svamp-1-n","dataset":"SVAMP (1:N)","dataset_url":"/dataset/svamp","rows_in_archive":2,"metrics":["Execution Accuracy"],"first_row_in_archive_order":{"model":"ATHENA (roberta-large)","paper_title":"ATHENA: Mathematical Reasoning with Thought Expansion","paper_url":"/paper/athena-mathematical-reasoning-with-thought","paper_date":"2023-11-02","arxiv_id":"2311.01036","code_links":[{"title":"the-jb/athena-math","url":"https://github.com/the-jb/athena-math"}],"syntology":null}},{"leaderboard":"/sota/math-word-problem-solving-on-gsm-plus","slug":"math-word-problem-solving-on-gsm-plus","dataset":"GSM-Plus","dataset_url":"/dataset/gsm-plus","rows_in_archive":1,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"GPT-4","paper_title":"GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers","paper_url":"/paper/gsm-plus-a-comprehensive-benchmark-for","paper_date":"2024-02-29","arxiv_id":"2402.19255","code_links":[{"title":"qtli/gsm-plus","url":"https://github.com/qtli/gsm-plus"}],"syntology":null}},{"leaderboard":"/sota/math-word-problem-solving-on-math-minival","slug":"math-word-problem-solving-on-math-minival","dataset":"MATH minival","dataset_url":"/dataset/math","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Process Supervision (GPT-4)","paper_title":"Let's Verify Step by Step","paper_url":"/paper/let-s-verify-step-by-step-1","paper_date":"2023-05-31","arxiv_id":"2305.20050","code_links":[{"title":"openai/prm800k","url":"https://github.com/openai/prm800k"},{"title":"gentopia-ai/gentopia","url":"https://github.com/gentopia-ai/gentopia"},{"title":"consequentai/fneval","url":"https://github.com/consequentai/fneval"}],"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"]}}}},{"leaderboard":"/sota/math-word-problem-solving-on-pen","slug":"math-word-problem-solving-on-pen","dataset":"PEN","dataset_url":"/dataset/pen","rows_in_archive":1,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"EPT-X","paper_title":"EPT-X: An Expression-Pointer Transformer model that generates eXplanations for numbers","paper_url":"/paper/ept-x-an-expression-pointer-transformer-model","paper_date":"","arxiv_id":null,"code_links":[{"title":"snucclab/ept-x","url":"https://github.com/snucclab/ept-x"}],"syntology":null}}],"datasets":[{"url":"/dataset/math","name":"MATH","full_name":"","num_papers_in_archive":1330},{"url":"/dataset/svamp","name":"SVAMP","full_name":"Simple Variations on Arithmetic Math word Problems","num_papers_in_archive":362},{"url":"/dataset/mathvista","name":"MathVista","full_name":"Mathematical Reasoning of in Visual Contexts","num_papers_in_archive":242},{"url":"/dataset/mathqa","name":"MathQA","full_name":"","num_papers_in_archive":159},{"url":"/dataset/asdiv","name":"ASDiv","full_name":"Academia Sinica Diverse MWP Dataset","num_papers_in_archive":150},{"url":"/dataset/mawps","name":"MAWPS","full_name":"MAth Word ProblemS","num_papers_in_archive":122},{"url":"/dataset/mgsm","name":"MGSM","full_name":"Multilingual Grade School Math","num_papers_in_archive":107},{"url":"/dataset/math23k","name":"Math23K","full_name":"Math23K for Math Word Problem Solving","num_papers_in_archive":95},{"url":"/dataset/geometry3k","name":"Geometry3K","full_name":"","num_papers_in_archive":45},{"url":"/dataset/iconqa","name":"IconQA","full_name":"Icon Question Answering","num_papers_in_archive":42},{"url":"/dataset/geos","name":"GeoS","full_name":"","num_papers_in_archive":24},{"url":"/dataset/alg514","name":"ALG514","full_name":"","num_papers_in_archive":22},{"url":"/dataset/gsm-plus","name":"GSM-Plus","full_name":"","num_papers_in_archive":17},{"url":"/dataset/pgps9k","name":"PGPS9K","full_name":"","num_papers_in_archive":14},{"url":"/dataset/pen","name":"PEN","full_name":"Problems with Explanations for Numbers","num_papers_in_archive":5},{"url":"/dataset/draw-1k","name":"DRAW-1K","full_name":"Diverse Algebra Word Problem Set","num_papers_in_archive":4},{"url":"/dataset/dart-math-hard","name":"DART-Math-Hard","full_name":"","num_papers_in_archive":2},{"url":"/dataset/paramawps","name":"ParaMAWPS","full_name":"Paraphrased Math Word Problem Solving Repository","num_papers_in_archive":2},{"url":"/dataset/dart-math-uniform","name":"DART-Math-Uniform","full_name":"","num_papers_in_archive":1},{"url":"/dataset/synthetic-grade-school-math-sgsm","name":"Educational Grade School Math (EGSM)","full_name":"","num_papers_in_archive":1},{"url":"/dataset/mathmc","name":"MathMC","full_name":"","num_papers_in_archive":1},{"url":"/dataset/mathtof","name":"MathToF","full_name":"","num_papers_in_archive":1},{"url":"/dataset/mmos","name":"MMOS","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/mathematical-question-answering","name":"Mathematical Question Answering"},{"url":"/task/mathematical-reasoning","name":"Mathematical Reasoning"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":107,"of_with_code":80,"tagged_in_all":107,"counts":{"archive_papers_tagged":107,"with_a_code_link":80,"where_syntology_ran_a_sample":39,"not_listed_spam_title":0,"listed":107,"listed_where_code_ran":39,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":34,"every_run_a_failure_of_syntologys_instrument":5,"listed_with_a_run_with_no_instrument_failure":34,"listed_every_run_a_failure_of_syntologys_instrument":5,"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"},"items":[{"url":"/paper/llama-open-and-efficient-foundation-language-1","slug":"llama-open-and-efficient-foundation-language-1","title":"LLaMA: Open and Efficient Foundation Language Models","date":"2023-02-27","arxiv_id":"2302.13971","repositories_listed":57,"syntology":{"n":58,"n_ran":37,"n_constructed":9,"n_ran_checked":25,"n_instrument":12,"n_unverified":21,"n_honours":3,"n_violates":0,"n_no_contract":22,"n_pointer_only":4,"phrase":"37 ran (of which 9 constructed an object rather than computing a result; 25 with no instrument failure: 3 honoured, 0 violated, 22 with no contract checked; 12 where Syntology's instrument failed) · 21 unverified","sample_list":"/paper/llama-open-and-efficient-foundation-language-1#ran","syntology_url":"https://syntology.ai/paper/2302.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13971"}},"official":{"repos":["facebookresearch/llama"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/llama-2-open-foundation-and-fine-tuned-chat","slug":"llama-2-open-foundation-and-fine-tuned-chat","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","date":"2023-07-18","arxiv_id":"2307.09288","repositories_listed":19,"syntology":{"n":52,"n_ran":33,"n_constructed":7,"n_ran_checked":20,"n_instrument":13,"n_unverified":19,"n_honours":1,"n_violates":1,"n_no_contract":18,"n_pointer_only":20,"phrase":"33 ran (of which 7 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 1 violated, 18 with no contract checked; 13 where Syntology's instrument failed) · 19 unverified","sample_list":"/paper/llama-2-open-foundation-and-fine-tuned-chat#ran","syntology_url":"https://syntology.ai/paper/2307.09288","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09288"}},"official":{"repos":["facebookresearch/llama"],"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/deberta-decoding-enhanced-bert-with","slug":"deberta-decoding-enhanced-bert-with","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","date":"2020-06-05","arxiv_id":"2006.03654","repositories_listed":14,"syntology":{"n":13,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":9,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/deberta-decoding-enhanced-bert-with#ran","syntology_url":"https://syntology.ai/paper/2006.03654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.03654"}},"official":{"repos":["microsoft/DeBERTa"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","named_in_paper","unlocated"]}}},{"url":"/paper/analysing-mathematical-reasoning-abilities-of-1","slug":"analysing-mathematical-reasoning-abilities-of-1","title":"Analysing Mathematical Reasoning Abilities of Neural Models","date":"2019-04-02","arxiv_id":"1904.01557","repositories_listed":7,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/analysing-mathematical-reasoning-abilities-of-1#ran","syntology_url":"https://syntology.ai/paper/1904.01557","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01557"}},"official":null}},{"url":"/paper/qwen2-technical-report","slug":"qwen2-technical-report","title":"Qwen2 Technical Report","date":"2024-07-15","arxiv_id":"2407.10671","repositories_listed":6,"syntology":null},{"url":"/paper/mixtral-of-experts","slug":"mixtral-of-experts","title":"Mixtral of Experts","date":"2024-01-08","arxiv_id":"2401.04088","repositories_listed":6,"syntology":{"n":5,"n_ran":5,"n_constructed":5,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 5 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) · 0 unverified; every one of the 5 samples that ran constructed an object rather than computing a result","sample_list":"/paper/mixtral-of-experts#ran","syntology_url":"https://syntology.ai/paper/2401.04088","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.04088"}},"official":null}},{"url":"/paper/mistral-7b","slug":"mistral-7b","title":"Mistral 7B","date":"2023-10-10","arxiv_id":"2310.06825","repositories_listed":6,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mistral-7b#ran","syntology_url":"https://syntology.ai/paper/2310.06825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06825"}},"official":{"repos":["mistralai/mistral-src"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/deepseekmath-pushing-the-limits-of","slug":"deepseekmath-pushing-the-limits-of","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","date":"2024-02-05","arxiv_id":"2402.03300","repositories_listed":5,"syntology":{"n":24,"n_ran":14,"n_constructed":0,"n_ran_checked":3,"n_instrument":11,"n_unverified":10,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"14 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; 11 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/deepseekmath-pushing-the-limits-of#ran","syntology_url":"https://syntology.ai/paper/2402.03300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03300"}},"official":{"repos":["deepseek-ai/deepseek-math"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","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/large-language-models-are-zero-shot-reasoners","slug":"large-language-models-are-zero-shot-reasoners","title":"Large Language Models are Zero-Shot Reasoners","date":"2022-05-24","arxiv_id":"2205.11916","repositories_listed":4,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/large-language-models-are-zero-shot-reasoners#ran","syntology_url":"https://syntology.ai/paper/2205.11916","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.11916"}},"official":{"repos":["kojima-takeshi188/zero_shot_cot"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/math-shepherd-a-label-free-step-by-step","slug":"math-shepherd-a-label-free-step-by-step","title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations","date":"2023-12-14","arxiv_id":"2312.08935","repositories_listed":3,"syntology":null},{"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/sparks-of-artificial-general-intelligence","slug":"sparks-of-artificial-general-intelligence","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","date":"2023-03-22","arxiv_id":"2303.12712","repositories_listed":3,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/sparks-of-artificial-general-intelligence#ran","syntology_url":"https://syntology.ai/paper/2303.12712","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.12712"}},"official":null}},{"url":"/paper/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/are-nlp-models-really-able-to-solve-simple","slug":"are-nlp-models-really-able-to-solve-simple","title":"Are NLP Models really able to Solve Simple Math Word Problems?","date":"2021-03-12","arxiv_id":"2103.07191","repositories_listed":3,"syntology":null},{"url":"/paper/parameter-efficient-sparsity-crafting-from","slug":"parameter-efficient-sparsity-crafting-from","title":"Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks","date":"2024-01-05","arxiv_id":"2401.02731","repositories_listed":2,"syntology":null},{"url":"/paper/an-empirical-study-on-challenging-math","slug":"an-empirical-study-on-challenging-math","title":"MathChat: Converse to Tackle Challenging Math Problems with LLM Agents","date":"2023-06-02","arxiv_id":"2306.01337","repositories_listed":2,"syntology":null},{"url":"/paper/reticl-sequential-retrieval-of-in-context","slug":"reticl-sequential-retrieval-of-in-context","title":"RetICL: Sequential Retrieval of In-Context Examples with Reinforcement Learning","date":"2023-05-23","arxiv_id":"2305.14502","repositories_listed":2,"syntology":null},{"url":"/paper/logicsolver-towards-interpretable-math-word","slug":"logicsolver-towards-interpretable-math-word","title":"LogicSolver: Towards Interpretable Math Word Problem Solving with Logical Prompt-enhanced Learning","date":"2022-05-17","arxiv_id":"2205.08232","repositories_listed":2,"syntology":null},{"url":"/paper/a-diversity-enhanced-knowledge-distillation","slug":"a-diversity-enhanced-knowledge-distillation","title":"A Diversity-Enhanced Knowledge Distillation Model for Practical Math Word Problem Solving","date":"2025-01-07","arxiv_id":"2501.03670","repositories_listed":1,"syntology":null},{"url":"/paper/sbi-rag-enhancing-math-word-problem-solving","slug":"sbi-rag-enhancing-math-word-problem-solving","title":"SBI-RAG: Enhancing Math Word Problem Solving for Students through Schema-Based Instruction and Retrieval-Augmented Generation","date":"2024-10-17","arxiv_id":"2410.13293","repositories_listed":1,"syntology":null},{"url":"/paper/teaching-inspired-integrated-prompting","slug":"teaching-inspired-integrated-prompting","title":"Teaching-Inspired Integrated Prompting Framework: A Novel Approach for Enhancing Reasoning in Large Language Models","date":"2024-10-10","arxiv_id":"2410.08068","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":8,"phrase":"8 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; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/teaching-inspired-integrated-prompting#ran","syntology_url":"https://syntology.ai/paper/2410.08068","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08068"}},"official":{"repos":["sallytan13/teaching-inspired-prompting"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/openmathinstruct-2-accelerating-ai-for-math","slug":"openmathinstruct-2-accelerating-ai-for-math","title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","date":"2024-10-02","arxiv_id":"2410.01560","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":5,"n_instrument":7,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/openmathinstruct-2-accelerating-ai-for-math#ran","syntology_url":"https://syntology.ai/paper/2410.01560","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01560"}},"official":null}},{"url":"/paper/step-dpo-step-wise-preference-optimization","slug":"step-dpo-step-wise-preference-optimization","title":"Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs","date":"2024-06-26","arxiv_id":"2406.18629","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":5,"n_instrument":6,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":12,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/step-dpo-step-wise-preference-optimization#ran","syntology_url":"https://syntology.ai/paper/2406.18629","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18629"}},"official":{"repos":["dvlab-research/step-dpo"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/dart-math-difficulty-aware-rejection-tuning-1","slug":"dart-math-difficulty-aware-rejection-tuning-1","title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","date":"2024-06-18","arxiv_id":"2407.13690","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":2,"n_instrument":8,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/dart-math-difficulty-aware-rejection-tuning-1#ran","syntology_url":"https://syntology.ai/paper/2407.13690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.13690"}},"official":{"repos":["hkust-nlp/dart-math"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/alphamath-almost-zero-process-supervision","slug":"alphamath-almost-zero-process-supervision","title":"AlphaMath Almost Zero: Process Supervision without Process","date":"2024-05-06","arxiv_id":"2405.03553","repositories_listed":1,"syntology":null},{"url":"/paper/achieving-97-on-gsm8k-deeply-understanding","slug":"achieving-97-on-gsm8k-deeply-understanding","title":"Achieving >97% on GSM8K: Deeply Understanding the Problems Makes LLMs Better Solvers for Math Word Problems","date":"2024-04-23","arxiv_id":"2404.14963","repositories_listed":1,"syntology":null},{"url":"/paper/toward-self-improvement-of-llms-via","slug":"toward-self-improvement-of-llms-via","title":"Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing","date":"2024-04-18","arxiv_id":"2404.12253","repositories_listed":1,"syntology":{"n":18,"n_ran":14,"n_constructed":1,"n_ran_checked":5,"n_instrument":9,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":18,"phrase":"14 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 9 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/toward-self-improvement-of-llms-via#ran","syntology_url":"https://syntology.ai/paper/2404.12253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.12253"}},"official":{"repos":["yetianjhu/alphallm"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":1,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/macm-utilizing-a-multi-agent-system-for","slug":"macm-utilizing-a-multi-agent-system-for","title":"MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems","date":"2024-04-06","arxiv_id":"2404.04735","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/macm-utilizing-a-multi-agent-system-for#ran","syntology_url":"https://syntology.ai/paper/2404.04735","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.04735"}},"official":{"repos":["bin123apple/macm"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/branch-train-mix-mixing-expert-llms-into-a","slug":"branch-train-mix-mixing-expert-llms-into-a","title":"Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM","date":"2024-03-12","arxiv_id":"2403.07816","repositories_listed":1,"syntology":null},{"url":"/paper/gemini-1-5-unlocking-multimodal-understanding","slug":"gemini-1-5-unlocking-multimodal-understanding","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","date":"2024-03-08","arxiv_id":"2403.05530","repositories_listed":1,"syntology":null},{"url":"/paper/gsm-plus-a-comprehensive-benchmark-for","slug":"gsm-plus-a-comprehensive-benchmark-for","title":"GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers","date":"2024-02-29","arxiv_id":"2402.19255","repositories_listed":1,"syntology":null},{"url":"/paper/an-empirical-study-of-data-ability-boundary","slug":"an-empirical-study-of-data-ability-boundary","title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","date":"2024-02-23","arxiv_id":"2403.00799","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":11,"phrase":"9 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; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/an-empirical-study-of-data-ability-boundary#ran","syntology_url":"https://syntology.ai/paper/2403.00799","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00799"}},"official":{"repos":["cyzhh/MMOS"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/openmathinstruct-1-a-1-8-million-math","slug":"openmathinstruct-1-a-1-8-million-math","title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","date":"2024-02-15","arxiv_id":"2402.10176","repositories_listed":1,"syntology":null},{"url":"/paper/augmenting-math-word-problems-via-iterative","slug":"augmenting-math-word-problems-via-iterative","title":"Augmenting Math Word Problems via Iterative Question Composing","date":"2024-01-17","arxiv_id":"2401.09003","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"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, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/augmenting-math-word-problems-via-iterative#ran","syntology_url":"https://syntology.ai/paper/2401.09003","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.09003"}},"official":{"repos":["iiis-ai/iterativequestioncomposing"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/frugal-lms-trained-to-invoke-symbolic-solvers","slug":"frugal-lms-trained-to-invoke-symbolic-solvers","title":"Frugal LMs Trained to Invoke Symbolic Solvers Achieve Parameter-Efficient Arithmetic Reasoning","date":"2023-12-09","arxiv_id":"2312.05571","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/frugal-lms-trained-to-invoke-symbolic-solvers#ran","syntology_url":"https://syntology.ai/paper/2312.05571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.05571"}},"official":{"repos":["joykirat18/syrelm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/knowledgemath-knowledge-intensive-math-word","slug":"knowledgemath-knowledge-intensive-math-word","title":"FinanceMath: Knowledge-Intensive Math Reasoning in Finance Domains","date":"2023-11-16","arxiv_id":"2311.09797","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":15,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/knowledgemath-knowledge-intensive-math-word#ran","syntology_url":"https://syntology.ai/paper/2311.09797","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09797"}},"official":{"repos":["yale-nlp/knowledgemath"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/veritymath-advancing-mathematical-reasoning","slug":"veritymath-advancing-mathematical-reasoning","title":"VerityMath: Advancing Mathematical Reasoning by Self-Verification Through Unit Consistency","date":"2023-11-13","arxiv_id":"2311.07172","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/veritymath-advancing-mathematical-reasoning#ran","syntology_url":"https://syntology.ai/paper/2311.07172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.07172"}},"official":{"repos":["vernontoh/veritymath"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/athena-mathematical-reasoning-with-thought","slug":"athena-mathematical-reasoning-with-thought","title":"ATHENA: Mathematical Reasoning with Thought Expansion","date":"2023-11-02","arxiv_id":"2311.01036","repositories_listed":1,"syntology":null},{"url":"/paper/an-expression-tree-decoding-strategy-for","slug":"an-expression-tree-decoding-strategy-for","title":"An Expression Tree Decoding Strategy for Mathematical Equation Generation","date":"2023-10-14","arxiv_id":"2310.09619","repositories_listed":1,"syntology":null},{"url":"/paper/query-and-response-augmentation-cannot-help","slug":"query-and-response-augmentation-cannot-help","title":"MuggleMath: Assessing the Impact of Query and Response Augmentation on Math Reasoning","date":"2023-10-09","arxiv_id":"2310.05506","repositories_listed":1,"syntology":null},{"url":"/paper/mathcoder-seamless-code-integration-in-llms","slug":"mathcoder-seamless-code-integration-in-llms","title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","date":"2023-10-05","arxiv_id":"2310.03731","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mathcoder-seamless-code-integration-in-llms#ran","syntology_url":"https://syntology.ai/paper/2310.03731","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03731"}},"official":{"repos":["mathllm/mathcoder"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tora-a-tool-integrated-reasoning-agent-for","slug":"tora-a-tool-integrated-reasoning-agent-for","title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","date":"2023-09-29","arxiv_id":"2309.17452","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":5,"n_instrument":6,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":9,"phrase":"11 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; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tora-a-tool-integrated-reasoning-agent-for#ran","syntology_url":"https://syntology.ai/paper/2309.17452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17452"}},"official":{"repos":["microsoft/tora"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/metamath-bootstrap-your-own-mathematical","slug":"metamath-bootstrap-your-own-mathematical","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","date":"2023-09-21","arxiv_id":"2309.12284","repositories_listed":1,"syntology":{"n":22,"n_ran":15,"n_constructed":0,"n_ran_checked":1,"n_instrument":14,"n_unverified":7,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 14 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/metamath-bootstrap-your-own-mathematical#ran","syntology_url":"https://syntology.ai/paper/2309.12284","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.12284"}},"official":{"repos":["meta-math/MetaMath"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/openchat-advancing-open-source-language","slug":"openchat-advancing-open-source-language","title":"OpenChat: Advancing Open-source Language Models with Mixed-Quality Data","date":"2023-09-20","arxiv_id":"2309.11235","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/openchat-advancing-open-source-language#ran","syntology_url":"https://syntology.ai/paper/2309.11235","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.11235"}},"official":{"repos":["imoneoi/openchat"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"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":7,"n_instrument":3,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":16,"phrase":"10 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; 3 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/do-multilingual-language-models-think-better","slug":"do-multilingual-language-models-think-better","title":"Do Multilingual Language Models Think Better in English?","date":"2023-08-02","arxiv_id":"2308.01223","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":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) · 2 unverified","sample_list":"/paper/do-multilingual-language-models-think-better#ran","syntology_url":"https://syntology.ai/paper/2308.01223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.01223"}},"official":{"repos":["juletx/self-translate"],"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/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/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/automatic-model-selection-with-large-language","slug":"automatic-model-selection-with-large-language","title":"Automatic Model Selection with Large Language Models for Reasoning","date":"2023-05-23","arxiv_id":"2305.14333","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/automatic-model-selection-with-large-language#ran","syntology_url":"https://syntology.ai/paper/2305.14333","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14333"}},"official":{"repos":["xuzhao0/model-selection-reasoning"],"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/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/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/galactica-a-large-language-model-for-science-1","slug":"galactica-a-large-language-model-for-science-1","title":"Galactica: A Large Language Model for Science","date":"2022-11-16","arxiv_id":"2211.09085","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/galactica-a-large-language-model-for-science-1#ran","syntology_url":"https://syntology.ai/paper/2211.09085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09085"}},"official":{"repos":["paperswithcode/galai"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-view-reasoning-consistent-contrastive","slug":"multi-view-reasoning-consistent-contrastive","title":"Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problem","date":"2022-10-21","arxiv_id":"2210.11694","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/multi-view-reasoning-consistent-contrastive#ran","syntology_url":"https://syntology.ai/paper/2210.11694","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.11694"}},"official":{"repos":["zwq2018/multi-view-consistency-for-mwp"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/elastic-numerical-reasoning-with-adaptive","slug":"elastic-numerical-reasoning-with-adaptive","title":"ELASTIC: Numerical Reasoning with Adaptive Symbolic Compiler","date":"2022-10-18","arxiv_id":"2210.10105","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/elastic-numerical-reasoning-with-adaptive#ran","syntology_url":"https://syntology.ai/paper/2210.10105","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.10105"}},"official":{"repos":["neurasearch/neurips-2022-submission-3358"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/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/solving-quantitative-reasoning-problems-with","slug":"solving-quantitative-reasoning-problems-with","title":"Solving Quantitative Reasoning Problems with Language Models","date":"2022-06-29","arxiv_id":"2206.14858","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/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/an-edge-enhanced-hierarchical-graph-to-tree","slug":"an-edge-enhanced-hierarchical-graph-to-tree","title":"An Edge-Enhanced Hierarchical Graph-to-Tree Network for Math Word Problem Solving","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/iconqa-a-new-benchmark-for-abstract-diagram","slug":"iconqa-a-new-benchmark-for-abstract-diagram","title":"IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning","date":"2021-10-25","arxiv_id":"2110.13214","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/iconqa-a-new-benchmark-for-abstract-diagram#ran","syntology_url":"https://syntology.ai/paper/2110.13214","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.13214"}},"official":{"repos":["lupantech/iconqa"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/recall-and-learn-a-memory-augmented-solver","slug":"recall-and-learn-a-memory-augmented-solver","title":"Recall and Learn: A Memory-augmented Solver for Math Word Problems","date":"2021-09-27","arxiv_id":"2109.13112","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-examples-for-evaluating-math-word","slug":"adversarial-examples-for-evaluating-math-word","title":"Adversarial Examples for Evaluating Math Word Problem Solvers","date":"2021-09-13","arxiv_id":"2109.05925","repositories_listed":1,"syntology":null},{"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/math-word-problem-solving-with-explicit","slug":"math-word-problem-solving-with-explicit","title":"Math Word Problem Solving with Explicit Numerical Values","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"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/point-to-the-expression-solving-algebraic","slug":"point-to-the-expression-solving-algebraic","title":"Point to the Expression: Solving Algebraic Word Problems using the Expression-Pointer Transformer Model","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"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/reverse-operation-based-data-augmentation-for","slug":"reverse-operation-based-data-augmentation-for","title":"Reverse Operation based Data Augmentation for Solving Math Word Problems","date":"2020-10-04","arxiv_id":"2010.01556","repositories_listed":1,"syntology":null},{"url":"/paper/ape210k-a-large-scale-and-template-rich","slug":"ape210k-a-large-scale-and-template-rich","title":"Ape210K: A Large-Scale and Template-Rich Dataset of Math Word Problems","date":"2020-09-24","arxiv_id":"2009.11506","repositories_listed":1,"syntology":null},{"url":"/paper/graph-to-tree-learning-for-solving-math-word","slug":"graph-to-tree-learning-for-solving-math-word","title":"Graph-to-Tree Learning for Solving Math Word Problems","date":"2020-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"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/a-goal-driven-tree-structured-neural-model","slug":"a-goal-driven-tree-structured-neural-model","title":"A Goal-Driven Tree-Structured Neural Model for Math Word Problems","date":"2019-08-10","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/modeling-intra-relation-in-math-word-problems","slug":"modeling-intra-relation-in-math-word-problems","title":"Modeling Intra-Relation in Math Word Problems with Different Functional Multi-Head Attentions","date":"2019-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/translating-a-math-word-problem-to-an","slug":"translating-a-math-word-problem-to-an","title":"Translating a Math Word Problem to an Expression Tree","date":"2018-11-14","arxiv_id":"1811.05632","repositories_listed":1,"syntology":null},{"url":"/paper/semantically-aligned-equation-generation-for","slug":"semantically-aligned-equation-generation-for","title":"Semantically-Aligned Equation Generation for Solving and Reasoning Math Word Problems","date":"2018-11-02","arxiv_id":"1811.00720","repositories_listed":1,"syntology":null},{"url":"/paper/mawps-a-math-word-problem-repository","slug":"mawps-a-math-word-problem-repository","title":"MAWPS: A Math Word Problem Repository","date":"2016-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":null,"slug":"learning-by-analogy-enhancing-few-shot","title":"Learning by Analogy: Enhancing Few-Shot Prompting for Math Word Problem Solving with Computational Graph-Based Retrieval","date":"2024-11-25","arxiv_id":"2411.16454","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-not-to-answer-evaluating-prompts-on-gpt","title":"When Not to Answer: Evaluating Prompts on GPT Models for Effective Abstention in Unanswerable Math Word Problems","date":"2024-10-16","arxiv_id":"2410.13029","repositories_listed":0,"syntology":null},{"url":"/paper/qwen2-5-math-technical-report-toward","slug":"qwen2-5-math-technical-report-toward","title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","date":"2024-09-18","arxiv_id":"2409.12122","repositories_listed":0,"syntology":null},{"url":null,"slug":"program-synthesis-benchmark-for-visual","title":"Program Synthesis Benchmark for Visual Programming in XLogoOnline Environment","date":"2024-06-17","arxiv_id":"2406.11334","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-augmentation-with-in-context-learning","title":"Data Augmentation with In-Context Learning and Comparative Evaluation in Math Word Problem Solving","date":"2024-04-05","arxiv_id":"2404.03938","repositories_listed":0,"syntology":null},{"url":"/paper/key-point-driven-data-synthesis-with-its","slug":"key-point-driven-data-synthesis-with-its","title":"Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning","date":"2024-03-04","arxiv_id":"2403.02333","repositories_listed":0,"syntology":null},{"url":"/paper/skills-in-context-prompting-unlocking","slug":"skills-in-context-prompting-unlocking","title":"Skills-in-Context Prompting: Unlocking Compositionality in Large Language Models","date":"2023-08-01","arxiv_id":"2308.00304","repositories_listed":0,"syntology":null},{"url":null,"slug":"cmath-can-your-language-model-pass-chinese","title":"CMATH: Can Your Language Model Pass Chinese Elementary School Math Test?","date":"2023-06-29","arxiv_id":"2306.16636","repositories_listed":0,"syntology":null},{"url":null,"slug":"2305-14386","title":"Let GPT be a Math Tutor: Teaching Math Word Problem Solvers with Customized Exercise Generation","date":"2023-05-22","arxiv_id":"2305.14386","repositories_listed":0,"syntology":null},{"url":null,"slug":"mwp-bert-numeracy-augmented-pre-training-for","title":"MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem Solving","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-interpretable-math-word-problem","title":"Towards Interpretable Math Word Problem Solving with Grounded Linguistic Logic Reasoning","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/generate-rank-a-multi-task-framework-for-math","slug":"generate-rank-a-multi-task-framework-for-math","title":"Generate & Rank: A Multi-task Framework for Math Word Problems","date":"2021-09-07","arxiv_id":"2109.03034","repositories_listed":0,"syntology":null},{"url":"/paper/generating-equation-by-utilizing-operators","slug":"generating-equation-by-utilizing-operators","title":"Generating Equation by Utilizing Operators : GEO model","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-knowledge-aware-sequence-to-tree-network","title":"A Knowledge-Aware Sequence-to-Tree Network for Math Word Problem Solving","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-chinese-math-word-problem-solving-system","title":"A Chinese Math Word Problem Solving System Based on Linguistic Theory and Non-statistical Approach","date":"2020-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/mathqa-towards-interpretable-math-word","slug":"mathqa-towards-interpretable-math-word","title":"MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms","date":"2019-05-30","arxiv_id":"1905.13319","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-improved-coarse-to-fine-method-for-solving","title":"An Improved Coarse-to-Fine Method for Solving Generation Tasks","date":"2019-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"translating-a-math-word-problem-to-a","title":"Translating a Math Word Problem to a Expression Tree","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-math-word-problem-solver-with","title":"Neural Math Word Problem Solver with Reinforcement Learning","date":"2018-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"using-intermediate-representations-to-solve","title":"Using Intermediate Representations to Solve Math Word Problems","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":41,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"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)"},"since_archive_judged":{"papers":74,"papers_placed":1,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/math-word-problem-solving-on-math","since_archive":"/sota/math-word-problem-solving-on-math#since-judged","papers_judged":53,"placed":0},{"leaderboard":"/sota/math-word-problem-solving-on-svamp","since_archive":"/sota/math-word-problem-solving-on-svamp#since-judged","papers_judged":18,"placed":0},{"leaderboard":"/sota/math-word-problem-solving-on-mawps","since_archive":"/sota/math-word-problem-solving-on-mawps#since-judged","papers_judged":2,"placed":1},{"leaderboard":"/sota/math-word-problem-solving-on-asdiv-a","since_archive":"/sota/math-word-problem-solving-on-asdiv-a#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/math-word-problem-solving-on-mathqa","since_archive":"/sota/math-word-problem-solving-on-mathqa#since-judged","papers_judged":4,"placed":0},{"leaderboard":"/sota/math-word-problem-solving-on-math-minival","since_archive":"/sota/math-word-problem-solving-on-math-minival#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":39,"papers_where_code_ran_first_page":"/task/math-word-problem-solving/papers/ran/1","papers_where_code_ran_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.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/math-word-problem-solving/papers/2","json":"/task/math-word-problem-solving/papers/2.json","rows":7},{"order":"ran","page":1,"of":1,"url":"/task/math-word-problem-solving/papers/ran/1","json":"/task/math-word-problem-solving/papers/ran/1.json","rows":39}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"a448b6d02009aac681c7be4d75ee76bb53e81704b7a69a70e393109759b9fcf1","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}