{"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":"/dataset/gsm8k/papers/ran/1","list_of":"/dataset/gsm8k","dataset":"GSM8K","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","key_notes":{"samples_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'","samples_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)"},"order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"rows":[1,27],"of":27,"counts":{"papers_with_a_benchmark_row":58,"with_a_code_link":44,"where_syntology_ran_a_sample":27,"not_listed_spam_title":0,"listed":58,"listed_where_code_ran":27,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":25,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":25,"listed_every_run_a_failure_of_syntologys_instrument":2,"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 with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/dataset/gsm8k/papers/ran/1","prev":null,"next":null,"papers":[{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":8,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":8,"official":{"repos":["sallytan13/teaching-inspired-prompting"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":15,"samples_ran":12,"samples_constructed":0,"samples_ran_checked":12,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":12,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":12,"official":{"repos":["dvlab-research/step-dpo"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/breaking-the-ceiling-of-the-llm-community-by","slug":"breaking-the-ceiling-of-the-llm-community-by","title":"Breaking the Ceiling of the LLM Community by Treating Token Generation as a Classification for Ensembling","date":"2024-06-18","arxiv_id":"2406.12585","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["yaoching0/gac"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/breaking-the-ceiling-of-the-llm-community-by#ran","syntology_url":"https://syntology.ai/paper/2406.12585","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12585"}}}},{"paper":"/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","rows_on_this_dataset":8,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":12,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["hkust-nlp/dart-math"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":18,"samples_ran":14,"samples_constructed":1,"samples_ran_checked":12,"samples_ran_instrument_failed":2,"samples_unverified":4,"pointer_only_for_licence":18,"official":{"repos":["yetianjhu/alphallm"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":1,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":11,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":11,"official":{"repos":["cyzhh/MMOS"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":24,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":4,"samples_unverified":10,"pointer_only_for_licence":3,"official":{"repos":["deepseek-ai/deepseek-math"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/outcome-supervised-verifiers-for-planning-in","slug":"outcome-supervised-verifiers-for-planning-in","title":"OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoning","date":"2023-11-16","arxiv_id":"2311.09724","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["freedomintelligence/ovm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/outcome-supervised-verifiers-for-planning-in#ran","syntology_url":"https://syntology.ai/paper/2311.09724","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09724"}}}},{"paper":"/paper/llemma-an-open-language-model-for-mathematics","slug":"llemma-an-open-language-model-for-mathematics","title":"Llemma: An Open Language Model For Mathematics","date":"2023-10-16","arxiv_id":"2310.10631","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":8,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["EleutherAI/math-lm","eleutherai/gpt-neox","wellecks/llmstep"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/llemma-an-open-language-model-for-mathematics#ran","syntology_url":"https://syntology.ai/paper/2310.10631","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.10631"}}}},{"paper":"/paper/mistral-7b","slug":"mistral-7b","title":"Mistral 7B","date":"2023-10-10","arxiv_id":"2310.06825","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":2,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mistral-7b#ran","syntology_url":"https://syntology.ai/paper/2310.06825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06825"}}}},{"paper":"/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","rows_on_this_dataset":6,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":6,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":12,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":9,"official":{"repos":["microsoft/tora"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":22,"samples_ran":15,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":14,"samples_unverified":7,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":16,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":2,"samples_unverified":6,"pointer_only_for_licence":16,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/scaling-relationship-on-learning-mathematical","slug":"scaling-relationship-on-learning-mathematical","title":"Scaling Relationship on Learning Mathematical Reasoning with Large Language Models","date":"2023-08-03","arxiv_id":"2308.01825","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["ofa-sys/gsm8k-screl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/scaling-relationship-on-learning-mathematical#ran","syntology_url":"https://syntology.ai/paper/2308.01825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.01825"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":19,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":52,"samples_ran":33,"samples_constructed":7,"samples_ran_checked":22,"samples_ran_instrument_failed":11,"samples_unverified":19,"pointer_only_for_licence":20,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/codet5-open-code-large-language-models-for","slug":"codet5-open-code-large-language-models-for","title":"CodeT5+: Open Code Large Language Models for Code Understanding and Generation","date":"2023-05-13","arxiv_id":"2305.07922","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["salesforce/codet5"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/codet5-open-code-large-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2305.07922","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.07922"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":10,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/gpt-4-technical-report-1","slug":"gpt-4-technical-report-1","title":"GPT-4 Technical Report","date":"2023-03-15","arxiv_id":"2303.08774","rows_on_this_dataset":1,"code_links":11,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["openai/evals"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/gpt-4-technical-report-1#ran","syntology_url":"https://syntology.ai/paper/2303.08774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08774"}}}},{"paper":"/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","rows_on_this_dataset":8,"code_links":57,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":58,"samples_ran":37,"samples_constructed":9,"samples_ran_checked":25,"samples_ran_instrument_failed":12,"samples_unverified":21,"pointer_only_for_licence":4,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":22,"samples_ran":18,"samples_constructed":0,"samples_ran_checked":18,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":11,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":7,"code_links":4,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/unifying-language-learning-paradigms","slug":"unifying-language-learning-paradigms","title":"UL2: Unifying Language Learning Paradigms","date":"2022-05-10","arxiv_id":"2205.05131","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":16,"samples_ran":15,"samples_constructed":0,"samples_ran_checked":15,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unifying-language-learning-paradigms#ran","syntology_url":"https://syntology.ai/paper/2205.05131","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.05131"}}}},{"paper":"/paper/self-consistency-improves-chain-of-thought","slug":"self-consistency-improves-chain-of-thought","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","date":"2022-03-21","arxiv_id":"2203.11171","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/self-consistency-improves-chain-of-thought#ran","syntology_url":"https://syntology.ai/paper/2203.11171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.11171"}}}}],"record_sha256":"14d96bfa0830d211b81dd01a09b280e7f57afac38068ed86ecb219e152f83e37","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}