{"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/arithmetic-reasoning","name":"Arithmetic Reasoning","slug":"arithmetic-reasoning","description_markdown":null,"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":175,"papers_with_code":112,"benchmarks":5,"benchmark_tables_in_archive":5,"benchmark_tables_shown":5,"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":8,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/arithmetic-reasoning-on-gsm8k","slug":"arithmetic-reasoning-on-gsm8k","dataset":"GSM8K","dataset_url":"/dataset/gsm8k","rows_in_archive":164,"metrics":["Accuracy","Parameters (Billion)"],"first_row_in_archive_order":{"model":"Claude 3.5 Sonnet (HPT)","paper_title":"Hierarchical Prompting Taxonomy: A Universal Evaluation Framework for Large Language Models Aligned with Human Cognitive Principles","paper_url":"/paper/hierarchical-prompting-taxonomy-a-universal","paper_date":"2024-06-18","arxiv_id":"2406.12644","code_links":[{"title":"devichand579/HPT","url":"https://github.com/devichand579/HPT"}],"syntology":null}},{"leaderboard":"/sota/arithmetic-reasoning-on-multiarith","slug":"arithmetic-reasoning-on-multiarith","dataset":"MultiArith","dataset_url":null,"rows_in_archive":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Text-davinci-002 (175B)(zero-shot-cot)","paper_title":"Large Language Models are Zero-Shot Reasoners","paper_url":"/paper/large-language-models-are-zero-shot-reasoners","paper_date":"2022-05-24","arxiv_id":"2205.11916","code_links":[{"title":"kojima-takeshi188/zero_shot_cot","url":"https://github.com/kojima-takeshi188/zero_shot_cot"},{"title":"skytliang/multi-agents-debate","url":"https://github.com/skytliang/multi-agents-debate"},{"title":"zongqianwu/st-cot","url":"https://github.com/zongqianwu/st-cot"},{"title":"nicolay-r/reasoning-for-sentiment-analysis-framework","url":"https://github.com/nicolay-r/reasoning-for-sentiment-analysis-framework"}],"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"]}}}},{"leaderboard":"/sota/arithmetic-reasoning-on-game-of-24","slug":"arithmetic-reasoning-on-game-of-24","dataset":"Game of 24","dataset_url":"/dataset/game-of-24","rows_in_archive":1,"metrics":["Success"],"first_row_in_archive_order":{"model":"Tree of Thoughts (b=5)","paper_title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","paper_url":"/paper/tree-of-thoughts-deliberate-problem-solving-1","paper_date":"2023-05-17","arxiv_id":"2305.10601","code_links":[{"title":"ysymyth/tree-of-thought-llm","url":"https://github.com/ysymyth/tree-of-thought-llm"},{"title":"princeton-nlp/tree-of-thought-llm","url":"https://github.com/princeton-nlp/tree-of-thought-llm"},{"title":"codelion/optillm","url":"https://github.com/codelion/optillm"},{"title":"appl-team/appl","url":"https://github.com/appl-team/appl"},{"title":"huiwy/reflection-on-trees","url":"https://github.com/huiwy/reflection-on-trees"},{"title":"katamb/tree-of-thought-llm-ca","url":"https://github.com/katamb/tree-of-thought-llm-ca"}],"syntology":{"n":24,"n_ran":19,"n_constructed":6,"n_ran_checked":17,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":17,"n_pointer_only":1,"phrase":"19 ran (of which 6 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/tree-of-thoughts-deliberate-problem-solving-1#ran","syntology_url":"https://syntology.ai/paper/2305.10601","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.10601"}},"official":{"repos":["princeton-nlp/tree-of-thought-llm","ysymyth/tree-of-thought-llm"],"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":["community","listed","official"]}}}},{"leaderboard":"/sota/arithmetic-reasoning-on-mathmc","slug":"arithmetic-reasoning-on-mathmc","dataset":"MathMC","dataset_url":"/dataset/mathmc","rows_in_archive":1,"metrics":["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/arithmetic-reasoning-on-mathtof","slug":"arithmetic-reasoning-on-mathtof","dataset":"MathToF","dataset_url":"/dataset/mathtof","rows_in_archive":1,"metrics":["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"]}}}}],"datasets":[{"url":"/dataset/gsm8k","name":"GSM8K","full_name":"","num_papers_in_archive":1881},{"url":"/dataset/mgsm","name":"MGSM","full_name":"Multilingual Grade School Math","num_papers_in_archive":107},{"url":"/dataset/game-of-24","name":"Game of 24","full_name":"","num_papers_in_archive":61},{"url":"/dataset/gsm-plus","name":"GSM-Plus","full_name":"","num_papers_in_archive":17},{"url":"/dataset/smart-101","name":"SMART-101","full_name":"Simple Multimodal Algorithmic Reasoning Task Dataset","num_papers_in_archive":6},{"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/polymath","name":"PolyMATH","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"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":175,"of_with_code":112,"tagged_in_all":175,"counts":{"archive_papers_tagged":175,"with_a_code_link":112,"where_syntology_ran_a_sample":64,"not_listed_spam_title":0,"listed":175,"listed_where_code_ran":64,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":52,"every_run_a_failure_of_syntologys_instrument":12,"listed_with_a_run_with_no_instrument_failure":52,"listed_every_run_a_failure_of_syntologys_instrument":12,"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/gpt-4-technical-report-1","slug":"gpt-4-technical-report-1","title":"GPT-4 Technical Report","date":"2023-03-15","arxiv_id":"2303.08774","repositories_listed":11,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gpt-4-technical-report-1#ran","syntology_url":"https://syntology.ai/paper/2303.08774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08774"}},"official":{"repos":["openai/evals"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/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/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/tree-of-thoughts-deliberate-problem-solving-1","slug":"tree-of-thoughts-deliberate-problem-solving-1","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","date":"2023-05-17","arxiv_id":"2305.10601","repositories_listed":6,"syntology":{"n":24,"n_ran":19,"n_constructed":6,"n_ran_checked":17,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":17,"n_pointer_only":1,"phrase":"19 ran (of which 6 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/tree-of-thoughts-deliberate-problem-solving-1#ran","syntology_url":"https://syntology.ai/paper/2305.10601","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.10601"}},"official":{"repos":["princeton-nlp/tree-of-thought-llm","ysymyth/tree-of-thought-llm"],"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":["community","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/llemma-an-open-language-model-for-mathematics","slug":"llemma-an-open-language-model-for-mathematics","title":"Llemma: An Open Language Model For Mathematics","date":"2023-10-16","arxiv_id":"2310.10631","repositories_listed":4,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/llemma-an-open-language-model-for-mathematics#ran","syntology_url":"https://syntology.ai/paper/2310.10631","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.10631"}},"official":{"repos":["EleutherAI/math-lm","eleutherai/gpt-neox","wellecks/llmstep"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/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/neural-comprehension-language-models-with","slug":"neural-comprehension-language-models-with","title":"Mastering Symbolic Operations: Augmenting Language Models with Compiled Neural Networks","date":"2023-04-04","arxiv_id":"2304.01665","repositories_listed":3,"syntology":{"n":11,"n_ran":5,"n_constructed":2,"n_ran_checked":4,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/neural-comprehension-language-models-with#ran","syntology_url":"https://syntology.ai/paper/2304.01665","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.01665"}},"official":{"repos":["wengsyx/neural-comprehension"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["listed","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/self-consistency-improves-chain-of-thought","slug":"self-consistency-improves-chain-of-thought","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","date":"2022-03-21","arxiv_id":"2203.11171","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/self-consistency-improves-chain-of-thought#ran","syntology_url":"https://syntology.ai/paper/2203.11171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.11171"}},"official":null}},{"url":"/paper/capo-cost-aware-prompt-optimization","slug":"capo-cost-aware-prompt-optimization","title":"CAPO: Cost-Aware Prompt Optimization","date":"2025-04-22","arxiv_id":"2504.16005","repositories_listed":2,"syntology":null},{"url":"/paper/fed-sb-a-silver-bullet-for-extreme","slug":"fed-sb-a-silver-bullet-for-extreme","title":"Fed-SB: A Silver Bullet for Extreme Communication Efficiency and Performance in (Private) Federated LoRA Fine-Tuning","date":"2025-02-21","arxiv_id":"2502.15436","repositories_listed":2,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/fed-sb-a-silver-bullet-for-extreme#ran","syntology_url":"https://syntology.ai/paper/2502.15436","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.15436"}},"official":{"repos":["CERT-Lab/fed-sb"],"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/exact-aggregation-for-federated-and-efficient","slug":"exact-aggregation-for-federated-and-efficient","title":"FedEx-LoRA: Exact Aggregation for Federated and Efficient Fine-Tuning of Foundation Models","date":"2024-10-12","arxiv_id":"2410.09432","repositories_listed":2,"syntology":null},{"url":"/paper/an-investigation-of-neuron-activation-as-a","slug":"an-investigation-of-neuron-activation-as-a","title":"An Investigation of Neuron Activation as a Unified Lens to Explain Chain-of-Thought Eliciting Arithmetic Reasoning of LLMs","date":"2024-06-18","arxiv_id":"2406.12288","repositories_listed":2,"syntology":{"n":36,"n_ran":34,"n_constructed":0,"n_ran_checked":12,"n_instrument":22,"n_unverified":2,"n_honours":2,"n_violates":7,"n_no_contract":3,"n_pointer_only":12,"phrase":"34 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 7 violated, 3 with no contract checked; 22 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/an-investigation-of-neuron-activation-as-a#ran","syntology_url":"https://syntology.ai/paper/2406.12288","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12288"}},"official":{"repos":["dakingrai/neuron-analysis-cot-arithmetic-reasoning"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/buffer-of-thoughts-thought-augmented","slug":"buffer-of-thoughts-thought-augmented","title":"Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models","date":"2024-06-06","arxiv_id":"2406.04271","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_constructed":1,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 1 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/buffer-of-thoughts-thought-augmented#ran","syntology_url":"https://syntology.ai/paper/2406.04271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04271"}},"official":{"repos":["yangling0818/buffer-of-thought-llm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/reft-representation-finetuning-for-language","slug":"reft-representation-finetuning-for-language","title":"ReFT: Representation Finetuning for Language Models","date":"2024-04-04","arxiv_id":"2404.03592","repositories_listed":2,"syntology":{"n":14,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":8,"n_honours":2,"n_violates":1,"n_no_contract":3,"n_pointer_only":12,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/reft-representation-finetuning-for-language#ran","syntology_url":"https://syntology.ai/paper/2404.03592","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03592"}},"official":{"repos":["stanfordnlp/pyreft"],"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":["listed","official"]}}},{"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/offline-prompt-evaluation-and-optimization","slug":"offline-prompt-evaluation-and-optimization","title":"Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL","date":"2023-09-13","arxiv_id":"2309.06553","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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/offline-prompt-evaluation-and-optimization#ran","syntology_url":"https://syntology.ai/paper/2309.06553","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.06553"}},"official":{"repos":["holarissun/prompt-oirl","vanderschaarlab/prompt-oirl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/codet5-open-code-large-language-models-for","slug":"codet5-open-code-large-language-models-for","title":"CodeT5+: Open Code Large Language Models for Code Understanding and Generation","date":"2023-05-13","arxiv_id":"2305.07922","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/codet5-open-code-large-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2305.07922","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.07922"}},"official":{"repos":["salesforce/codet5"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/llm-adapters-an-adapter-family-for-parameter","slug":"llm-adapters-an-adapter-family-for-parameter","title":"LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models","date":"2023-04-04","arxiv_id":"2304.01933","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"4 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/llm-adapters-an-adapter-family-for-parameter#ran","syntology_url":"https://syntology.ai/paper/2304.01933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.01933"}},"official":{"repos":["agi-edgerunners/llm-adapters"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/automatic-prompt-augmentation-and-selection","slug":"automatic-prompt-augmentation-and-selection","title":"Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data","date":"2023-02-24","arxiv_id":"2302.12822","repositories_listed":2,"syntology":null},{"url":"/paper/batch-prompting-efficient-inference-with","slug":"batch-prompting-efficient-inference-with","title":"Batch Prompting: Efficient Inference with Large Language Model APIs","date":"2023-01-19","arxiv_id":"2301.08721","repositories_listed":2,"syntology":null},{"url":"/paper/reasoning-with-language-model-prompting-a","slug":"reasoning-with-language-model-prompting-a","title":"Reasoning with Language Model Prompting: A Survey","date":"2022-12-19","arxiv_id":"2212.09597","repositories_listed":2,"syntology":null},{"url":"/paper/unifying-language-learning-paradigms","slug":"unifying-language-learning-paradigms","title":"UL2: Unifying Language Learning Paradigms","date":"2022-05-10","arxiv_id":"2205.05131","repositories_listed":2,"syntology":{"n":16,"n_ran":15,"n_constructed":0,"n_ran_checked":15,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","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"}},"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"]}}},{"url":"/paper/learning-to-reason-for-text-generation-from","slug":"learning-to-reason-for-text-generation-from","title":"Learning to Reason for Text Generation from Scientific Tables","date":"2021-04-16","arxiv_id":"2104.08296","repositories_listed":2,"syntology":null},{"url":"/paper/dcr-quantifying-data-contamination-in-llms","slug":"dcr-quantifying-data-contamination-in-llms","title":"DCR: Quantifying Data Contamination in LLMs Evaluation","date":"2025-07-15","arxiv_id":"2507.11405","repositories_listed":1,"syntology":null},{"url":"/paper/ds-gt-at-checkthat-2025-evaluating-context","slug":"ds-gt-at-checkthat-2025-evaluating-context","title":"DS@GT at CheckThat! 2025: Evaluating Context and Tokenization Strategies for Numerical Fact Verification","date":"2025-07-08","arxiv_id":"2507.06195","repositories_listed":1,"syntology":null},{"url":"/paper/mathematical-reasoning-for-unmanned-aerial","slug":"mathematical-reasoning-for-unmanned-aerial","title":"Mathematical Reasoning for Unmanned Aerial Vehicles: A RAG-Based Approach for Complex Arithmetic Reasoning","date":"2025-06-05","arxiv_id":"2506.04998","repositories_listed":1,"syntology":null},{"url":"/paper/diablo-diagonal-blocks-are-sufficient-for","slug":"diablo-diagonal-blocks-are-sufficient-for","title":"DiaBlo: Diagonal Blocks Are Sufficient For Finetuning","date":"2025-06-03","arxiv_id":"2506.03230","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/diablo-diagonal-blocks-are-sufficient-for#ran","syntology_url":"https://syntology.ai/paper/2506.03230","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.03230"}},"official":{"repos":["ziyangjoy/diablo"],"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/halo-hierarchical-autonomous-logic-oriented","slug":"halo-hierarchical-autonomous-logic-oriented","title":"HALO: Hierarchical Autonomous Logic-Oriented Orchestration for Multi-Agent LLM Systems","date":"2025-05-17","arxiv_id":"2505.13516","repositories_listed":1,"syntology":null},{"url":"/paper/omac-a-broad-optimization-framework-for-llm","slug":"omac-a-broad-optimization-framework-for-llm","title":"OMAC: A Broad Optimization Framework for LLM-Based Multi-Agent Collaboration","date":"2025-05-17","arxiv_id":"2505.11765","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/omac-a-broad-optimization-framework-for-llm#ran","syntology_url":"https://syntology.ai/paper/2505.11765","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.11765"}},"official":{"repos":["xiwenchao/omac-demo"],"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":["found_in_text"]}}},{"url":"/paper/is-the-reversal-curse-a-binding-problem","slug":"is-the-reversal-curse-a-binding-problem","title":"Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failure","date":"2025-04-02","arxiv_id":"2504.01928","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-addressing-in-language-models-via","slug":"rethinking-addressing-in-language-models-via","title":"Rethinking Addressing in Language Models via Contexualized Equivariant Positional Encoding","date":"2025-01-01","arxiv_id":"2501.00712","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":0,"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/rethinking-addressing-in-language-models-via#ran","syntology_url":"https://syntology.ai/paper/2501.00712","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.00712"}},"official":{"repos":["vita-group/tape"],"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/seq-vcr-preventing-collapse-in-intermediate","slug":"seq-vcr-preventing-collapse-in-intermediate","title":"Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning","date":"2024-11-04","arxiv_id":"2411.02344","repositories_listed":1,"syntology":null},{"url":"/paper/arithmetic-without-algorithms-language-models","slug":"arithmetic-without-algorithms-language-models","title":"Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics","date":"2024-10-28","arxiv_id":"2410.21272","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/arithmetic-without-algorithms-language-models#ran","syntology_url":"https://syntology.ai/paper/2410.21272","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21272"}},"official":{"repos":["technion-cs-nlp/llm-arithmetic-heuristics"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/language-imbalance-driven-rewarding-for","slug":"language-imbalance-driven-rewarding-for","title":"Language Imbalance Driven Rewarding for Multilingual Self-improving","date":"2024-10-11","arxiv_id":"2410.08964","repositories_listed":1,"syntology":{"n":13,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"n_unverified":5,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":13,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/language-imbalance-driven-rewarding-for#ran","syntology_url":"https://syntology.ai/paper/2410.08964","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08964"}},"official":{"repos":["znlp/language-imbalance-driven-rewarding"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"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/3-in-1-2d-rotary-adaptation-for-efficient","slug":"3-in-1-2d-rotary-adaptation-for-efficient","title":"3-in-1: 2D Rotary Adaptation for Efficient Finetuning, Efficient Batching and Composability","date":"2024-08-28","arxiv_id":"2409.00119","repositories_listed":1,"syntology":null},{"url":"/paper/toward-adaptive-reasoning-in-large-language","slug":"toward-adaptive-reasoning-in-large-language","title":"Toward Adaptive Reasoning in Large Language Models with Thought Rollback","date":"2024-07-21","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/self-training-language-models-for-arithmetic","slug":"self-training-language-models-for-arithmetic","title":"Self-training Language Models for Arithmetic Reasoning","date":"2024-07-11","arxiv_id":"2407.08400","repositories_listed":1,"syntology":null},{"url":"/paper/sbora-low-rank-adaptation-with-regional","slug":"sbora-low-rank-adaptation-with-regional","title":"SBoRA: Low-Rank Adaptation with Regional Weight Updates","date":"2024-07-07","arxiv_id":"2407.05413","repositories_listed":1,"syntology":null},{"url":"/paper/workarena-towards-compositional-planning-and","slug":"workarena-towards-compositional-planning-and","title":"WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks","date":"2024-07-07","arxiv_id":"2407.05291","repositories_listed":1,"syntology":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/improving-arithmetic-reasoning-ability-of","slug":"improving-arithmetic-reasoning-ability-of","title":"Improving Arithmetic Reasoning Ability of Large Language Models through Relation Tuples, Verification and Dynamic Feedback","date":"2024-06-25","arxiv_id":"2406.17873","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"5 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; 3 where Syntology's instrument failed) · 2 unverified","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"}},"official":{"repos":["yaoching0/gac"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"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/hierarchical-prompting-taxonomy-a-universal","slug":"hierarchical-prompting-taxonomy-a-universal","title":"Hierarchical Prompting Taxonomy: A Universal Evaluation Framework for Large Language Models Aligned with Human Cognitive Principles","date":"2024-06-18","arxiv_id":"2406.12644","repositories_listed":1,"syntology":null},{"url":"/paper/chain-of-preference-optimization-improving","slug":"chain-of-preference-optimization-improving","title":"Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs","date":"2024-06-13","arxiv_id":"2406.09136","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/chain-of-preference-optimization-improving#ran","syntology_url":"https://syntology.ai/paper/2406.09136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09136"}},"official":{"repos":["sail-sg/cpo"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/quanta-efficient-high-rank-fine-tuning-of","slug":"quanta-efficient-high-rank-fine-tuning-of","title":"QuanTA: Efficient High-Rank Fine-Tuning of LLMs with Quantum-Informed Tensor Adaptation","date":"2024-05-31","arxiv_id":"2406.00132","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":5,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/quanta-efficient-high-rank-fine-tuning-of#ran","syntology_url":"https://syntology.ai/paper/2406.00132","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00132"}},"official":{"repos":["quanta-fine-tuning/quanta"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"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/bridging-the-gap-between-different","slug":"bridging-the-gap-between-different","title":"Bridging the Gap between Different Vocabularies for LLM Ensemble","date":"2024-04-15","arxiv_id":"2404.09492","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"4 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; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/bridging-the-gap-between-different#ran","syntology_url":"https://syntology.ai/paper/2404.09492","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09492"}},"official":{"repos":["xydaytoy/eva"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"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/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/distillation-contrastive-decoding-improving","slug":"distillation-contrastive-decoding-improving","title":"Distillation Contrastive Decoding: Improving LLMs Reasoning with Contrastive Decoding and Distillation","date":"2024-02-21","arxiv_id":"2402.14874","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":10,"phrase":"6 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; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/distillation-contrastive-decoding-improving#ran","syntology_url":"https://syntology.ai/paper/2402.14874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14874"}},"official":{"repos":["pphuc25/distil-cd"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"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/stuck-in-the-quicksand-of-numeracy-far-from","slug":"stuck-in-the-quicksand-of-numeracy-far-from","title":"Evaluating LLMs' Mathematical and Coding Competency through Ontology-guided Interventions","date":"2024-01-17","arxiv_id":"2401.09395","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/stuck-in-the-quicksand-of-numeracy-far-from#ran","syntology_url":"https://syntology.ai/paper/2401.09395","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.09395"}},"official":{"repos":["declare-lab/llm-reasoningtest"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/llm-augmented-llms-expanding-capabilities","slug":"llm-augmented-llms-expanding-capabilities","title":"LLM Augmented LLMs: Expanding Capabilities through Composition","date":"2024-01-04","arxiv_id":"2401.02412","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/llm-augmented-llms-expanding-capabilities#ran","syntology_url":"https://syntology.ai/paper/2401.02412","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.02412"}},"official":null}},{"url":"/paper/turning-dust-into-gold-distilling-complex","slug":"turning-dust-into-gold-distilling-complex","title":"Turning Dust into Gold: Distilling Complex Reasoning Capabilities from LLMs by Leveraging Negative Data","date":"2023-12-20","arxiv_id":"2312.12832","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":9,"phrase":"7 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; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/turning-dust-into-gold-distilling-complex#ran","syntology_url":"https://syntology.ai/paper/2312.12832","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12832"}},"official":{"repos":["Yiwei98/TDG"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/gemini-a-family-of-highly-capable-multimodal-1","slug":"gemini-a-family-of-highly-capable-multimodal-1","title":"Gemini: A Family of Highly Capable Multimodal Models","date":"2023-12-19","arxiv_id":"2312.11805","repositories_listed":1,"syntology":null},{"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/prompt-optimization-via-adversarial-in","slug":"prompt-optimization-via-adversarial-in","title":"Prompt Optimization via Adversarial In-Context Learning","date":"2023-12-05","arxiv_id":"2312.02614","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":12,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/prompt-optimization-via-adversarial-in#ran","syntology_url":"https://syntology.ai/paper/2312.02614","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02614"}},"official":{"repos":["zhaoyiran924/adv-in-context-learning"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/chatgpt-as-a-math-questioner-evaluating","slug":"chatgpt-as-a-math-questioner-evaluating","title":"ChatGPT as a Math Questioner? Evaluating ChatGPT on Generating Pre-university Math Questions","date":"2023-12-04","arxiv_id":"2312.01661","repositories_listed":1,"syntology":null},{"url":"/paper/gift-generative-interpretable-fine-tuning","slug":"gift-generative-interpretable-fine-tuning","title":"Generative Parameter-Efficient Fine-Tuning","date":"2023-12-01","arxiv_id":"2312.00700","repositories_listed":1,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":6,"n_instrument":6,"n_unverified":4,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":10,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/gift-generative-interpretable-fine-tuning#ran","syntology_url":"https://syntology.ai/paper/2312.00700","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.00700"}},"official":{"repos":["savadikarc/gift"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/neuro-symbolic-integration-brings-causal-and","slug":"neuro-symbolic-integration-brings-causal-and","title":"Neuro-Symbolic Integration Brings Causal and Reliable Reasoning Proofs","date":"2023-11-16","arxiv_id":"2311.09802","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"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":3,"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/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"}},"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"]}}},{"url":"/paper/empirical-study-of-zero-shot-ner-with-chatgpt","slug":"empirical-study-of-zero-shot-ner-with-chatgpt","title":"Empirical Study of Zero-Shot NER with ChatGPT","date":"2023-10-16","arxiv_id":"2310.10035","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":2,"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/empirical-study-of-zero-shot-ner-with-chatgpt#ran","syntology_url":"https://syntology.ai/paper/2310.10035","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.10035"}},"official":{"repos":["emma1066/zero-shot-ner-with-chatgpt"],"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/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/dialcot-meets-ppo-decomposing-and-exploring","slug":"dialcot-meets-ppo-decomposing-and-exploring","title":"DialCoT Meets PPO: Decomposing and Exploring Reasoning Paths in Smaller Language Models","date":"2023-10-08","arxiv_id":"2310.05074","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/domino-a-dual-system-for-multi-step-visual","slug":"domino-a-dual-system-for-multi-step-visual","title":"DOMINO: A Dual-System for Multi-step Visual Language Reasoning","date":"2023-10-04","arxiv_id":"2310.02804","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-llm-agent-network-an-llm-agent","slug":"dynamic-llm-agent-network-an-llm-agent","title":"A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration","date":"2023-10-03","arxiv_id":"2310.02170","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dynamic-llm-agent-network-an-llm-agent#ran","syntology_url":"https://syntology.ai/paper/2310.02170","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.02170"}},"official":{"repos":["salt-nlp/dylan"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/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/are-human-generated-demonstrations-necessary","slug":"are-human-generated-demonstrations-necessary","title":"Are Human-generated Demonstrations Necessary for In-context Learning?","date":"2023-09-26","arxiv_id":"2309.14681","repositories_listed":1,"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":11,"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/are-human-generated-demonstrations-necessary#ran","syntology_url":"https://syntology.ai/paper/2309.14681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.14681"}},"official":{"repos":["ruili33/sec"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"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/token-scaled-logit-distillation-for-ternary-1","slug":"token-scaled-logit-distillation-for-ternary-1","title":"Token-Scaled Logit Distillation for Ternary Weight Generative Language Models","date":"2023-08-13","arxiv_id":"2308.06744","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"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) · 0 unverified","sample_list":"/paper/token-scaled-logit-distillation-for-ternary-1#ran","syntology_url":"https://syntology.ai/paper/2308.06744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.06744"}},"official":{"repos":["aiha-lab/tsld"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/scaling-relationship-on-learning-mathematical#ran","syntology_url":"https://syntology.ai/paper/2308.01825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.01825"}},"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"]}}},{"url":"/paper/can-llms-express-their-uncertainty-an","slug":"can-llms-express-their-uncertainty-an","title":"Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs","date":"2023-06-22","arxiv_id":"2306.13063","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/can-llms-express-their-uncertainty-an#ran","syntology_url":"https://syntology.ai/paper/2306.13063","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.13063"}},"official":{"repos":["miaoxiong2320/llm-uncertainty"],"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/boosting-language-models-reasoning-with-chain","slug":"boosting-language-models-reasoning-with-chain","title":"Boosting Language Models Reasoning with Chain-of-Knowledge Prompting","date":"2023-06-10","arxiv_id":"2306.06427","repositories_listed":1,"syntology":null},{"url":"/paper/prompt-space-optimizing-few-shot-reasoning","slug":"prompt-space-optimizing-few-shot-reasoning","title":"Prompt Space Optimizing Few-shot Reasoning Success with Large Language Models","date":"2023-06-06","arxiv_id":"2306.03799","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/prompt-space-optimizing-few-shot-reasoning#ran","syntology_url":"https://syntology.ai/paper/2306.03799","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.03799"}},"official":{"repos":["youblei/prompt-space"],"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/encouraging-divergent-thinking-in-large","slug":"encouraging-divergent-thinking-in-large","title":"Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate","date":"2023-05-30","arxiv_id":"2305.19118","repositories_listed":1,"syntology":null},{"url":"/paper/2305-15017","slug":"2305-15017","title":"Calc-X and Calcformers: Empowering Arithmetical Chain-of-Thought through Interaction with Symbolic Systems","date":"2023-05-24","arxiv_id":"2305.15017","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/2305-15017#ran","syntology_url":"https://syntology.ai/paper/2305.15017","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.15017"}},"official":{"repos":["prompteus/calc-x"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/understanding-arithmetic-reasoning-in","slug":"understanding-arithmetic-reasoning-in","title":"A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis","date":"2023-05-24","arxiv_id":"2305.15054","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":3,"n_ran_checked":3,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"7 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/understanding-arithmetic-reasoning-in#ran","syntology_url":"https://syntology.ai/paper/2305.15054","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.15054"}},"official":{"repos":["alestolfo/lm-arithmetic"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"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/pad-program-aided-distillation-specializes","slug":"pad-program-aided-distillation-specializes","title":"PaD: Program-aided Distillation Can Teach Small Models Reasoning Better than Chain-of-thought Fine-tuning","date":"2023-05-23","arxiv_id":"2305.13888","repositories_listed":1,"syntology":null},{"url":"/paper/satlm-satisfiability-aided-language-models-1","slug":"satlm-satisfiability-aided-language-models-1","title":"SatLM: Satisfiability-Aided Language Models Using Declarative Prompting","date":"2023-05-16","arxiv_id":"2305.09656","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 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) · 3 unverified","sample_list":"/paper/satlm-satisfiability-aided-language-models-1#ran","syntology_url":"https://syntology.ai/paper/2305.09656","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.09656"}},"official":{"repos":["xiye17/sat-lm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-non-linguistic-skills-without","slug":"learning-non-linguistic-skills-without","title":"Learning Non-linguistic Skills without Sacrificing Linguistic Proficiency","date":"2023-05-14","arxiv_id":"2305.08246","repositories_listed":1,"syntology":null},{"url":"/paper/not-all-languages-are-created-equal-in-llms","slug":"not-all-languages-are-created-equal-in-llms","title":"Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting","date":"2023-05-11","arxiv_id":"2305.07004","repositories_listed":1,"syntology":null},{"url":"/paper/mot-pre-thinking-and-recalling-enable-chatgpt","slug":"mot-pre-thinking-and-recalling-enable-chatgpt","title":"MoT: Memory-of-Thought Enables ChatGPT to Self-Improve","date":"2023-05-09","arxiv_id":"2305.05181","repositories_listed":1,"syntology":null},{"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/mathprompter-mathematical-reasoning-using","slug":"mathprompter-mathematical-reasoning-using","title":"MathPrompter: Mathematical Reasoning using Large Language Models","date":"2023-03-04","arxiv_id":"2303.05398","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mathprompter-mathematical-reasoning-using#ran","syntology_url":"https://syntology.ai/paper/2303.05398","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.05398"}},"official":null}},{"url":"/paper/lever-learning-to-verify-language-to-code","slug":"lever-learning-to-verify-language-to-code","title":"LEVER: Learning to Verify Language-to-Code Generation with Execution","date":"2023-02-16","arxiv_id":"2302.08468","repositories_listed":1,"syntology":{"n":22,"n_ran":18,"n_constructed":0,"n_ran_checked":14,"n_instrument":4,"n_unverified":4,"n_honours":0,"n_violates":2,"n_no_contract":12,"n_pointer_only":1,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 2 violated, 12 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/lever-learning-to-verify-language-to-code#ran","syntology_url":"https://syntology.ai/paper/2302.08468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.08468"}},"official":{"repos":["niansong1996/lever"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":4,"ran_from_kinds":["official"]}}}],"syntology_records":62,"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":170,"papers_placed":0,"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/arithmetic-reasoning-on-gsm8k","since_archive":"/sota/arithmetic-reasoning-on-gsm8k#since-judged","papers_judged":168,"placed":0},{"leaderboard":"/sota/arithmetic-reasoning-on-multiarith","since_archive":"/sota/arithmetic-reasoning-on-multiarith#since-judged","papers_judged":11,"placed":0},{"leaderboard":"/sota/arithmetic-reasoning-on-game-of-24","since_archive":"/sota/arithmetic-reasoning-on-game-of-24#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":64,"papers_where_code_ran_first_page":"/task/arithmetic-reasoning/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/arithmetic-reasoning/papers/2","json":"/task/arithmetic-reasoning/papers/2.json","rows":75},{"order":"ran","page":1,"of":1,"url":"/task/arithmetic-reasoning/papers/ran/1","json":"/task/arithmetic-reasoning/papers/ran/1.json","rows":64}],"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":"828e9e41c13fcb560b59ad54471d9f0f89c31ce8fd954f126adc06762177da0f","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}