{"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/gsm8k","name":"GSM8K","slug":"gsm8k","description_markdown":null,"categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":439,"papers_with_code":209,"benchmarks":1,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"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":1,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/gsm8k-on-gsm8k","slug":"gsm8k-on-gsm8k","dataset":"GSM8K","dataset_url":"/dataset/gsm8k","rows_in_archive":3,"metrics":["Accuracy","0-shot MRR"],"first_row_in_archive_order":{"model":"Xolver","paper_title":"Xolver: Multi-Agent Reasoning with Holistic Experience Learning Just Like an Olympiad Team","paper_url":"/paper/xolver-multi-agent-reasoning-with-holistic","paper_date":"2025-06-17","arxiv_id":"2506.14234","code_links":[{"title":"kagnlp/Xolver","url":"https://github.com/kagnlp/Xolver"}],"syntology":null}},{"leaderboard":null,"slug":"gsm8k-on-gsm8k-5-shots","dataset":"gsm8k (5-shots)","dataset_url":"/dataset/gsm8k","rows_in_archive":0,"metrics":["exact_match_strict"],"first_row_in_archive_order":null}],"datasets":[{"url":"/dataset/gsm8k","name":"GSM8K","full_name":"","num_papers_in_archive":1881}],"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":5,"rows_per_page":100,"shown":100,"of":439,"of_with_code":209,"tagged_in_all":439,"counts":{"archive_papers_tagged":439,"with_a_code_link":209,"where_syntology_ran_a_sample":116,"not_listed_spam_title":0,"listed":439,"listed_where_code_ran":116,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":94,"every_run_a_failure_of_syntologys_instrument":22,"listed_with_a_run_with_no_instrument_failure":94,"listed_every_run_a_failure_of_syntologys_instrument":22,"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/chain-of-thought-prompting-elicits-reasoning","slug":"chain-of-thought-prompting-elicits-reasoning","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","date":"2022-01-28","arxiv_id":"2201.11903","repositories_listed":19,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/chain-of-thought-prompting-elicits-reasoning#ran","syntology_url":"https://syntology.ai/paper/2201.11903","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.11903"}},"official":null}},{"url":"/paper/chatglm-a-family-of-large-language-models","slug":"chatglm-a-family-of-large-language-models","title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","date":"2024-06-18","arxiv_id":"2406.12793","repositories_listed":7,"syntology":{"n":29,"n_ran":21,"n_constructed":0,"n_ran_checked":15,"n_instrument":6,"n_unverified":8,"n_honours":1,"n_violates":0,"n_no_contract":14,"n_pointer_only":1,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 0 violated, 14 with no contract checked; 6 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/chatglm-a-family-of-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2406.12793","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12793"}},"official":{"repos":["thudm/chatglm-6b"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"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/training-verifiers-to-solve-math-word","slug":"training-verifiers-to-solve-math-word","title":"Training Verifiers to Solve Math Word Problems","date":"2021-10-27","arxiv_id":"2110.14168","repositories_listed":6,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/training-verifiers-to-solve-math-word#ran","syntology_url":"https://syntology.ai/paper/2110.14168","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.14168"}},"official":{"repos":["openai/grade-school-math"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/large-language-models-as-optimizers","slug":"large-language-models-as-optimizers","title":"Large Language Models as Optimizers","date":"2023-09-07","arxiv_id":"2309.03409","repositories_listed":4,"syntology":{"n":14,"n_ran":14,"n_constructed":0,"n_ran_checked":10,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":6,"phrase":"14 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/large-language-models-as-optimizers#ran","syntology_url":"https://syntology.ai/paper/2309.03409","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.03409"}},"official":{"repos":["google-deepmind/opro"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/language-models-are-multilingual-chain-of","slug":"language-models-are-multilingual-chain-of","title":"Language Models are Multilingual Chain-of-Thought Reasoners","date":"2022-10-06","arxiv_id":"2210.03057","repositories_listed":4,"syntology":null},{"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/bone-block-affine-transformation-as-parameter","slug":"bone-block-affine-transformation-as-parameter","title":"Balancing LoRA Performance and Efficiency with Simple Shard Sharing","date":"2024-09-19","arxiv_id":"2409.15371","repositories_listed":3,"syntology":null},{"url":"/paper/mutual-reasoning-makes-smaller-llms-stronger","slug":"mutual-reasoning-makes-smaller-llms-stronger","title":"Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers","date":"2024-08-12","arxiv_id":"2408.06195","repositories_listed":3,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mutual-reasoning-makes-smaller-llms-stronger#ran","syntology_url":"https://syntology.ai/paper/2408.06195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.06195"}},"official":{"repos":["zhentingqi/rstar"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/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/language-models-are-super-mario-absorbing","slug":"language-models-are-super-mario-absorbing","title":"Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch","date":"2023-11-06","arxiv_id":"2311.03099","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/language-models-are-super-mario-absorbing#ran","syntology_url":"https://syntology.ai/paper/2311.03099","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.03099"}},"official":{"repos":["yule-buaa/mergelm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/askit-unified-programming-interface-for","slug":"askit-unified-programming-interface-for","title":"AskIt: Unified Programming Interface for Programming with Large Language Models","date":"2023-08-29","arxiv_id":"2308.15645","repositories_listed":3,"syntology":null},{"url":"/paper/kernel-ssl-kernel-kl-divergence-for-self","slug":"kernel-ssl-kernel-kl-divergence-for-self","title":"Matrix Information Theory for Self-Supervised Learning","date":"2023-05-27","arxiv_id":"2305.17326","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/kernel-ssl-kernel-kl-divergence-for-self#ran","syntology_url":"https://syntology.ai/paper/2305.17326","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.17326"}},"official":{"repos":["yifanzhang-pro/matrix-llm","yifanzhang-pro/matrix-ssl"],"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","unlocated"]}}},{"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/let-llms-break-free-from-overthinking-via","slug":"let-llms-break-free-from-overthinking-via","title":"Let LLMs Break Free from Overthinking via Self-Braking Tuning","date":"2025-05-20","arxiv_id":"2505.14604","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/let-llms-break-free-from-overthinking-via#ran","syntology_url":"https://syntology.ai/paper/2505.14604","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.14604"}},"official":{"repos":["ccai-lab/self-braking-tuning","zju-real/self-braking-tuning"],"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/offline-reinforcement-learning-for-llm-multi","slug":"offline-reinforcement-learning-for-llm-multi","title":"Offline Reinforcement Learning for LLM Multi-Step Reasoning","date":"2024-12-20","arxiv_id":"2412.16145","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/offline-reinforcement-learning-for-llm-multi#ran","syntology_url":"https://syntology.ai/paper/2412.16145","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.16145"}},"official":{"repos":["jwhj/oreo"],"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/enhancing-multi-step-reasoning-abilities-of","slug":"enhancing-multi-step-reasoning-abilities-of","title":"Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization","date":"2024-10-11","arxiv_id":"2410.09302","repositories_listed":2,"syntology":null},{"url":"/paper/supercorrect-supervising-and-correcting","slug":"supercorrect-supervising-and-correcting","title":"SuperCorrect: Supervising and Correcting Language Models with Error-Driven Insights","date":"2024-10-11","arxiv_id":"2410.09008","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/supercorrect-supervising-and-correcting#ran","syntology_url":"https://syntology.ai/paper/2410.09008","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09008"}},"official":{"repos":["yangling0818/supercorrect-llm"],"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/omni-math-a-universal-olympiad-level","slug":"omni-math-a-universal-olympiad-level","title":"Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models","date":"2024-10-10","arxiv_id":"2410.07985","repositories_listed":2,"syntology":{"n":19,"n_ran":13,"n_constructed":0,"n_ran_checked":6,"n_instrument":7,"n_unverified":6,"n_honours":1,"n_violates":5,"n_no_contract":0,"n_pointer_only":19,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 5 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/omni-math-a-universal-olympiad-level#ran","syntology_url":"https://syntology.ai/paper/2410.07985","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07985"}},"official":{"repos":["kbsdjames/omni-math","kbsdjames/omni-math-rule"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/gsm-symbolic-understanding-the-limitations-of","slug":"gsm-symbolic-understanding-the-limitations-of","title":"GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models","date":"2024-10-07","arxiv_id":"2410.05229","repositories_listed":2,"syntology":null},{"url":"/paper/large-language-monkeys-scaling-inference","slug":"large-language-monkeys-scaling-inference","title":"Large Language Monkeys: Scaling Inference Compute with Repeated Sampling","date":"2024-07-31","arxiv_id":"2407.21787","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/large-language-monkeys-scaling-inference#ran","syntology_url":"https://syntology.ai/paper/2407.21787","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.21787"}},"official":{"repos":["scalingintelligence/large_language_monkeys"],"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":["official"]}}},{"url":"/paper/monte-carlo-tree-search-boosts-reasoning-via","slug":"monte-carlo-tree-search-boosts-reasoning-via","title":"Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning","date":"2024-05-01","arxiv_id":"2405.00451","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/monte-carlo-tree-search-boosts-reasoning-via#ran","syntology_url":"https://syntology.ai/paper/2405.00451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.00451"}},"official":{"repos":["YuxiXie/MCTS-DPO"],"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/quiet-star-language-models-can-teach","slug":"quiet-star-language-models-can-teach","title":"Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking","date":"2024-03-14","arxiv_id":"2403.09629","repositories_listed":2,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"8 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/quiet-star-language-models-can-teach#ran","syntology_url":"https://syntology.ai/paper/2403.09629","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09629"}},"official":{"repos":["ezelikman/quiet-star"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/common-7b-language-models-already-possess","slug":"common-7b-language-models-already-possess","title":"Common 7B Language Models Already Possess Strong Math Capabilities","date":"2024-03-07","arxiv_id":"2403.04706","repositories_listed":2,"syntology":{"n":28,"n_ran":21,"n_constructed":0,"n_ran_checked":15,"n_instrument":6,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":12,"phrase":"21 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; 6 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/common-7b-language-models-already-possess#ran","syntology_url":"https://syntology.ai/paper/2403.04706","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04706"}},"official":{"repos":["xwin-lm/xwin-lm"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/automathtext-autonomous-data-selection-with","slug":"automathtext-autonomous-data-selection-with","title":"Autonomous Data Selection with Zero-shot Generative Classifiers for Mathematical Texts","date":"2024-02-12","arxiv_id":"2402.07625","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/automathtext-autonomous-data-selection-with#ran","syntology_url":"https://syntology.ai/paper/2402.07625","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07625"}},"official":{"repos":["hiyouga/llama-factory","yifanzhang-pro/automathtext"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mario-math-reasoning-with-code-interpreter","slug":"mario-math-reasoning-with-code-interpreter","title":"MARIO: MAth Reasoning with code Interpreter Output -- A Reproducible Pipeline","date":"2024-01-16","arxiv_id":"2401.08190","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":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/mario-math-reasoning-with-code-interpreter#ran","syntology_url":"https://syntology.ai/paper/2401.08190","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.08190"}},"official":{"repos":["mario-math-reasoning/mario"],"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/challenge-llms-to-reason-about-reasoning-a","slug":"challenge-llms-to-reason-about-reasoning-a","title":"MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model Evaluation","date":"2023-12-28","arxiv_id":"2312.17080","repositories_listed":2,"syntology":null},{"url":"/paper/data-contamination-quiz-a-tool-to-detect-and","slug":"data-contamination-quiz-a-tool-to-detect-and","title":"Data Contamination Quiz: A Tool to Detect and Estimate Contamination in Large Language Models","date":"2023-11-10","arxiv_id":"2311.06233","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/data-contamination-quiz-a-tool-to-detect-and#ran","syntology_url":"https://syntology.ai/paper/2311.06233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.06233"}},"official":{"repos":["shahriargolchin/dcq"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/breaking-language-barriers-in-multilingual","slug":"breaking-language-barriers-in-multilingual","title":"Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and Observations","date":"2023-10-31","arxiv_id":"2310.20246","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":3,"phrase":"8 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; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/breaking-language-barriers-in-multilingual#ran","syntology_url":"https://syntology.ai/paper/2310.20246","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.20246"}},"official":{"repos":["microsoft/MathOctopus"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/baichuan-2-open-large-scale-language-models","slug":"baichuan-2-open-large-scale-language-models","title":"Baichuan 2: Open Large-scale Language Models","date":"2023-09-19","arxiv_id":"2309.10305","repositories_listed":2,"syntology":null},{"url":"/paper/beyond-chain-of-thought-effective-graph-of","slug":"beyond-chain-of-thought-effective-graph-of","title":"Beyond Chain-of-Thought, Effective Graph-of-Thought Reasoning in Language Models","date":"2023-05-26","arxiv_id":"2305.16582","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":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/beyond-chain-of-thought-effective-graph-of#ran","syntology_url":"https://syntology.ai/paper/2305.16582","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16582"}},"official":{"repos":["zoeyyao27/graph-of-thought"],"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/dac-a-dynamic-attention-aware-approach-for","slug":"dac-a-dynamic-attention-aware-approach-for","title":"DAC: A Dynamic Attention-aware Approach for Task-Agnostic Prompt Compression","date":"2025-07-16","arxiv_id":"2507.11942","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/dac-a-dynamic-attention-aware-approach-for#ran","syntology_url":"https://syntology.ai/paper/2507.11942","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.11942"}},"official":{"repos":["qqq-yi/dac"],"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/any4-learned-4-bit-numeric-representation-for","slug":"any4-learned-4-bit-numeric-representation-for","title":"any4: Learned 4-bit Numeric Representation for LLMs","date":"2025-07-07","arxiv_id":"2507.04610","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/any4-learned-4-bit-numeric-representation-for#ran","syntology_url":"https://syntology.ai/paper/2507.04610","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.04610"}},"official":{"repos":["facebookresearch/any4"],"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/iranker-towards-ranking-foundation-model","slug":"iranker-towards-ranking-foundation-model","title":"IRanker: Towards Ranking Foundation Model","date":"2025-06-25","arxiv_id":"2506.21638","repositories_listed":1,"syntology":null},{"url":"/paper/commvq-commutative-vector-quantization-for-kv","slug":"commvq-commutative-vector-quantization-for-kv","title":"CommVQ: Commutative Vector Quantization for KV Cache Compression","date":"2025-06-23","arxiv_id":"2506.18879","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/commvq-commutative-vector-quantization-for-kv#ran","syntology_url":"https://syntology.ai/paper/2506.18879","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.18879"}},"official":{"repos":["umass-embodied-agi/commvq"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/agentgroupchat-v2-divide-and-conquer-is-what","slug":"agentgroupchat-v2-divide-and-conquer-is-what","title":"AgentGroupChat-V2: Divide-and-Conquer Is What LLM-Based Multi-Agent System Need","date":"2025-06-18","arxiv_id":"2506.15451","repositories_listed":1,"syntology":null},{"url":"/paper/re-initialization-token-learning-for-tool","slug":"re-initialization-token-learning-for-tool","title":"Re-Initialization Token Learning for Tool-Augmented Large Language Models","date":"2025-06-17","arxiv_id":"2506.14248","repositories_listed":1,"syntology":null},{"url":"/paper/xolver-multi-agent-reasoning-with-holistic","slug":"xolver-multi-agent-reasoning-with-holistic","title":"Xolver: Multi-Agent Reasoning with Holistic Experience Learning Just Like an Olympiad Team","date":"2025-06-17","arxiv_id":"2506.14234","repositories_listed":1,"syntology":null},{"url":"/paper/learning-a-continue-thinking-token-for","slug":"learning-a-continue-thinking-token-for","title":"Learning a Continue-Thinking Token for Enhanced Test-Time Scaling","date":"2025-06-12","arxiv_id":"2506.11274","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-elicitation-of-language-models","slug":"unsupervised-elicitation-of-language-models","title":"Unsupervised Elicitation of Language Models","date":"2025-06-11","arxiv_id":"2506.10139","repositories_listed":1,"syntology":null},{"url":"/paper/topology-of-reasoning-understanding-large","slug":"topology-of-reasoning-understanding-large","title":"Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph Properties","date":"2025-06-06","arxiv_id":"2506.05744","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/topology-of-reasoning-understanding-large#ran","syntology_url":"https://syntology.ai/paper/2506.05744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.05744"}},"official":{"repos":["gouki510/Topology_of_Reasoning"],"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/discriminative-policy-optimization-for-token","slug":"discriminative-policy-optimization-for-token","title":"Discriminative Policy Optimization for Token-Level Reward Models","date":"2025-05-29","arxiv_id":"2505.23363","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/discriminative-policy-optimization-for-token#ran","syntology_url":"https://syntology.ai/paper/2505.23363","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.23363"}},"official":{"repos":["homzer/q-rm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/segment-policy-optimization-effective-segment","slug":"segment-policy-optimization-effective-segment","title":"Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models","date":"2025-05-29","arxiv_id":"2505.23564","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"7 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; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/segment-policy-optimization-effective-segment#ran","syntology_url":"https://syntology.ai/paper/2505.23564","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.23564"}},"official":{"repos":["aiframeresearch/spo"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/the-price-of-format-diversity-collapse-in","slug":"the-price-of-format-diversity-collapse-in","title":"The Price of Format: Diversity Collapse in LLMs","date":"2025-05-25","arxiv_id":"2505.18949","repositories_listed":1,"syntology":null},{"url":"/paper/adactrl-towards-adaptive-and-controllable","slug":"adactrl-towards-adaptive-and-controllable","title":"AdaCtrl: Towards Adaptive and Controllable Reasoning via Difficulty-Aware Budgeting","date":"2025-05-24","arxiv_id":"2505.18822","repositories_listed":1,"syntology":{"n":15,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":9,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/adactrl-towards-adaptive-and-controllable#ran","syntology_url":"https://syntology.ai/paper/2505.18822","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.18822"}},"official":{"repos":["joeying1019/adactrl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/equivpruner-boosting-efficiency-and-quality-1","slug":"equivpruner-boosting-efficiency-and-quality-1","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","date":"2025-05-22","arxiv_id":"2505.16312","repositories_listed":1,"syntology":null},{"url":"/paper/seek-in-the-dark-reasoning-via-test-time","slug":"seek-in-the-dark-reasoning-via-test-time","title":"Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space","date":"2025-05-19","arxiv_id":"2505.13308","repositories_listed":1,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":4,"n_honours":1,"n_violates":2,"n_no_contract":8,"n_pointer_only":3,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 2 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/seek-in-the-dark-reasoning-via-test-time#ran","syntology_url":"https://syntology.ai/paper/2505.13308","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.13308"}},"official":{"repos":["bigai-nlco/latentseek"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/thinkless-llm-learns-when-to-think","slug":"thinkless-llm-learns-when-to-think","title":"Thinkless: LLM Learns When to Think","date":"2025-05-19","arxiv_id":"2505.13379","repositories_listed":1,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/thinkless-llm-learns-when-to-think#ran","syntology_url":"https://syntology.ai/paper/2505.13379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.13379"}},"official":{"repos":["vainf/thinkless"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/data-whisperer-efficient-data-selection-for","slug":"data-whisperer-efficient-data-selection-for","title":"Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning","date":"2025-05-18","arxiv_id":"2505.12212","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":7,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/data-whisperer-efficient-data-selection-for#ran","syntology_url":"https://syntology.ai/paper/2505.12212","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.12212"}},"official":{"repos":["gszfwsb/Data-Whisperer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/slot-sample-specific-language-model","slug":"slot-sample-specific-language-model","title":"SLOT: Sample-specific Language Model Optimization at Test-time","date":"2025-05-18","arxiv_id":"2505.12392","repositories_listed":1,"syntology":null},{"url":"/paper/synthetic-data-rl-task-definition-is-all-you","slug":"synthetic-data-rl-task-definition-is-all-you","title":"Synthetic Data RL: Task Definition Is All You Need","date":"2025-05-18","arxiv_id":"2505.17063","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"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) · 3 unverified","sample_list":"/paper/synthetic-data-rl-task-definition-is-all-you#ran","syntology_url":"https://syntology.ai/paper/2505.17063","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.17063"}},"official":{"repos":["gydpku/data_synthesis_rl"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/rewriting-pre-training-data-boosts-llm","slug":"rewriting-pre-training-data-boosts-llm","title":"Rewriting Pre-Training Data Boosts LLM Performance in Math and Code","date":"2025-05-05","arxiv_id":"2505.02881","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/rewriting-pre-training-data-boosts-llm#ran","syntology_url":"https://syntology.ai/paper/2505.02881","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.02881"}},"official":{"repos":["rioyokotalab/swallow-code-math"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tutorgym-a-testbed-for-evaluating-ai-agents","slug":"tutorgym-a-testbed-for-evaluating-ai-agents","title":"TutorGym: A Testbed for Evaluating AI Agents as Tutors and Students","date":"2025-05-02","arxiv_id":"2505.01563","repositories_listed":1,"syntology":null},{"url":"/paper/nemo-inspector-a-visualization-tool-for-llm","slug":"nemo-inspector-a-visualization-tool-for-llm","title":"NeMo-Inspector: A Visualization Tool for LLM Generation Analysis","date":"2025-05-01","arxiv_id":"2505.00903","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-reasoning-for-llms-through","slug":"efficient-reasoning-for-llms-through","title":"Efficient Reasoning for LLMs through Speculative Chain-of-Thought","date":"2025-04-27","arxiv_id":"2504.19095","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 2 unverified","sample_list":"/paper/efficient-reasoning-for-llms-through#ran","syntology_url":"https://syntology.ai/paper/2504.19095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.19095"}},"official":{"repos":["jikai0wang/speculative_cot"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/dynamic-early-exit-in-reasoning-models","slug":"dynamic-early-exit-in-reasoning-models","title":"Dynamic Early Exit in Reasoning Models","date":"2025-04-22","arxiv_id":"2504.15895","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":0,"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/dynamic-early-exit-in-reasoning-models#ran","syntology_url":"https://syntology.ai/paper/2504.15895","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.15895"}},"official":{"repos":["iie-ycx/deer"],"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/syzygy-of-thoughts-improving-llm-cot-with-the","slug":"syzygy-of-thoughts-improving-llm-cot-with-the","title":"Syzygy of Thoughts: Improving LLM CoT with the Minimal Free Resolution","date":"2025-04-13","arxiv_id":"2504.09566","repositories_listed":1,"syntology":null},{"url":"/paper/seal-steerable-reasoning-calibration-of-large","slug":"seal-steerable-reasoning-calibration-of-large","title":"SEAL: Steerable Reasoning Calibration of Large Language Models for Free","date":"2025-04-07","arxiv_id":"2504.07986","repositories_listed":1,"syntology":null},{"url":"/paper/large-vision-language-models-are-unsupervised","slug":"large-vision-language-models-are-unsupervised","title":"Large (Vision) Language Models are Unsupervised In-Context Learners","date":"2025-04-03","arxiv_id":"2504.02349","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/large-vision-language-models-are-unsupervised#ran","syntology_url":"https://syntology.ai/paper/2504.02349","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.02349"}},"official":{"repos":["mlbio-epfl/joint-inference"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/reasoning-under-1-billion-memory-augmented","slug":"reasoning-under-1-billion-memory-augmented","title":"Reasoning Under 1 Billion: Memory-Augmented Reinforcement Learning for Large Language Models","date":"2025-04-03","arxiv_id":"2504.02273","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-rectification-sampling-for-test-time","slug":"adaptive-rectification-sampling-for-test-time","title":"Adaptive Rectification Sampling for Test-Time Compute Scaling","date":"2025-04-02","arxiv_id":"2504.01317","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-llm-reasoning-through-controlled","slug":"exploring-llm-reasoning-through-controlled","title":"Exploring LLM Reasoning Through Controlled Prompt Variations","date":"2025-04-02","arxiv_id":"2504.02111","repositories_listed":1,"syntology":null},{"url":"/paper/entropy-based-adaptive-weighting-for-self","slug":"entropy-based-adaptive-weighting-for-self","title":"Entropy-Based Adaptive Weighting for Self-Training","date":"2025-03-31","arxiv_id":"2503.23913","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/entropy-based-adaptive-weighting-for-self#ran","syntology_url":"https://syntology.ai/paper/2503.23913","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.23913"}},"official":{"repos":["mandyyyyii/east"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cppo-accelerating-the-training-of-group","slug":"cppo-accelerating-the-training-of-group","title":"CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models","date":"2025-03-28","arxiv_id":"2503.22342","repositories_listed":1,"syntology":{"n":13,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"8 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; 5 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/cppo-accelerating-the-training-of-group#ran","syntology_url":"https://syntology.ai/paper/2503.22342","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.22342"}},"official":{"repos":["lzhxmu/cppo"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/qwen2-5-omni-technical-report","slug":"qwen2-5-omni-technical-report","title":"Qwen2.5-Omni Technical Report","date":"2025-03-26","arxiv_id":"2503.20215","repositories_listed":1,"syntology":null},{"url":"/paper/lost-in-cultural-translation-do-llms-struggle","slug":"lost-in-cultural-translation-do-llms-struggle","title":"Lost in Cultural Translation: Do LLMs Struggle with Math Across Cultural Contexts?","date":"2025-03-23","arxiv_id":"2503.18018","repositories_listed":1,"syntology":null},{"url":"/paper/chain-of-tools-utilizing-massive-unseen-tools","slug":"chain-of-tools-utilizing-massive-unseen-tools","title":"Chain-of-Tools: Utilizing Massive Unseen Tools in the CoT Reasoning of Frozen Language Models","date":"2025-03-21","arxiv_id":"2503.16779","repositories_listed":1,"syntology":null},{"url":"/paper/safemerge-preserving-safety-alignment-in-fine","slug":"safemerge-preserving-safety-alignment-in-fine","title":"SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging","date":"2025-03-21","arxiv_id":"2503.17239","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/safemerge-preserving-safety-alignment-in-fine#ran","syntology_url":"https://syntology.ai/paper/2503.17239","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.17239"}},"official":{"repos":["aladinD/SafeMERGE"],"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/towards-hierarchical-multi-step-reward-models","slug":"towards-hierarchical-multi-step-reward-models","title":"Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models","date":"2025-03-16","arxiv_id":"2503.13551","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":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/towards-hierarchical-multi-step-reward-models#ran","syntology_url":"https://syntology.ai/paper/2503.13551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.13551"}},"official":{"repos":["tengwang0318/hierarchial_reward_model"],"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/delta-a-decoding-strategy-based-on-logit","slug":"delta-a-decoding-strategy-based-on-logit","title":"DeLTa: A Decoding Strategy based on Logit Trajectory Prediction Improves Factuality and Reasoning Ability","date":"2025-03-04","arxiv_id":"2503.02343","repositories_listed":1,"syntology":null},{"url":"/paper/promptcot-synthesizing-olympiad-level","slug":"promptcot-synthesizing-olympiad-level","title":"PromptCoT: Synthesizing Olympiad-level Problems for Mathematical Reasoning in Large Language Models","date":"2025-03-04","arxiv_id":"2503.02324","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/promptcot-synthesizing-olympiad-level#ran","syntology_url":"https://syntology.ai/paper/2503.02324","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.02324"}},"official":{"repos":["zhaoxlpku/promptcot"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/codi-compressing-chain-of-thought-into","slug":"codi-compressing-chain-of-thought-into","title":"CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation","date":"2025-02-28","arxiv_id":"2502.21074","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/codi-compressing-chain-of-thought-into#ran","syntology_url":"https://syntology.ai/paper/2502.21074","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.21074"}},"official":null}},{"url":"/paper/finereason-evaluating-and-improving-llms","slug":"finereason-evaluating-and-improving-llms","title":"FINEREASON: Evaluating and Improving LLMs' Deliberate Reasoning through Reflective Puzzle Solving","date":"2025-02-27","arxiv_id":"2502.20238","repositories_listed":1,"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":4,"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/finereason-evaluating-and-improving-llms#ran","syntology_url":"https://syntology.ai/paper/2502.20238","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.20238"}},"official":{"repos":["DAMO-NLP-SG/FineReason"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/self-training-elicits-concise-reasoning-in","slug":"self-training-elicits-concise-reasoning-in","title":"Self-Training Elicits Concise Reasoning in Large Language Models","date":"2025-02-27","arxiv_id":"2502.20122","repositories_listed":1,"syntology":{"n":16,"n_ran":15,"n_constructed":0,"n_ran_checked":13,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":2,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/self-training-elicits-concise-reasoning-in#ran","syntology_url":"https://syntology.ai/paper/2502.20122","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.20122"}},"official":{"repos":["tergelmunkhbat/concise-reasoning"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/big-math-a-large-scale-high-quality-math","slug":"big-math-a-large-scale-high-quality-math","title":"Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models","date":"2025-02-24","arxiv_id":"2502.17387","repositories_listed":1,"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":14,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/big-math-a-large-scale-high-quality-math#ran","syntology_url":"https://syntology.ai/paper/2502.17387","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.17387"}},"official":{"repos":["synthlabsai/big-math"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/earlier-tokens-contribute-more-learning","slug":"earlier-tokens-contribute-more-learning","title":"Earlier Tokens Contribute More: Learning Direct Preference Optimization From Temporal Decay Perspective","date":"2025-02-20","arxiv_id":"2502.14340","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":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/earlier-tokens-contribute-more-learning#ran","syntology_url":"https://syntology.ai/paper/2502.14340","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.14340"}},"official":{"repos":["lotusrc/d2po"],"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/nlora-nystrom-initiated-low-rank-adaptation","slug":"nlora-nystrom-initiated-low-rank-adaptation","title":"NLoRA: Nyström-Initiated Low-Rank Adaptation for Large Language Models","date":"2025-02-20","arxiv_id":"2502.14482","repositories_listed":1,"syntology":null},{"url":"/paper/sift-grounding-llm-reasoning-in-contexts-via","slug":"sift-grounding-llm-reasoning-in-contexts-via","title":"SIFT: Grounding LLM Reasoning in Contexts via Stickers","date":"2025-02-19","arxiv_id":"2502.14922","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/sift-grounding-llm-reasoning-in-contexts-via#ran","syntology_url":"https://syntology.ai/paper/2502.14922","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.14922"}},"official":{"repos":["zhijie-group/sift"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/treecut-a-synthetic-unanswerable-math-word","slug":"treecut-a-synthetic-unanswerable-math-word","title":"TreeCut: A Synthetic Unanswerable Math Word Problem Dataset for LLM Hallucination Evaluation","date":"2025-02-19","arxiv_id":"2502.13442","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/treecut-a-synthetic-unanswerable-math-word#ran","syntology_url":"https://syntology.ai/paper/2502.13442","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.13442"}},"official":{"repos":["j-bagel/treecut-math"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/smart-self-aware-agent-for-tool-overuse","slug":"smart-self-aware-agent-for-tool-overuse","title":"SMART: Self-Aware Agent for Tool Overuse Mitigation","date":"2025-02-17","arxiv_id":"2502.11435","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 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; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/smart-self-aware-agent-for-tool-overuse#ran","syntology_url":"https://syntology.ai/paper/2502.11435","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.11435"}},"official":{"repos":["qiancheng0/open-smartagent"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tokenskip-controllable-chain-of-thought","slug":"tokenskip-controllable-chain-of-thought","title":"TokenSkip: Controllable Chain-of-Thought Compression in LLMs","date":"2025-02-17","arxiv_id":"2502.12067","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":6,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":4,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tokenskip-controllable-chain-of-thought#ran","syntology_url":"https://syntology.ai/paper/2502.12067","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.12067"}},"official":{"repos":["hemingkx/tokenskip"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/don-t-get-lost-in-the-trees-streamlining-llm","slug":"don-t-get-lost-in-the-trees-streamlining-llm","title":"Don't Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration Pitfalls","date":"2025-02-16","arxiv_id":"2502.11183","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"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/don-t-get-lost-in-the-trees-streamlining-llm#ran","syntology_url":"https://syntology.ai/paper/2502.11183","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.11183"}},"official":{"repos":["soistesimmer/fetch"],"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/cot-valve-length-compressible-chain-of","slug":"cot-valve-length-compressible-chain-of","title":"CoT-Valve: Length-Compressible Chain-of-Thought Tuning","date":"2025-02-13","arxiv_id":"2502.09601","repositories_listed":1,"syntology":null},{"url":"/paper/mathematical-reasoning-in-large-language","slug":"mathematical-reasoning-in-large-language","title":"Mathematical Reasoning in Large Language Models: Assessing Logical and Arithmetic Errors across Wide Numerical Ranges","date":"2025-02-12","arxiv_id":"2502.08680","repositories_listed":1,"syntology":null},{"url":"/paper/upweighting-easy-samples-in-fine-tuning","slug":"upweighting-easy-samples-in-fine-tuning","title":"Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting","date":"2025-02-05","arxiv_id":"2502.02797","repositories_listed":1,"syntology":null},{"url":"/paper/mygo-multiplex-cot-a-method-for-self","slug":"mygo-multiplex-cot-a-method-for-self","title":"MyGO Multiplex CoT: A Method for Self-Reflection in Large Language Models via Double Chain of Thought Thinking","date":"2025-01-20","arxiv_id":"2501.13117","repositories_listed":1,"syntology":null},{"url":"/paper/arithmattack-evaluating-robustness-of-llms-to","slug":"arithmattack-evaluating-robustness-of-llms-to","title":"ArithmAttack: Evaluating Robustness of LLMs to Noisy Context in Math Problem Solving","date":"2025-01-14","arxiv_id":"2501.08203","repositories_listed":1,"syntology":null},{"url":"/paper/discquant-a-quantization-method-for-neural","slug":"discquant-a-quantization-method-for-neural","title":"DiscQuant: A Quantization Method for Neural Networks Inspired by Discrepancy Theory","date":"2025-01-11","arxiv_id":"2501.06417","repositories_listed":1,"syntology":null},{"url":"/paper/dive-diversified-iterative-self-improvement","slug":"dive-diversified-iterative-self-improvement","title":"DIVE: Diversified Iterative Self-Improvement","date":"2025-01-01","arxiv_id":"2501.00747","repositories_listed":1,"syntology":null},{"url":"/paper/llm2-let-large-language-models-harness-system","slug":"llm2-let-large-language-models-harness-system","title":"LLM2: Let Large Language Models Harness System 2 Reasoning","date":"2024-12-29","arxiv_id":"2412.20372","repositories_listed":1,"syntology":null},{"url":"/paper/natural-language-fine-tuning","slug":"natural-language-fine-tuning","title":"Natural Language Fine-Tuning","date":"2024-12-29","arxiv_id":"2412.20382","repositories_listed":1,"syntology":null},{"url":"/paper/inference-scaling-vs-reasoning-an-empirical","slug":"inference-scaling-vs-reasoning-an-empirical","title":"Inference Scaling vs Reasoning: An Empirical Analysis of Compute-Optimal LLM Problem-Solving","date":"2024-12-20","arxiv_id":"2412.16260","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-knowledge-distillation-for-llms","slug":"enhancing-knowledge-distillation-for-llms","title":"Enhancing Knowledge Distillation for LLMs with Response-Priming Prompting","date":"2024-12-18","arxiv_id":"2412.17846","repositories_listed":1,"syntology":null},{"url":"/paper/sepllm-accelerate-large-language-models-by","slug":"sepllm-accelerate-large-language-models-by","title":"SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator","date":"2024-12-16","arxiv_id":"2412.12094","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/sepllm-accelerate-large-language-models-by#ran","syntology_url":"https://syntology.ai/paper/2412.12094","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.12094"}},"official":{"repos":["HKUDS/SepLLM"],"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/entropy-regularized-process-reward-model","slug":"entropy-regularized-process-reward-model","title":"Entropy-Regularized Process Reward Model","date":"2024-12-15","arxiv_id":"2412.11006","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/entropy-regularized-process-reward-model#ran","syntology_url":"https://syntology.ai/paper/2412.11006","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.11006"}},"official":{"repos":["hanningzhang/er-prm"],"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","unlocated"]}}},{"url":"/paper/greater-gradients-over-reasoning-makes","slug":"greater-gradients-over-reasoning-makes","title":"GReaTer: Gradients over Reasoning Makes Smaller Language Models Strong Prompt Optimizers","date":"2024-12-12","arxiv_id":"2412.09722","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/greater-gradients-over-reasoning-makes#ran","syntology_url":"https://syntology.ai/paper/2412.09722","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.09722"}},"official":{"repos":["psunlpgroup/greater"],"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/lexico-extreme-kv-cache-compression-via","slug":"lexico-extreme-kv-cache-compression-via","title":"Lexico: Extreme KV Cache Compression via Sparse Coding over Universal Dictionaries","date":"2024-12-12","arxiv_id":"2412.08890","repositories_listed":1,"syntology":null},{"url":"/paper/processbench-identifying-process-errors-in","slug":"processbench-identifying-process-errors-in","title":"ProcessBench: Identifying Process Errors in Mathematical Reasoning","date":"2024-12-09","arxiv_id":"2412.06559","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/processbench-identifying-process-errors-in#ran","syntology_url":"https://syntology.ai/paper/2412.06559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.06559"}},"official":{"repos":["qwenlm/processbench"],"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/how-to-correctly-do-semantic-backpropagation","slug":"how-to-correctly-do-semantic-backpropagation","title":"How to Correctly do Semantic Backpropagation on Language-based Agentic Systems","date":"2024-12-04","arxiv_id":"2412.03624","repositories_listed":1,"syntology":{"n":8,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/how-to-correctly-do-semantic-backpropagation#ran","syntology_url":"https://syntology.ai/paper/2412.03624","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.03624"}},"official":{"repos":["hishamalyahya/semantic_backprop"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}}],"syntology_records":58,"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":81,"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/gsm8k-on-gsm8k","since_archive":"/sota/gsm8k-on-gsm8k#since-judged","papers_judged":81,"placed":0}]},"papers_where_code_ran":116,"papers_where_code_ran_first_page":"/task/gsm8k/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":5,"url":"/task/gsm8k/papers/2","json":"/task/gsm8k/papers/2.json","rows":100},{"order":"archive","page":3,"of":5,"url":"/task/gsm8k/papers/3","json":"/task/gsm8k/papers/3.json","rows":100},{"order":"archive","page":4,"of":5,"url":"/task/gsm8k/papers/4","json":"/task/gsm8k/papers/4.json","rows":100},{"order":"archive","page":5,"of":5,"url":"/task/gsm8k/papers/5","json":"/task/gsm8k/papers/5.json","rows":39},{"order":"ran","page":1,"of":2,"url":"/task/gsm8k/papers/ran/1","json":"/task/gsm8k/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":2,"url":"/task/gsm8k/papers/ran/2","json":"/task/gsm8k/papers/ran/2.json","rows":16}],"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":"8f1e4a8998c86b7f6c424d9d589df015ef444ecbea604c5cec4cf2b9c41af9fe","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}