{"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/mmlu","name":"MMLU","slug":"mmlu","description_markdown":null,"categories":[{"name":"Knowledge Base","url":"/area/knowledge-base"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":340,"papers_with_code":156,"benchmarks":1,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"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/mmlu-on-mmlu-pro","slug":"mmlu-on-mmlu-pro","dataset":"MMLU-Pro","dataset_url":"/dataset/mmlu-pro","rows_in_archive":1,"metrics":["0-shot MRR"],"first_row_in_archive_order":{"model":"Orange-mini","paper_title":"MyGO Multiplex CoT: A Method for Self-Reflection in Large Language Models via Double Chain of Thought Thinking","paper_url":"/paper/mygo-multiplex-cot-a-method-for-self","paper_date":"2025-01-20","arxiv_id":"2501.13117","code_links":[{"title":"data-dream-gdsp/Multiplex-CoT","url":"https://github.com/data-dream-gdsp/Multiplex-CoT"}],"syntology":null}},{"leaderboard":null,"slug":"mmlu-on-mmlu-5-shots","dataset":"mmlu (5-shots)","dataset_url":null,"rows_in_archive":0,"metrics":["acc"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"mmlu-on-mmlu-chat-cot","dataset":"mmlu (chat CoT)","dataset_url":null,"rows_in_archive":0,"metrics":["exact_match"],"first_row_in_archive_order":null}],"datasets":[{"url":"/dataset/mmlu-pro","name":"MMLU-Pro","full_name":"","num_papers_in_archive":150}],"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":4,"rows_per_page":100,"shown":100,"of":340,"of_with_code":156,"tagged_in_all":340,"counts":{"archive_papers_tagged":340,"with_a_code_link":156,"where_syntology_ran_a_sample":78,"not_listed_spam_title":0,"listed":340,"listed_where_code_ran":78,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":59,"every_run_a_failure_of_syntologys_instrument":19,"listed_with_a_run_with_no_instrument_failure":59,"listed_every_run_a_failure_of_syntologys_instrument":19,"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/scaling-instruction-finetuned-language-models","slug":"scaling-instruction-finetuned-language-models","title":"Scaling Instruction-Finetuned Language Models","date":"2022-10-20","arxiv_id":"2210.11416","repositories_listed":9,"syntology":{"n":17,"n_ran":8,"n_constructed":1,"n_ran_checked":1,"n_instrument":7,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"8 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; 7 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/scaling-instruction-finetuned-language-models#ran","syntology_url":"https://syntology.ai/paper/2210.11416","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.11416"}},"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/tinybenchmarks-evaluating-llms-with-fewer","slug":"tinybenchmarks-evaluating-llms-with-fewer","title":"tinyBenchmarks: evaluating LLMs with fewer examples","date":"2024-02-22","arxiv_id":"2402.14992","repositories_listed":4,"syntology":{"n":39,"n_ran":25,"n_constructed":0,"n_ran_checked":22,"n_instrument":3,"n_unverified":14,"n_honours":4,"n_violates":1,"n_no_contract":17,"n_pointer_only":17,"phrase":"25 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 4 honoured, 1 violated, 17 with no contract checked; 3 where Syntology's instrument failed) · 14 unverified","sample_list":"/paper/tinybenchmarks-evaluating-llms-with-fewer#ran","syntology_url":"https://syntology.ai/paper/2402.14992","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14992"}},"official":{"repos":["felipemaiapolo/efficbench","felipemaiapolo/tinybenchmarks"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":12,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/datacomp-lm-in-search-of-the-next-generation","slug":"datacomp-lm-in-search-of-the-next-generation","title":"DataComp-LM: In search of the next generation of training sets for language models","date":"2024-06-17","arxiv_id":"2406.11794","repositories_listed":3,"syntology":{"n":22,"n_ran":22,"n_constructed":0,"n_ran_checked":9,"n_instrument":13,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"phrase":"22 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 13 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/datacomp-lm-in-search-of-the-next-generation#ran","syntology_url":"https://syntology.ai/paper/2406.11794","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11794"}},"official":null}},{"url":"/paper/are-we-done-with-mmlu","slug":"are-we-done-with-mmlu","title":"Are We Done with MMLU?","date":"2024-06-06","arxiv_id":"2406.04127","repositories_listed":3,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"6 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; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/are-we-done-with-mmlu#ran","syntology_url":"https://syntology.ai/paper/2406.04127","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04127"}},"official":{"repos":["aryopg/mmlu-redux"],"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":["listed","official"]}}},{"url":"/paper/replug-retrieval-augmented-black-box-language","slug":"replug-retrieval-augmented-black-box-language","title":"REPLUG: Retrieval-Augmented Black-Box Language Models","date":"2023-01-30","arxiv_id":"2301.12652","repositories_listed":3,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":13,"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) · 3 unverified","sample_list":"/paper/replug-retrieval-augmented-black-box-language#ran","syntology_url":"https://syntology.ai/paper/2301.12652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12652"}},"official":null}},{"url":"/paper/lm2-large-memory-models","slug":"lm2-large-memory-models","title":"LM2: Large Memory Models","date":"2025-02-09","arxiv_id":"2502.06049","repositories_listed":2,"syntology":null},{"url":"/paper/what-matters-in-transformers-not-all","slug":"what-matters-in-transformers-not-all","title":"What Matters in Transformers? Not All Attention is Needed","date":"2024-06-22","arxiv_id":"2406.15786","repositories_listed":2,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":5,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/what-matters-in-transformers-not-all#ran","syntology_url":"https://syntology.ai/paper/2406.15786","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.15786"}},"official":{"repos":["case-lab-umd/llm-drop","shwai-he/llm-drop"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/mmlu-pro-a-more-robust-and-challenging-multi","slug":"mmlu-pro-a-more-robust-and-challenging-multi","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","date":"2024-06-03","arxiv_id":"2406.01574","repositories_listed":2,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":3,"n_instrument":9,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"12 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; 9 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mmlu-pro-a-more-robust-and-challenging-multi#ran","syntology_url":"https://syntology.ai/paper/2406.01574","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.01574"}},"official":null}},{"url":"/paper/owlore-outlier-weighed-layerwise-sampled-low","slug":"owlore-outlier-weighed-layerwise-sampled-low","title":"OwLore: Outlier-weighed Layerwise Sampled Low-Rank Projection for Memory-Efficient LLM Fine-tuning","date":"2024-05-28","arxiv_id":"2405.18380","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/owlore-outlier-weighed-layerwise-sampled-low#ran","syntology_url":"https://syntology.ai/paper/2405.18380","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.18380"}},"official":{"repos":["pixeli99/owlore"],"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":["listed","official"]}}},{"url":"/paper/efficient-multi-prompt-evaluation-of-llms","slug":"efficient-multi-prompt-evaluation-of-llms","title":"Efficient multi-prompt evaluation of LLMs","date":"2024-05-27","arxiv_id":"2405.17202","repositories_listed":2,"syntology":{"n":9,"n_ran":7,"n_constructed":1,"n_ran_checked":4,"n_instrument":3,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/efficient-multi-prompt-evaluation-of-llms#ran","syntology_url":"https://syntology.ai/paper/2405.17202","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17202"}},"official":{"repos":["felipemaiapolo/prompteval","microsoft/promptbench"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":1,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/make-your-llm-fully-utilize-the-context","slug":"make-your-llm-fully-utilize-the-context","title":"Make Your LLM Fully Utilize the Context","date":"2024-04-25","arxiv_id":"2404.16811","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":0,"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; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/make-your-llm-fully-utilize-the-context#ran","syntology_url":"https://syntology.ai/paper/2404.16811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.16811"}},"official":{"repos":["microsoft/FILM"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-strongreject-for-empty-jailbreaks","slug":"a-strongreject-for-empty-jailbreaks","title":"A StrongREJECT for Empty Jailbreaks","date":"2024-02-15","arxiv_id":"2402.10260","repositories_listed":2,"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 4 unverified","sample_list":"/paper/a-strongreject-for-empty-jailbreaks#ran","syntology_url":"https://syntology.ai/paper/2402.10260","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10260"}},"official":{"repos":["alexandrasouly/strongreject"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"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/red-teaming-large-language-models-using-chain","slug":"red-teaming-large-language-models-using-chain","title":"Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment","date":"2023-08-18","arxiv_id":"2308.09662","repositories_listed":2,"syntology":null},{"url":"/paper/augmentation-adapted-retriever-improves","slug":"augmentation-adapted-retriever-improves","title":"Augmentation-Adapted Retriever Improves Generalization of Language Models as Generic Plug-In","date":"2023-05-27","arxiv_id":"2305.17331","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_constructed":1,"n_ran_checked":8,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":2,"phrase":"9 ran (of which 1 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/augmentation-adapted-retriever-improves#ran","syntology_url":"https://syntology.ai/paper/2305.17331","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.17331"}},"official":{"repos":["openmatch/augmentation-adapted-retriever"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/art-automatic-multi-step-reasoning-and-tool","slug":"art-automatic-multi-step-reasoning-and-tool","title":"ART: Automatic multi-step reasoning and tool-use for large language models","date":"2023-03-16","arxiv_id":"2303.09014","repositories_listed":2,"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":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) · 1 unverified","sample_list":"/paper/art-automatic-multi-step-reasoning-and-tool#ran","syntology_url":"https://syntology.ai/paper/2303.09014","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.09014"}},"official":null}},{"url":"/paper/few-shot-learning-with-retrieval-augmented","slug":"few-shot-learning-with-retrieval-augmented","title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","date":"2022-08-05","arxiv_id":"2208.03299","repositories_listed":2,"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/few-shot-learning-with-retrieval-augmented#ran","syntology_url":"https://syntology.ai/paper/2208.03299","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.03299"}},"official":{"repos":["facebookresearch/atlas"],"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/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/training-compute-optimal-large-language","slug":"training-compute-optimal-large-language","title":"Training Compute-Optimal Large Language Models","date":"2022-03-29","arxiv_id":"2203.15556","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":3,"n_ran_checked":5,"n_instrument":3,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"8 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/training-compute-optimal-large-language#ran","syntology_url":"https://syntology.ai/paper/2203.15556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15556"}},"official":null}},{"url":"/paper/step-wise-policy-for-rare-tool-knowledge","slug":"step-wise-policy-for-rare-tool-knowledge","title":"Step-wise Policy for Rare-tool Knowledge (SPaRK): Offline RL that Drives Diverse Tool Use in LLMs","date":"2025-07-15","arxiv_id":"2507.11371","repositories_listed":1,"syntology":null},{"url":"/paper/growing-transformers-modular-composition-and","slug":"growing-transformers-modular-composition-and","title":"Growing Transformers: Modular Composition and Layer-wise Expansion on a Frozen Substrate","date":"2025-07-08","arxiv_id":"2507.07129","repositories_listed":1,"syntology":null},{"url":"/paper/the-delta-learning-hypothesis-preference","slug":"the-delta-learning-hypothesis-preference","title":"The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains","date":"2025-07-08","arxiv_id":"2507.06187","repositories_listed":1,"syntology":null},{"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/emergent-semantics-beyond-token-embeddings","slug":"emergent-semantics-beyond-token-embeddings","title":"Emergent Semantics Beyond Token Embeddings: Transformer LMs with Frozen Visual Unicode Representations","date":"2025-07-07","arxiv_id":"2507.04886","repositories_listed":1,"syntology":null},{"url":"/paper/do-language-models-mirror-human-confidence","slug":"do-language-models-mirror-human-confidence","title":"Do Language Models Mirror Human Confidence? Exploring Psychological Insights to Address Overconfidence in LLMs","date":"2025-05-31","arxiv_id":"2506.00582","repositories_listed":1,"syntology":null},{"url":"/paper/helm-hyperbolic-large-language-models-via","slug":"helm-hyperbolic-large-language-models-via","title":"HELM: Hyperbolic Large Language Models via Mixture-of-Curvature Experts","date":"2025-05-30","arxiv_id":"2505.24722","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/helm-hyperbolic-large-language-models-via#ran","syntology_url":"https://syntology.ai/paper/2505.24722","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.24722"}},"official":{"repos":["graph-and-geometric-learning/helm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/silvr-a-simple-language-based-video-reasoning","slug":"silvr-a-simple-language-based-video-reasoning","title":"SiLVR: A Simple Language-based Video Reasoning Framework","date":"2025-05-30","arxiv_id":"2505.24869","repositories_listed":1,"syntology":null},{"url":"/paper/simulating-training-data-leakage-in-multiple","slug":"simulating-training-data-leakage-in-multiple","title":"Simulating Training Data Leakage in Multiple-Choice Benchmarks for LLM Evaluation","date":"2025-05-30","arxiv_id":"2505.24263","repositories_listed":1,"syntology":null},{"url":"/paper/dyepack-provably-flagging-test-set","slug":"dyepack-provably-flagging-test-set","title":"DyePack: Provably Flagging Test Set Contamination in LLMs Using Backdoors","date":"2025-05-29","arxiv_id":"2505.23001","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcing-general-reasoning-without","slug":"reinforcing-general-reasoning-without","title":"Reinforcing General Reasoning without Verifiers","date":"2025-05-27","arxiv_id":"2505.21493","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/reinforcing-general-reasoning-without#ran","syntology_url":"https://syntology.ai/paper/2505.21493","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.21493"}},"official":{"repos":["sail-sg/verifree"],"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/capability-based-scaling-laws-for-llm-red","slug":"capability-based-scaling-laws-for-llm-red","title":"Capability-Based Scaling Laws for LLM Red-Teaming","date":"2025-05-26","arxiv_id":"2505.20162","repositories_listed":1,"syntology":{"n":23,"n_ran":17,"n_constructed":0,"n_ran_checked":17,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":17,"n_pointer_only":0,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/capability-based-scaling-laws-for-llm-red#ran","syntology_url":"https://syntology.ai/paper/2505.20162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.20162"}},"official":{"repos":["kotekjedi/capability-based-scaling"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":17,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/bnmmlu-measuring-massive-multitask-language","slug":"bnmmlu-measuring-massive-multitask-language","title":"BnMMLU: Measuring Massive Multitask Language Understanding in Bengali","date":"2025-05-25","arxiv_id":"2505.18951","repositories_listed":1,"syntology":null},{"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/lota-qaf-lossless-ternary-adaptation-for","slug":"lota-qaf-lossless-ternary-adaptation-for","title":"LoTA-QAF: Lossless Ternary Adaptation for Quantization-Aware Fine-Tuning","date":"2025-05-24","arxiv_id":"2505.18724","repositories_listed":1,"syntology":null},{"url":"/paper/training-step-level-reasoning-verifiers-with","slug":"training-step-level-reasoning-verifiers-with","title":"Training Step-Level Reasoning Verifiers with Formal Verification Tools","date":"2025-05-21","arxiv_id":"2505.15960","repositories_listed":1,"syntology":null},{"url":"/paper/general-reasoner-advancing-llm-reasoning","slug":"general-reasoner-advancing-llm-reasoning","title":"General-Reasoner: Advancing LLM Reasoning Across All Domains","date":"2025-05-20","arxiv_id":"2505.14652","repositories_listed":1,"syntology":null},{"url":"/paper/void-in-language-models","slug":"void-in-language-models","title":"Void in Language Models","date":"2025-05-20","arxiv_id":"2505.14467","repositories_listed":1,"syntology":null},{"url":"/paper/decentralized-arena-towards-democratic-and","slug":"decentralized-arena-towards-democratic-and","title":"Decentralized Arena: Towards Democratic and Scalable Automatic Evaluation of Language Models","date":"2025-05-19","arxiv_id":"2505.12808","repositories_listed":1,"syntology":null},{"url":"/paper/warm-up-before-you-train-unlocking-general","slug":"warm-up-before-you-train-unlocking-general","title":"Warm Up Before You Train: Unlocking General Reasoning in Resource-Constrained Settings","date":"2025-05-19","arxiv_id":"2505.13718","repositories_listed":1,"syntology":null},{"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/tiny-qa-benchmark-ultra-lightweight-synthetic","slug":"tiny-qa-benchmark-ultra-lightweight-synthetic","title":"Tiny QA Benchmark++: Ultra-Lightweight, Synthetic Multilingual Dataset Generation & Smoke-Tests for Continuous LLM Evaluation","date":"2025-05-17","arxiv_id":"2505.12058","repositories_listed":1,"syntology":null},{"url":"/paper/2505-11010","slug":"2505-11010","title":"Review-Instruct: A Review-Driven Multi-Turn Conversations Generation Method for Large Language Models","date":"2025-05-16","arxiv_id":"2505.11010","repositories_listed":1,"syntology":null},{"url":"/paper/medcasereasoning-evaluating-and-learning","slug":"medcasereasoning-evaluating-and-learning","title":"MedCaseReasoning: Evaluating and learning diagnostic reasoning from clinical case reports","date":"2025-05-16","arxiv_id":"2505.11733","repositories_listed":1,"syntology":null},{"url":"/paper/reasonir-training-retrievers-for-reasoning","slug":"reasonir-training-retrievers-for-reasoning","title":"ReasonIR: Training Retrievers for Reasoning Tasks","date":"2025-04-29","arxiv_id":"2504.20595","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/reasonir-training-retrievers-for-reasoning#ran","syntology_url":"https://syntology.ai/paper/2504.20595","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.20595"}},"official":{"repos":["facebookresearch/reasonir"],"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":["unlocated"]}}},{"url":"/paper/video-mmlu-a-massive-multi-discipline-lecture","slug":"video-mmlu-a-massive-multi-discipline-lecture","title":"Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmark","date":"2025-04-20","arxiv_id":"2504.14693","repositories_listed":1,"syntology":null},{"url":"/paper/sha256-at-semeval-2025-task-4-selective","slug":"sha256-at-semeval-2025-task-4-selective","title":"SHA256 at SemEval-2025 Task 4: Selective Amnesia -- Constrained Unlearning for Large Language Models via Knowledge Isolation","date":"2025-04-17","arxiv_id":"2504.12996","repositories_listed":1,"syntology":null},{"url":"/paper/datadecide-how-to-predict-best-pretraining","slug":"datadecide-how-to-predict-best-pretraining","title":"DataDecide: How to Predict Best Pretraining Data with Small Experiments","date":"2025-04-15","arxiv_id":"2504.11393","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":8,"n_pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/datadecide-how-to-predict-best-pretraining#ran","syntology_url":"https://syntology.ai/paper/2504.11393","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.11393"}},"official":null}},{"url":"/paper/probing-then-editing-response-personality-of","slug":"probing-then-editing-response-personality-of","title":"Probing then Editing Response Personality of Large Language Models","date":"2025-04-14","arxiv_id":"2504.10227","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-cheatsheet-test-time-learning-with","slug":"dynamic-cheatsheet-test-time-learning-with","title":"Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory","date":"2025-04-10","arxiv_id":"2504.07952","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":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) · 0 unverified","sample_list":"/paper/dynamic-cheatsheet-test-time-learning-with#ran","syntology_url":"https://syntology.ai/paper/2504.07952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.07952"}},"official":{"repos":["suzgunmirac/dynamic-cheatsheet"],"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/task-circuit-quantization-leveraging","slug":"task-circuit-quantization-leveraging","title":"Task-Circuit Quantization: Leveraging Knowledge Localization and Interpretability for Compression","date":"2025-04-10","arxiv_id":"2504.07389","repositories_listed":1,"syntology":null},{"url":"/paper/right-question-is-already-half-the-answer","slug":"right-question-is-already-half-the-answer","title":"Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization","date":"2025-04-08","arxiv_id":"2504.05812","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/right-question-is-already-half-the-answer#ran","syntology_url":"https://syntology.ai/paper/2504.05812","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.05812"}},"official":{"repos":["qingyangzhang/empo"],"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":["unlocated"]}}},{"url":"/paper/yourbench-easy-custom-evaluation-sets-for","slug":"yourbench-easy-custom-evaluation-sets-for","title":"YourBench: Easy Custom Evaluation Sets for Everyone","date":"2025-04-02","arxiv_id":"2504.01833","repositories_listed":1,"syntology":null},{"url":"/paper/quamba2-a-robust-and-scalable-post-training","slug":"quamba2-a-robust-and-scalable-post-training","title":"Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models","date":"2025-03-28","arxiv_id":"2503.22879","repositories_listed":1,"syntology":null},{"url":"/paper/effective-skill-unlearning-through","slug":"effective-skill-unlearning-through","title":"Effective Skill Unlearning through Intervention and Abstention","date":"2025-03-27","arxiv_id":"2503.21730","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/effective-skill-unlearning-through#ran","syntology_url":"https://syntology.ai/paper/2503.21730","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.21730"}},"official":{"repos":["trustworthy-ml-lab/effective_skill_unlearning"],"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/mobile-mmlu-a-mobile-intelligence-language","slug":"mobile-mmlu-a-mobile-intelligence-language","title":"Mobile-MMLU: A Mobile Intelligence Language Understanding Benchmark","date":"2025-03-26","arxiv_id":"2503.20786","repositories_listed":1,"syntology":null},{"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/chatbench-from-static-benchmarks-to-human-ai","slug":"chatbench-from-static-benchmarks-to-human-ai","title":"ChatBench: From Static Benchmarks to Human-AI Evaluation","date":"2025-03-22","arxiv_id":"2504.07114","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":7,"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) · 2 unverified","sample_list":"/paper/chatbench-from-static-benchmarks-to-human-ai#ran","syntology_url":"https://syntology.ai/paper/2504.07114","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.07114"}},"official":{"repos":["serinachang5/interactive-eval"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/when-an-llm-is-apprehensive-about-its-answers","slug":"when-an-llm-is-apprehensive-about-its-answers","title":"When an LLM is apprehensive about its answers -- and when its uncertainty is justified","date":"2025-03-03","arxiv_id":"2503.01688","repositories_listed":1,"syntology":null},{"url":"/paper/score-systematic-consistency-and-robustness","slug":"score-systematic-consistency-and-robustness","title":"SCORE: Systematic COnsistency and Robustness Evaluation for Large Language Models","date":"2025-02-28","arxiv_id":"2503.00137","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":0,"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/score-systematic-consistency-and-robustness#ran","syntology_url":"https://syntology.ai/paper/2503.00137","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.00137"}},"official":{"repos":["EleutherAI/lm-evaluation-harness"],"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/voting-or-consensus-decision-making-in-multi","slug":"voting-or-consensus-decision-making-in-multi","title":"Voting or Consensus? Decision-Making in Multi-Agent Debate","date":"2025-02-26","arxiv_id":"2502.19130","repositories_listed":1,"syntology":null},{"url":"/paper/wicked-a-simple-method-to-make-multiple","slug":"wicked-a-simple-method-to-make-multiple","title":"WiCkeD: A Simple Method to Make Multiple Choice Benchmarks More Challenging","date":"2025-02-25","arxiv_id":"2502.18316","repositories_listed":1,"syntology":null},{"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/tumlu-a-unified-and-native-language","slug":"tumlu-a-unified-and-native-language","title":"TUMLU: A Unified and Native Language Understanding Benchmark for Turkic Languages","date":"2025-02-16","arxiv_id":"2502.11020","repositories_listed":1,"syntology":null},{"url":"/paper/forget-what-you-know-about-llms-evaluations","slug":"forget-what-you-know-about-llms-evaluations","title":"Forget What You Know about LLMs Evaluations - LLMs are Like a Chameleon","date":"2025-02-11","arxiv_id":"2502.07445","repositories_listed":1,"syntology":null},{"url":"/paper/opengrok-enhancing-sns-data-processing-with","slug":"opengrok-enhancing-sns-data-processing-with","title":"OpenGrok: Enhancing SNS Data Processing with Distilled Knowledge and Mask-like Mechanisms","date":"2025-02-11","arxiv_id":"2502.07312","repositories_listed":1,"syntology":null},{"url":"/paper/rotor-towards-more-reliable-responses-for","slug":"rotor-towards-more-reliable-responses-for","title":"RoToR: Towards More Reliable Responses for Order-Invariant Inputs","date":"2025-02-10","arxiv_id":"2502.08662","repositories_listed":1,"syntology":null},{"url":"/paper/evaluation-of-large-language-models-via","slug":"evaluation-of-large-language-models-via","title":"Evaluation of Large Language Models via Coupled Token Generation","date":"2025-02-03","arxiv_id":"2502.01754","repositories_listed":1,"syntology":null},{"url":"/paper/qless-a-quantized-approach-for-data-valuation","slug":"qless-a-quantized-approach-for-data-valuation","title":"QLESS: A Quantized Approach for Data Valuation and Selection in Large Language Model Fine-Tuning","date":"2025-02-03","arxiv_id":"2502.01703","repositories_listed":1,"syntology":null},{"url":"/paper/llm-powered-benchmark-factory-reliable","slug":"llm-powered-benchmark-factory-reliable","title":"LLM-Powered Benchmark Factory: Reliable, Generic, and Efficient","date":"2025-02-02","arxiv_id":"2502.01683","repositories_listed":1,"syntology":null},{"url":"/paper/dfpe-a-diverse-fingerprint-ensemble-for","slug":"dfpe-a-diverse-fingerprint-ensemble-for","title":"DFPE: A Diverse Fingerprint Ensemble for Enhancing LLM Performance","date":"2025-01-29","arxiv_id":"2501.17479","repositories_listed":1,"syntology":null},{"url":"/paper/explain-query-test-self-evaluating-llms-via","slug":"explain-query-test-self-evaluating-llms-via","title":"Explain-Query-Test: Self-Evaluating LLMs Via Explanation and Comprehension Discrepancy","date":"2025-01-20","arxiv_id":"2501.11721","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/control-llm-controlled-evolution-for","slug":"control-llm-controlled-evolution-for","title":"Control LLM: Controlled Evolution for Intelligence Retention in LLM","date":"2025-01-19","arxiv_id":"2501.10979","repositories_listed":1,"syntology":null},{"url":"/paper/chair-classifier-of-hallucination-as-improver","slug":"chair-classifier-of-hallucination-as-improver","title":"CHAIR -- Classifier of Hallucination as Improver","date":"2025-01-05","arxiv_id":"2501.02518","repositories_listed":1,"syntology":null},{"url":"/paper/mmlu-cf-a-contamination-free-multi-task","slug":"mmlu-cf-a-contamination-free-multi-task","title":"MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmark","date":"2024-12-19","arxiv_id":"2412.15194","repositories_listed":1,"syntology":null},{"url":"/paper/orbit-cost-effective-dataset-curation-for","slug":"orbit-cost-effective-dataset-curation-for","title":"ORBIT: Cost-Effective Dataset Curation for Large Language Model Domain Adaptation with an Astronomy Case Study","date":"2024-12-19","arxiv_id":"2412.14436","repositories_listed":1,"syntology":null},{"url":"/paper/bridging-the-gap-enhancing-llm-performance","slug":"bridging-the-gap-enhancing-llm-performance","title":"Bridging the Gap: Enhancing LLM Performance for Low-Resource African Languages with New Benchmarks, Fine-Tuning, and Cultural Adjustments","date":"2024-12-16","arxiv_id":"2412.12417","repositories_listed":1,"syntology":null},{"url":"/paper/llama-3-meets-moe-efficient-upcycling","slug":"llama-3-meets-moe-efficient-upcycling","title":"Llama 3 Meets MoE: Efficient Upcycling","date":"2024-12-13","arxiv_id":"2412.09952","repositories_listed":1,"syntology":null},{"url":"/paper/hadacore-tensor-core-accelerated-hadamard","slug":"hadacore-tensor-core-accelerated-hadamard","title":"HadaCore: Tensor Core Accelerated Hadamard Transform Kernel","date":"2024-12-12","arxiv_id":"2412.08832","repositories_listed":1,"syntology":null},{"url":"/paper/noise-injection-reveals-hidden-capabilities","slug":"noise-injection-reveals-hidden-capabilities","title":"Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models","date":"2024-12-02","arxiv_id":"2412.01784","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":3,"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/noise-injection-reveals-hidden-capabilities#ran","syntology_url":"https://syntology.ai/paper/2412.01784","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.01784"}},"official":{"repos":["camtice/sandbagdetect"],"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":["found_in_text","official"]}}},{"url":"/paper/todo-enhancing-llm-alignment-with-ternary","slug":"todo-enhancing-llm-alignment-with-ternary","title":"TODO: Enhancing LLM Alignment with Ternary Preferences","date":"2024-11-02","arxiv_id":"2411.02442","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/todo-enhancing-llm-alignment-with-ternary#ran","syntology_url":"https://syntology.ai/paper/2411.02442","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.02442"}},"official":{"repos":["xxares/todo"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/shopping-mmlu-a-massive-multi-task-online","slug":"shopping-mmlu-a-massive-multi-task-online","title":"Shopping MMLU: A Massive Multi-Task Online Shopping Benchmark for Large Language Models","date":"2024-10-28","arxiv_id":"2410.20745","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":2,"n_honours":1,"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; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/shopping-mmlu-a-massive-multi-task-online#ran","syntology_url":"https://syntology.ai/paper/2410.20745","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.20745"}},"official":{"repos":["kl4805/shoppingmmlu"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/logo-long-context-alignment-via-efficient","slug":"logo-long-context-alignment-via-efficient","title":"LOGO -- Long cOntext aliGnment via efficient preference Optimization","date":"2024-10-24","arxiv_id":"2410.18533","repositories_listed":1,"syntology":null},{"url":"/paper/read-me-refactorizing-llms-as-router","slug":"read-me-refactorizing-llms-as-router","title":"Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design","date":"2024-10-24","arxiv_id":"2410.19123","repositories_listed":1,"syntology":{"n":16,"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":5,"n_honours":4,"n_violates":0,"n_no_contract":3,"n_pointer_only":16,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/read-me-refactorizing-llms-as-router#ran","syntology_url":"https://syntology.ai/paper/2410.19123","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.19123"}},"official":{"repos":["vita-group/read-me"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/bento-benchmark-task-reduction-with-in","slug":"bento-benchmark-task-reduction-with-in","title":"BenTo: Benchmark Task Reduction with In-Context Transferability","date":"2024-10-17","arxiv_id":"2410.13804","repositories_listed":1,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":9,"n_instrument":3,"n_unverified":1,"n_honours":3,"n_violates":1,"n_no_contract":5,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 1 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/bento-benchmark-task-reduction-with-in#ran","syntology_url":"https://syntology.ai/paper/2410.13804","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13804"}},"official":{"repos":["tianyi-lab/bento"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/comat-chain-of-mathematically-annotated","slug":"comat-chain-of-mathematically-annotated","title":"CoMAT: Chain of Mathematically Annotated Thought Improves Mathematical Reasoning","date":"2024-10-14","arxiv_id":"2410.10336","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":1,"n_instrument":7,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":9,"phrase":"8 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; 7 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/comat-chain-of-mathematically-annotated#ran","syntology_url":"https://syntology.ai/paper/2410.10336","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10336"}},"official":{"repos":["joshuaongg21/comat"],"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":["official"]}}},{"url":"/paper/divide-reweight-and-conquer-a-logit","slug":"divide-reweight-and-conquer-a-logit","title":"Divide, Reweight, and Conquer: A Logit Arithmetic Approach for In-Context Learning","date":"2024-10-14","arxiv_id":"2410.10074","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/divide-reweight-and-conquer-a-logit#ran","syntology_url":"https://syntology.ai/paper/2410.10074","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10074"}},"official":{"repos":["chengsong-huang/lara"],"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/lolcats-on-low-rank-linearizing-of-large","slug":"lolcats-on-low-rank-linearizing-of-large","title":"LoLCATs: On Low-Rank Linearizing of Large Language Models","date":"2024-10-14","arxiv_id":"2410.10254","repositories_listed":1,"syntology":{"n":32,"n_ran":23,"n_constructed":9,"n_ran_checked":13,"n_instrument":10,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":0,"phrase":"23 ran (of which 9 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 10 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/lolcats-on-low-rank-linearizing-of-large#ran","syntology_url":"https://syntology.ai/paper/2410.10254","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10254"}},"official":{"repos":["hazyresearch/lolcats"],"state":"official (archive's flag): 23 ran","n_ran":23,"n_constructed":9,"n_ran_no_instrument_failure":13,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/mexa-multilingual-evaluation-of-english","slug":"mexa-multilingual-evaluation-of-english","title":"MEXA: Multilingual Evaluation of English-Centric LLMs via Cross-Lingual Alignment","date":"2024-10-08","arxiv_id":"2410.05873","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mexa-multilingual-evaluation-of-english#ran","syntology_url":"https://syntology.ai/paper/2410.05873","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05873"}},"official":{"repos":["cisnlp/mexa"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/commonit-commonality-aware-instruction-tuning","slug":"commonit-commonality-aware-instruction-tuning","title":"CommonIT: Commonality-Aware Instruction Tuning for Large Language Models via Data Partitions","date":"2024-10-04","arxiv_id":"2410.03077","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/commonit-commonality-aware-instruction-tuning#ran","syntology_url":"https://syntology.ai/paper/2410.03077","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.03077"}},"official":{"repos":["raojay7/commonit"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/llm-topla-efficient-llm-ensemble-by","slug":"llm-topla-efficient-llm-ensemble-by","title":"LLM-TOPLA: Efficient LLM Ensemble by Maximising Diversity","date":"2024-10-04","arxiv_id":"2410.03953","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":8,"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) · 3 unverified","sample_list":"/paper/llm-topla-efficient-llm-ensemble-by#ran","syntology_url":"https://syntology.ai/paper/2410.03953","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.03953"}},"official":{"repos":["git-disl/llm-topla"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/to-cot-or-not-to-cot-chain-of-thought-helps","slug":"to-cot-or-not-to-cot-chain-of-thought-helps","title":"To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning","date":"2024-09-18","arxiv_id":"2409.12183","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/to-cot-or-not-to-cot-chain-of-thought-helps#ran","syntology_url":"https://syntology.ai/paper/2409.12183","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.12183"}},"official":{"repos":["zayne-sprague/to-cot-or-not-to-cot"],"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/mmlu-pro-evaluating-higher-order-reasoning","slug":"mmlu-pro-evaluating-higher-order-reasoning","title":"MMLU-Pro+: Evaluating Higher-Order Reasoning and Shortcut Learning in LLMs","date":"2024-09-03","arxiv_id":"2409.02257","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mmlu-pro-evaluating-higher-order-reasoning#ran","syntology_url":"https://syntology.ai/paper/2409.02257","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.02257"}},"official":{"repos":["asgsaeid/mmlu-pro-plus"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/performance-law-of-large-language-models","slug":"performance-law-of-large-language-models","title":"Performance Law of Large Language Models","date":"2024-08-19","arxiv_id":"2408.09895","repositories_listed":1,"syntology":null},{"url":"/paper/arablegaleval-a-multitask-benchmark-for","slug":"arablegaleval-a-multitask-benchmark-for","title":"ArabLegalEval: A Multitask Benchmark for Assessing Arabic Legal Knowledge in Large Language Models","date":"2024-08-15","arxiv_id":"2408.07983","repositories_listed":1,"syntology":null},{"url":"/paper/2408-00727","slug":"2408-00727","title":"Improving Retrieval-Augmented Generation in Medicine with Iterative Follow-up Questions","date":"2024-08-01","arxiv_id":"2408.00727","repositories_listed":1,"syntology":null},{"url":"/paper/a-deeper-look-at-depth-pruning-of-llms","slug":"a-deeper-look-at-depth-pruning-of-llms","title":"A deeper look at depth pruning of LLMs","date":"2024-07-23","arxiv_id":"2407.16286","repositories_listed":1,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":3,"n_instrument":9,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":12,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 9 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-deeper-look-at-depth-pruning-of-llms#ran","syntology_url":"https://syntology.ai/paper/2407.16286","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.16286"}},"official":{"repos":["shoaibahmed/llm_depth_pruning"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/compact-language-models-via-pruning-and","slug":"compact-language-models-via-pruning-and","title":"Compact Language Models via Pruning and Knowledge Distillation","date":"2024-07-19","arxiv_id":"2407.14679","repositories_listed":1,"syntology":null}],"syntology_records":43,"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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"papers_where_code_ran":78,"papers_where_code_ran_first_page":"/task/mmlu/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":4,"url":"/task/mmlu/papers/2","json":"/task/mmlu/papers/2.json","rows":100},{"order":"archive","page":3,"of":4,"url":"/task/mmlu/papers/3","json":"/task/mmlu/papers/3.json","rows":100},{"order":"archive","page":4,"of":4,"url":"/task/mmlu/papers/4","json":"/task/mmlu/papers/4.json","rows":40},{"order":"ran","page":1,"of":1,"url":"/task/mmlu/papers/ran/1","json":"/task/mmlu/papers/ran/1.json","rows":78}],"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":"c942ed9884a02a7bd74d92973e581701348a8da7c7e00154e866dfa5c3d7888b","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}