{"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/long-context-understanding/papers/ran/1","list_of":"/task/long-context-understanding","task":"Long-Context Understanding","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":1,"pages_in_order":1,"rows_per_page":100,"rows":[1,28],"of":28,"counts":{"archive_papers_tagged":81,"with_a_code_link":54,"where_syntology_ran_a_sample":28,"not_listed_spam_title":0,"listed":81,"listed_where_code_ran":28,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":21,"every_run_a_failure_of_syntologys_instrument":7,"listed_with_a_run_with_no_instrument_failure":21,"listed_every_run_a_failure_of_syntologys_instrument":7,"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"},"first_page":"/task/long-context-understanding/papers/ran/1","prev":null,"next":null,"papers":[{"url":"/paper/can-compressed-llms-truly-act-an-empirical","slug":"can-compressed-llms-truly-act-an-empirical","title":"Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression","date":"2025-05-26","arxiv_id":"2505.19433","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/can-compressed-llms-truly-act-an-empirical#ran","syntology_url":"https://syntology.ai/paper/2505.19433","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19433"}},"official":{"repos":["pprp/acbench"],"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","unlocated"]}}},{"url":"/paper/longprolip-a-probabilistic-vision-language","slug":"longprolip-a-probabilistic-vision-language","title":"LongProLIP: A Probabilistic Vision-Language Model with Long Context Text","date":"2025-03-11","arxiv_id":"2503.08048","repositories_listed":1,"syntology":{"n":16,"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":16,"phrase":"7 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; 6 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/longprolip-a-probabilistic-vision-language#ran","syntology_url":"https://syntology.ai/paper/2503.08048","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.08048"}},"official":{"repos":["naver-ai/prolip"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":9,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/fino1-on-the-transferability-of-reasoning","slug":"fino1-on-the-transferability-of-reasoning","title":"Fino1: On the Transferability of Reasoning Enhanced LLMs to Finance","date":"2025-02-12","arxiv_id":"2502.08127","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fino1-on-the-transferability-of-reasoning#ran","syntology_url":"https://syntology.ai/paper/2502.08127","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.08127"}},"official":{"repos":["the-finai/fino1"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/m-extending-memoryllm-with-scalable-long-term","slug":"m-extending-memoryllm-with-scalable-long-term","title":"M+: Extending MemoryLLM with Scalable Long-Term Memory","date":"2025-02-01","arxiv_id":"2502.00592","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":2,"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/m-extending-memoryllm-with-scalable-long-term#ran","syntology_url":"https://syntology.ai/paper/2502.00592","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.00592"}},"official":{"repos":["wangyu-ustc/memoryllm"],"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/rulearena-a-benchmark-for-rule-guided","slug":"rulearena-a-benchmark-for-rule-guided","title":"RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World Scenarios","date":"2024-12-12","arxiv_id":"2412.08972","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/rulearena-a-benchmark-for-rule-guided#ran","syntology_url":"https://syntology.ai/paper/2412.08972","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.08972"}},"official":{"repos":["skyriver-2000/rulearena"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/gated-delta-networks-improving-mamba2-with","slug":"gated-delta-networks-improving-mamba2-with","title":"Gated Delta Networks: Improving Mamba2 with Delta Rule","date":"2024-12-09","arxiv_id":"2412.06464","repositories_listed":4,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":7,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/gated-delta-networks-improving-mamba2-with#ran","syntology_url":"https://syntology.ai/paper/2412.06464","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.06464"}},"official":{"repos":["NVlabs/GatedDeltaNet"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/what-is-wrong-with-perplexity-for-long","slug":"what-is-wrong-with-perplexity-for-long","title":"What is Wrong with Perplexity for Long-context Language Modeling?","date":"2024-10-31","arxiv_id":"2410.23771","repositories_listed":1,"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/what-is-wrong-with-perplexity-for-long#ran","syntology_url":"https://syntology.ai/paper/2410.23771","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23771"}},"official":{"repos":["pku-ml/longppl"],"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/hellobench-evaluating-long-text-generation","slug":"hellobench-evaluating-long-text-generation","title":"HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models","date":"2024-09-24","arxiv_id":"2409.16191","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hellobench-evaluating-long-text-generation#ran","syntology_url":"https://syntology.ai/paper/2409.16191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.16191"}},"official":{"repos":["quehry/hellobench"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mixture-of-in-context-experts-enhance-llms","slug":"mixture-of-in-context-experts-enhance-llms","title":"Mixture of In-Context Experts Enhance LLMs' Long Context Awareness","date":"2024-06-28","arxiv_id":"2406.19598","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"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) · 1 unverified","sample_list":"/paper/mixture-of-in-context-experts-enhance-llms#ran","syntology_url":"https://syntology.ai/paper/2406.19598","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.19598"}},"official":{"repos":["p1nksnow/moice"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/leave-no-document-behind-benchmarking-long","slug":"leave-no-document-behind-benchmarking-long","title":"Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA","date":"2024-06-25","arxiv_id":"2406.17419","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/leave-no-document-behind-benchmarking-long#ran","syntology_url":"https://syntology.ai/paper/2406.17419","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17419"}},"official":{"repos":["mozerwang/loong"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/moa-mixture-of-sparse-attention-for-automatic","slug":"moa-mixture-of-sparse-attention-for-automatic","title":"MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression","date":"2024-06-21","arxiv_id":"2406.14909","repositories_listed":1,"syntology":{"n":22,"n_ran":19,"n_constructed":0,"n_ran_checked":19,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":19,"n_pointer_only":0,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/moa-mixture-of-sparse-attention-for-automatic#ran","syntology_url":"https://syntology.ai/paper/2406.14909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14909"}},"official":{"repos":["thu-nics/moa"],"state":"official (archive's flag): 19 ran","n_ran":19,"n_constructed":0,"n_ran_no_instrument_failure":19,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/multimodal-needle-in-a-haystack-benchmarking","slug":"multimodal-needle-in-a-haystack-benchmarking","title":"Multimodal Needle in a Haystack: Benchmarking Long-Context Capability of Multimodal Large Language Models","date":"2024-06-17","arxiv_id":"2406.11230","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/multimodal-needle-in-a-haystack-benchmarking#ran","syntology_url":"https://syntology.ai/paper/2406.11230","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11230"}},"official":{"repos":["wang-ml-lab/multimodal-needle-in-a-haystack"],"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/recurrent-context-compression-efficiently","slug":"recurrent-context-compression-efficiently","title":"Recurrent Context Compression: Efficiently Expanding the Context Window of LLM","date":"2024-06-10","arxiv_id":"2406.06110","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/recurrent-context-compression-efficiently#ran","syntology_url":"https://syntology.ai/paper/2406.06110","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06110"}},"official":{"repos":["WUHU-G/RCC_Transformer"],"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/analyzing-temporal-complex-events-with-large","slug":"analyzing-temporal-complex-events-with-large","title":"Analyzing Temporal Complex Events with Large Language Models? A Benchmark towards Temporal, Long Context Understanding","date":"2024-06-04","arxiv_id":"2406.02472","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/analyzing-temporal-complex-events-with-large#ran","syntology_url":"https://syntology.ai/paper/2406.02472","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.02472"}},"official":{"repos":["Zhihan72/TCELongBench"],"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/retrieval-head-mechanistically-explains-long","slug":"retrieval-head-mechanistically-explains-long","title":"Retrieval Head Mechanistically Explains Long-Context Factuality","date":"2024-04-24","arxiv_id":"2404.15574","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":7,"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) · 0 unverified","sample_list":"/paper/retrieval-head-mechanistically-explains-long#ran","syntology_url":"https://syntology.ai/paper/2404.15574","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.15574"}},"official":{"repos":["nightdessert/retrieval_head"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hierarchical-context-merging-better-long","slug":"hierarchical-context-merging-better-long","title":"Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs","date":"2024-04-16","arxiv_id":"2404.10308","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":1,"n_ran_checked":7,"n_instrument":5,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":15,"phrase":"12 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/hierarchical-context-merging-better-long#ran","syntology_url":"https://syntology.ai/paper/2404.10308","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.10308"}},"official":{"repos":["alinlab/homer"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":1,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/ada-leval-evaluating-long-context-llms-with","slug":"ada-leval-evaluating-long-context-llms-with","title":"Ada-LEval: Evaluating long-context LLMs with length-adaptable benchmarks","date":"2024-04-09","arxiv_id":"2404.06480","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"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) · 0 unverified","sample_list":"/paper/ada-leval-evaluating-long-context-llms-with#ran","syntology_url":"https://syntology.ai/paper/2404.06480","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.06480"}},"official":{"repos":["open-compass/ada-leval"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/ruler-what-s-the-real-context-size-of-your","slug":"ruler-what-s-the-real-context-size-of-your","title":"RULER: What's the Real Context Size of Your Long-Context Language Models?","date":"2024-04-09","arxiv_id":"2404.06654","repositories_listed":6,"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":0,"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/ruler-what-s-the-real-context-size-of-your#ran","syntology_url":"https://syntology.ai/paper/2404.06654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.06654"}},"official":{"repos":["hsiehjackson/ruler"],"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/long-context-llms-struggle-with-long-in","slug":"long-context-llms-struggle-with-long-in","title":"Long-context LLMs Struggle with Long In-context Learning","date":"2024-04-02","arxiv_id":"2404.02060","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/long-context-llms-struggle-with-long-in#ran","syntology_url":"https://syntology.ai/paper/2404.02060","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.02060"}},"official":{"repos":["tiger-ai-lab/longiclbench"],"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":["official"]}}},{"url":"/paper/fables-evaluating-faithfulness-and-content","slug":"fables-evaluating-faithfulness-and-content","title":"FABLES: Evaluating faithfulness and content selection in book-length summarization","date":"2024-04-01","arxiv_id":"2404.01261","repositories_listed":3,"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/fables-evaluating-faithfulness-and-content#ran","syntology_url":"https://syntology.ai/paper/2404.01261","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01261"}},"official":{"repos":["mungg/fables"],"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/internlm2-technical-report","slug":"internlm2-technical-report","title":"InternLM2 Technical Report","date":"2024-03-26","arxiv_id":"2403.17297","repositories_listed":3,"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/internlm2-technical-report#ran","syntology_url":"https://syntology.ai/paper/2403.17297","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17297"}},"official":null}},{"url":"/paper/loogle-can-long-context-language-models","slug":"loogle-can-long-context-language-models","title":"LooGLE: Can Long-Context Language Models Understand Long Contexts?","date":"2023-11-08","arxiv_id":"2311.04939","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":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) · 1 unverified","sample_list":"/paper/loogle-can-long-context-language-models#ran","syntology_url":"https://syntology.ai/paper/2311.04939","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.04939"}},"official":{"repos":["bigai-nlco/loogle"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mplug-owl2-revolutionizing-multi-modal-large","slug":"mplug-owl2-revolutionizing-multi-modal-large","title":"mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration","date":"2023-11-07","arxiv_id":"2311.04257","repositories_listed":2,"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/mplug-owl2-revolutionizing-multi-modal-large#ran","syntology_url":"https://syntology.ai/paper/2311.04257","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.04257"}},"official":{"repos":["x-plug/mplug-owl"],"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/s3eval-a-synthetic-scalable-systematic","slug":"s3eval-a-synthetic-scalable-systematic","title":"S3Eval: A Synthetic, Scalable, Systematic Evaluation Suite for Large Language Models","date":"2023-10-23","arxiv_id":"2310.15147","repositories_listed":2,"syntology":{"n":26,"n_ran":21,"n_constructed":0,"n_ran_checked":21,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":21,"n_pointer_only":26,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 0 violated, 21 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/s3eval-a-synthetic-scalable-systematic#ran","syntology_url":"https://syntology.ai/paper/2310.15147","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.15147"}},"official":{"repos":["lfy79001/s3eval","lfy79001/sqleval"],"state":"official (archive's flag): 21 ran","n_ran":21,"n_constructed":0,"n_ran_no_instrument_failure":21,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/longbench-a-bilingual-multitask-benchmark-for","slug":"longbench-a-bilingual-multitask-benchmark-for","title":"LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding","date":"2023-08-28","arxiv_id":"2308.14508","repositories_listed":3,"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/longbench-a-bilingual-multitask-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2308.14508","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.14508"}},"official":{"repos":["thudm/longbench"],"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/judging-llm-as-a-judge-with-mt-bench-and-1","slug":"judging-llm-as-a-judge-with-mt-bench-and-1","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","date":"2023-06-09","arxiv_id":"2306.05685","repositories_listed":11,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/judging-llm-as-a-judge-with-mt-bench-and-1#ran","syntology_url":"https://syntology.ai/paper/2306.05685","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.05685"}},"official":{"repos":["lm-sys/fastchat"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/gpt-4-technical-report-1","slug":"gpt-4-technical-report-1","title":"GPT-4 Technical Report","date":"2023-03-15","arxiv_id":"2303.08774","repositories_listed":11,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gpt-4-technical-report-1#ran","syntology_url":"https://syntology.ai/paper/2303.08774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08774"}},"official":{"repos":["openai/evals"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/glm-130b-an-open-bilingual-pre-trained-model","slug":"glm-130b-an-open-bilingual-pre-trained-model","title":"GLM-130B: An Open Bilingual Pre-trained Model","date":"2022-10-05","arxiv_id":"2210.02414","repositories_listed":9,"syntology":{"n":21,"n_ran":15,"n_constructed":0,"n_ran_checked":14,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":0,"phrase":"15 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; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/glm-130b-an-open-bilingual-pre-trained-model#ran","syntology_url":"https://syntology.ai/paper/2210.02414","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.02414"}},"official":{"repos":["thudm/glm-130b"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["listed","official"]}}}],"record_sha256":"3407fc4802a914a7097cf4172464cec1424631c419ac22229eb02491e7689eec","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}