{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/code/gpt-context-window","entry":"GPT_context_window","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":5,"n_papers_ran":5,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":4,"n_samples_ran":4,"n_samples_fingerprinted":4,"n_places":5,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":4,"unverified":0},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2406.07791","paper":"/paper/judging-the-judges-a-systematic-investigation","title":"Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge","date":"2024-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Slimshilin/Position-Bias-Analyzer-Demo","path":"subeval/chat_api/gpt.py","file_url":"https://github.com/Slimshilin/Position-Bias-Analyzer-Demo/blob/HEAD/subeval/chat_api/gpt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"acd86dcb3b21fb02","mcp_get_code":{"code_sha256":"acd86dcb3b21fb02"}},{"arxiv_id":"2404.06480","paper":"/paper/ada-leval-evaluating-long-context-llms-with","title":"Ada-LEval: Evaluating long-context LLMs with length-adaptable benchmarks","date":"2024-04-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"open-compass/ada-leval","path":"ada_leval/api.py","file_url":"https://github.com/open-compass/ada-leval/blob/HEAD/ada_leval/api.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a868f0afe2141be4","mcp_get_code":{"code_sha256":"a868f0afe2141be4"}},{"arxiv_id":"2403.20330","paper":"/paper/are-we-on-the-right-way-for-evaluating-large","title":"Are We on the Right Way for Evaluating Large Vision-Language Models?","date":"2024-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MMStar-Benchmark/MMStar","path":"eval/vlmeval/api/gpt.py","file_url":"https://github.com/MMStar-Benchmark/MMStar/blob/HEAD/eval/vlmeval/api/gpt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f3eb697fcb8df296","mcp_get_code":{"code_sha256":"f3eb697fcb8df296"}},{"arxiv_id":"2403.04732","paper":"/paper/how-far-are-we-from-intelligent-visual","title":"How Far Are We from Intelligent Visual Deductive Reasoning?","date":"2024-03-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"apple/ml-rpm-bench","path":"src/models.py","file_url":"https://github.com/apple/ml-rpm-bench/blob/HEAD/src/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f3eb697fcb8df296","mcp_get_code":{"code_sha256":"f3eb697fcb8df296"}},{"arxiv_id":"2311.17647","paper":"/paper/vim-probing-multimodal-large-language-models","title":"Text as Images: Can Multimodal Large Language Models Follow Printed Instructions in Pixels?","date":"2023-11-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vim-bench/vim_tool","path":"vlmeval/api/gpt.py","file_url":"https://github.com/vim-bench/vim_tool/blob/HEAD/vlmeval/api/gpt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bdd0978c6450ead8","mcp_get_code":{"code_sha256":"bdd0978c6450ead8"}}]}