{"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/extract-text","entry":"extract_text","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":13,"n_papers_ran":8,"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":9,"n_samples_ran":5,"n_samples_fingerprinted":3,"n_places":13,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":4,"unverified":4},"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":"2606.22723","paper":"/paper/arxiv-2606-22723","title":"BLUEX v2: Benchmarking LLMs on Open-Ended Questions from Brazilian University Entrance Exams","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"TropicAI-Research/BLUEXv2","path":"dataset_pipeline/generate_marking_criteria.py","file_url":"https://github.com/TropicAI-Research/BLUEXv2/blob/HEAD/dataset_pipeline/generate_marking_criteria.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a5398264426e8832","mcp_get_code":{"code_sha256":"a5398264426e8832"}},{"arxiv_id":"2502.05567","paper":"/paper/2502-05567","title":"ATLAS: Autoformalizing Theorems through Lifting, Augmentation, and Synthesis of Data","date":"2025-02-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"XiaoyangLiu-sjtu/ATLAS","path":"utils.py","file_url":"https://github.com/XiaoyangLiu-sjtu/ATLAS/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"37cd345308b8adeb","mcp_get_code":{"code_sha256":"37cd345308b8adeb"}},{"arxiv_id":"2501.00912","paper":"/paper/autopresent-designing-structured-visuals-from","title":"AutoPresent: Designing Structured Visuals from Scratch","date":"2025-01-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"para-lost/AutoPresent","path":"evaluate/page_eval.py","file_url":"https://github.com/para-lost/AutoPresent/blob/HEAD/evaluate/page_eval.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9f5942c100b1ce65","mcp_get_code":{"code_sha256":"9f5942c100b1ce65"}},{"arxiv_id":"2405.20947","paper":"/paper/or-bench-an-over-refusal-benchmark-for-large","title":"OR-Bench: An Over-Refusal Benchmark for Large Language Models","date":"2024-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"justincui03/or-bench","path":"moderator/moderate_only.py","file_url":"https://github.com/justincui03/or-bench/blob/HEAD/moderator/moderate_only.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"bba6440d88b226a5","mcp_get_code":{"code_sha256":"bba6440d88b226a5"}},{"arxiv_id":"2405.11804","paper":"/paper/perhaps-beyond-human-translation-harnessing","title":"(Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Texts","date":"2024-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"andrewyng/translation-agent","path":"app/process.py","file_url":"https://github.com/andrewyng/translation-agent/blob/HEAD/app/process.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"69201dfb54d74f36","mcp_get_code":{"code_sha256":"69201dfb54d74f36"}},{"arxiv_id":"2403.04706","paper":"/paper/common-7b-language-models-already-possess","title":"Common 7B Language Models Already Possess Strong Math Capabilities","date":"2024-03-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xwin-lm/xwin-lm","path":"Xwin-Coder/HumanEval/humaneval_gen.py","file_url":"https://github.com/xwin-lm/xwin-lm/blob/HEAD/Xwin-Coder/HumanEval/humaneval_gen.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7a733b18081436f3","mcp_get_code":{"code_sha256":"7a733b18081436f3"}},{"arxiv_id":"2402.11683","paper":"/paper/one-prompt-to-rule-them-all-llms-for-opinion","title":"One Prompt To Rule Them All: LLMs for Opinion Summary Evaluation","date":"2024-02-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tjsiledar/SummEval-OP","path":"code/efficient-evaluator-v2.py","file_url":"https://github.com/tjsiledar/SummEval-OP/blob/HEAD/code/efficient-evaluator-v2.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f55db2ffc45ecfd2","mcp_get_code":{"code_sha256":"f55db2ffc45ecfd2"}},{"arxiv_id":"2401.00690","paper":"/paper/benchmarking-large-language-models-on","title":"Benchmarking Large Language Models on Controllable Generation under Diversified Instructions","date":"2024-01-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Xt-cyh/CoDI-Eval","path":"utils/eval_utils.py","file_url":"https://github.com/Xt-cyh/CoDI-Eval/blob/HEAD/utils/eval_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e551f21cb1015ac1","mcp_get_code":{"code_sha256":"e551f21cb1015ac1"}},{"arxiv_id":"2308.09583","paper":"/paper/wizardmath-empowering-mathematical-reasoning","title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","date":"2023-08-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nlpxucan/WizardLM","path":"WizardCoder/src/mbpp_gen.py","file_url":"https://github.com/nlpxucan/WizardLM/blob/HEAD/WizardCoder/src/mbpp_gen.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7a733b18081436f3","mcp_get_code":{"code_sha256":"7a733b18081436f3"}},{"arxiv_id":"2306.08568","paper":"/paper/wizardcoder-empowering-code-large-language","title":"WizardCoder: Empowering Code Large Language Models with Evol-Instruct","date":"2023-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nickrosh/evol-teacher","path":"humaneval_gen.py","file_url":"https://github.com/nickrosh/evol-teacher/blob/HEAD/humaneval_gen.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7a733b18081436f3","mcp_get_code":{"code_sha256":"7a733b18081436f3"}},{"arxiv_id":"2305.07922","paper":"/paper/codet5-open-code-large-language-models-for","title":"CodeT5+: Open Code Large Language Models for Code Understanding and Generation","date":"2023-05-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforce/codet5","path":"CodeT5+/humaneval/generate_codet5p.py","file_url":"https://github.com/salesforce/codet5/blob/HEAD/CodeT5%2B/humaneval/generate_codet5p.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"7a733b18081436f3","mcp_get_code":{"code_sha256":"7a733b18081436f3"}},{"arxiv_id":"2305.04533","paper":"/paper/prompted-llms-as-chatbot-modules-for-long","title":"Prompted LLMs as Chatbot Modules for Long Open-domain Conversation","date":"2023-05-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"krafton-ai/mpc","path":"gpt3chat/utils.py","file_url":"https://github.com/krafton-ai/mpc/blob/HEAD/gpt3chat/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7ade5211ce52a4dd","mcp_get_code":{"code_sha256":"7ade5211ce52a4dd"}},{"arxiv_id":"2023.findings-acl.277","paper":null,"title":"arXiv:2023.findings-acl.277","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"krafton-ai/MPC","path":"gpt3chat/utils.py","file_url":"https://github.com/krafton-ai/MPC/blob/HEAD/gpt3chat/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7ade5211ce52a4dd","mcp_get_code":{"code_sha256":"7ade5211ce52a4dd"}}]}