{"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/call-openai","entry":"call_openai","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":6,"n_papers_ran":3,"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":6,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":3,"unverified":3},"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":"2606.09865","paper":"/paper/arxiv-2606-09865","title":"LLM-as-a-Discriminator: When Synthetic Tables Still Look Real","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"SlokomManel/LLM-as-a-Discriminator","path":"code/evaluate.py","file_url":"https://github.com/SlokomManel/LLM-as-a-Discriminator/blob/HEAD/code/evaluate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"25d0149b1ef798f7","mcp_get_code":{"code_sha256":"25d0149b1ef798f7"}},{"arxiv_id":"2603.00634","paper":"/paper/arxiv-2603-00634","title":"BLUFF: Benchmarking the Detection of False and Synthetic Content across 58 Low-Resource Languages","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"jsl5710/BLUFF","path":"src/evaluation/decoder/inference.py","file_url":"https://github.com/jsl5710/BLUFF/blob/HEAD/src/evaluation/decoder/inference.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"00c79f83c5cd0e11","mcp_get_code":{"code_sha256":"00c79f83c5cd0e11"}},{"arxiv_id":"2404.13925","paper":"/paper/mario-eval-evaluate-your-math-llm-with-your","title":"MARIO Eval: Evaluate Your Math LLM with your Math LLM--A mathematical dataset evaluation toolkit","date":"2024-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mario-math-reasoning/math_evaluation","path":"math_evaluation/llms/llm_models.py","file_url":"https://github.com/mario-math-reasoning/math_evaluation/blob/HEAD/math_evaluation/llms/llm_models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1b7529dcbd572ad3","mcp_get_code":{"code_sha256":"1b7529dcbd572ad3"}},{"arxiv_id":"2404.12274","paper":"/paper/advancing-the-robustness-of-large-language","title":"Advancing the Robustness of Large Language Models through Self-Denoised Smoothing","date":"2024-04-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ucsb-nlp-chang/selfdenoise","path":"jailbreakcode/lib/language_models.py","file_url":"https://github.com/ucsb-nlp-chang/selfdenoise/blob/HEAD/jailbreakcode/lib/language_models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e0ff677292cbbb70","mcp_get_code":{"code_sha256":"e0ff677292cbbb70"}},{"arxiv_id":"2402.14008","paper":"/paper/olympiadbench-a-challenging-benchmark-for","title":"OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems","date":"2024-02-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OpenBMB/OlympiadBench","path":"inference/code/evaluators/text_only_gpt_4.py","file_url":"https://github.com/OpenBMB/OlympiadBench/blob/HEAD/inference/code/evaluators/text_only_gpt_4.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"04240f6bffe2447e","mcp_get_code":{"code_sha256":"04240f6bffe2447e"}},{"arxiv_id":"2312.17673","paper":"/paper/jatmo-prompt-injection-defense-by-task","title":"Jatmo: Prompt Injection Defense by Task-Specific Finetuning","date":"2023-12-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wagner-group/prompt-injection-defense","path":"src/jatmo/server.py","file_url":"https://github.com/wagner-group/prompt-injection-defense/blob/HEAD/src/jatmo/server.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"58f375594c3a65c3","mcp_get_code":{"code_sha256":"58f375594c3a65c3"}}]}