{"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/get-judge-system-prompt","entry":"get_judge_system_prompt","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":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":3,"n_samples_fingerprinted":3,"n_places":6,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":2,"unverified":1},"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":"2411.11407","paper":"/paper/the-dark-side-of-trust-authority-citation","title":"The Dark Side of Trust: Authority Citation-Driven Jailbreak Attacks on Large Language Models","date":"2024-11-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YancyKahn/DarkCite","path":"system_template.py","file_url":"https://github.com/YancyKahn/DarkCite/blob/HEAD/system_template.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2c6687ef6bc99678","mcp_get_code":{"code_sha256":"2c6687ef6bc99678"}},{"arxiv_id":"2409.14866","paper":"/paper/effective-and-evasive-fuzz-testing-driven","title":"PAPILLON: Efficient and Stealthy Fuzz Testing-Powered Jailbreaks for LLMs","date":"2024-09-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aaFrostnova/Papillon","path":"Judge/judges.py","file_url":"https://github.com/aaFrostnova/Papillon/blob/HEAD/Judge/judges.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"60e7444ebd37a613","mcp_get_code":{"code_sha256":"60e7444ebd37a613"}},{"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/judges.py","file_url":"https://github.com/ucsb-nlp-chang/selfdenoise/blob/HEAD/jailbreakcode/lib/judges.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1eb92df4126524c3","mcp_get_code":{"code_sha256":"1eb92df4126524c3"}},{"arxiv_id":"2404.02151","paper":"/paper/jailbreaking-leading-safety-aligned-llms-with","title":"Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks","date":"2024-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tml-epfl/llm-adaptive-attacks","path":"prompts.py","file_url":"https://github.com/tml-epfl/llm-adaptive-attacks/blob/HEAD/prompts.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"60e7444ebd37a613","mcp_get_code":{"code_sha256":"60e7444ebd37a613"}},{"arxiv_id":"2403.00867","paper":"/paper/gradient-cuff-detecting-jailbreak-attacks-on","title":"Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes","date":"2024-03-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"patrickrchao/JailbreakingLLMs","path":"judges.py","file_url":"https://github.com/patrickrchao/JailbreakingLLMs/blob/HEAD/judges.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"60e7444ebd37a613","mcp_get_code":{"code_sha256":"60e7444ebd37a613"}},{"arxiv_id":"2402.16459","paper":"/paper/defending-llms-against-jailbreaking-attacks","title":"Defending LLMs against Jailbreaking Attacks via Backtranslation","date":"2024-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yihanwang617/llm-jailbreaking-defense-backtranslation","path":"PAIR/system_prompts.py","file_url":"https://github.com/yihanwang617/llm-jailbreaking-defense-backtranslation/blob/HEAD/PAIR/system_prompts.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"581e46fff7eed12a","mcp_get_code":{"code_sha256":"581e46fff7eed12a"}}]}