{"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-user-prompt","entry":"get_user_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":5,"n_papers_ran":2,"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":5,"n_samples_ran":2,"n_samples_fingerprinted":1,"n_places":5,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":2,"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":"2604.22215","paper":"/paper/arxiv-2604-22215","title":"Verbal Confidence Saturation in 3-9B Open-Weight Instruction-Tuned LLMs: A Pre-Registered Psychometric Validity Screen","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"synthiumjp/koriat","path":"inference_engine_koriat.py","file_url":"https://github.com/synthiumjp/koriat/blob/HEAD/inference_engine_koriat.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d0ab8a8a4013a4dc","mcp_get_code":{"code_sha256":"d0ab8a8a4013a4dc"}},{"arxiv_id":"2602.01539","paper":"/paper/arxiv-2602-01539","title":"MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM Safety","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"BattleWen/MAGIC","path":"eval/pattern/src/prompts_grained.py","file_url":"https://github.com/BattleWen/MAGIC/blob/HEAD/eval/pattern/src/prompts_grained.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":"a4f4c25dc1cecc8f","mcp_get_code":{"code_sha256":"a4f4c25dc1cecc8f"}},{"arxiv_id":"2601.22139","paper":"/paper/arxiv-2601-22139","title":"Reasoning While Asking: Transforming Reasoning Large Language Models from Passive Solvers to Proactive Inquirers","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"SUAT-AIRI/Proactive-Interactive-R1","path":"data_construction/utils.py","file_url":"https://github.com/SUAT-AIRI/Proactive-Interactive-R1/blob/HEAD/data_construction/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":"6275174328ddcda4","mcp_get_code":{"code_sha256":"6275174328ddcda4"}},{"arxiv_id":"2408.16629","paper":"/paper/llms-generate-structurally-realistic-social","title":"LLMs generate structurally realistic social networks but overestimate political homophily","date":"2024-08-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"snap-stanford/llm-social-network","path":"generate_networks.py","file_url":"https://github.com/snap-stanford/llm-social-network/blob/HEAD/generate_networks.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0d02210460fd59f5","mcp_get_code":{"code_sha256":"0d02210460fd59f5"}},{"arxiv_id":"2405.20304","paper":"/paper/group-robust-preference-optimization-in","title":"Group Robust Preference Optimization in Reward-free RLHF","date":"2024-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rsshyam/Group-robust-preference-optimization","path":"src/eval/win_rate.py","file_url":"https://github.com/rsshyam/Group-robust-preference-optimization/blob/HEAD/src/eval/win_rate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"6d492ffbac8f0b24","mcp_get_code":{"code_sha256":"6d492ffbac8f0b24"}}]}