{"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/create-client","entry":"create_client","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":1,"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":1,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":0,"unverified":5},"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":"2604.19459","paper":"/paper/arxiv-2604-19459","title":"Do LLMs Game Formalization? Evaluating Faithfulness in Logical Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"koreankiwi99/formalization-gaming","path":"src/utils/api_client.py","file_url":"https://github.com/koreankiwi99/formalization-gaming/blob/HEAD/src/utils/api_client.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"88e267ab5c120ee7","mcp_get_code":{"code_sha256":"88e267ab5c120ee7"}},{"arxiv_id":"2604.03261","paper":"/paper/arxiv-2604-03261","title":"Vigil: An Extensible System for Real-Time Detection and Mitigation of Cognitive Bias Triggers","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"aida-ugent/vigil","path":"backend/llm/client.py","file_url":"https://github.com/aida-ugent/vigil/blob/HEAD/backend/llm/client.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c31e8d58a25f394d","mcp_get_code":{"code_sha256":"c31e8d58a25f394d"}},{"arxiv_id":"2507.02554","paper":"/paper/ai-research-agents-for-machine-learning","title":"AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench","date":"2025-07-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/aira-dojo","path":"src/dojo/analysis_utils/meta_tree_analysis.py","file_url":"https://github.com/facebookresearch/aira-dojo/blob/HEAD/src/dojo/analysis_utils/meta_tree_analysis.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"c6c33db9d576569b","mcp_get_code":{"code_sha256":"c6c33db9d576569b"}},{"arxiv_id":"2506.14175","paper":"/paper/gram-a-generative-foundation-reward-model-for","title":"GRAM: A Generative Foundation Reward Model for Reward Generalization","date":"2025-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NiuTrans/GRAM","path":"extensions/GRAM-RR/call_vllm_with_multi_port.py","file_url":"https://github.com/NiuTrans/GRAM/blob/HEAD/extensions/GRAM-RR/call_vllm_with_multi_port.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":"9ec4e052e8733047","mcp_get_code":{"code_sha256":"9ec4e052e8733047"}},{"arxiv_id":"2201.03544","paper":"/paper/the-effects-of-reward-misspecification-1","title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models","date":"2022-01-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aypan17/reward-misspecification","path":"flow/utils/aimsun/api.py","file_url":"https://github.com/aypan17/reward-misspecification/blob/HEAD/flow/utils/aimsun/api.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"552d152dfb50144b","mcp_get_code":{"code_sha256":"552d152dfb50144b"}},{"arxiv_id":"2025.findings-emnlp.1348","paper":null,"title":"arXiv:2025.findings-emnlp.1348","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"anhaidgroup/columbo","path":"columbo/ask_llm.py","file_url":"https://github.com/anhaidgroup/columbo/blob/HEAD/columbo/ask_llm.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":"e8cb9792db2f792c","mcp_get_code":{"code_sha256":"e8cb9792db2f792c"}}]}