{"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/load-problems","entry":"load_problems","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":8,"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":6,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":8,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":1,"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":"2607.14552","paper":"/paper/arxiv-2607-14552","title":"Answer-Conditioned Chains of Thought Degrade Verifiable-Reasoning Distillation in Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"js-lee-AI/answer-leakage","path":"answer_leakage/generation.py","file_url":"https://github.com/js-lee-AI/answer-leakage/blob/HEAD/answer_leakage/generation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2eca8abfaa2881d1","mcp_get_code":{"code_sha256":"2eca8abfaa2881d1"}},{"arxiv_id":"2605.23940","paper":"/paper/arxiv-2605-23940","title":"Published at ICLR 2026 Workshop on Reasoning and Planning for LLMs RESIDUAL DRIFT DOMINATES CONTRADICTION IN MULTI-TURN CONSTRAINT REASONING","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"kaons-research/drift-bench","path":"src/run_experiment.py","file_url":"https://github.com/kaons-research/drift-bench/blob/HEAD/src/run_experiment.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4737d24ad6135c21","mcp_get_code":{"code_sha256":"4737d24ad6135c21"}},{"arxiv_id":"2508.06361","paper":"/paper/arxiv-2508-06361","title":"Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"Xtra-Computing/LLM-Deception","path":"src/llm/local_inference.py","file_url":"https://github.com/Xtra-Computing/LLM-Deception/blob/HEAD/src/llm/local_inference.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":"ba47bd9499eeb0c2","mcp_get_code":{"code_sha256":"ba47bd9499eeb0c2"}},{"arxiv_id":"2502.09723","paper":"/paper/making-them-a-malicious-database-exploiting","title":"QueryAttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query Language","date":"2025-02-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"horizonsinzqs/queryattack","path":"evaluate_responses.py","file_url":"https://github.com/horizonsinzqs/queryattack/blob/HEAD/evaluate_responses.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ff749b86c2c8aa8","mcp_get_code":{"code_sha256":"3ff749b86c2c8aa8"}},{"arxiv_id":"2412.08972","paper":"/paper/rulearena-a-benchmark-for-rule-guided","title":"RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World Scenarios","date":"2024-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"skyriver-2000/rulearena","path":"airline/micro_evaluation.py","file_url":"https://github.com/skyriver-2000/rulearena/blob/HEAD/airline/micro_evaluation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"18fc43eb30bd48af","mcp_get_code":{"code_sha256":"18fc43eb30bd48af"}},{"arxiv_id":"1809.04682","paper":"/paper/automatic-program-synthesis-of-long-programs","title":"Automatic Program Synthesis of Long Programs with a Learned Garbage Collector","date":"2018-09-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"e629f07b6ec5ad50","mcp_get_code":{"code_sha256":"e629f07b6ec5ad50"}},{"arxiv_id":"1703.07469","paper":"/paper/robustfill-neural-program-learning-under","title":"RobustFill: Neural Program Learning under Noisy I/O","date":"2017-03-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amitz25/PCCoder","path":"scripts/solve_problems.py","file_url":"https://github.com/amitz25/PCCoder/blob/HEAD/scripts/solve_problems.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e629f07b6ec5ad50","mcp_get_code":{"code_sha256":"e629f07b6ec5ad50"}},{"arxiv_id":"2025.findings-acl.298","paper":null,"title":"arXiv:2025.findings-acl.298","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"horizonsinzqs/QueryAttack","path":"evaluate_responses.py","file_url":"https://github.com/horizonsinzqs/QueryAttack/blob/HEAD/evaluate_responses.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ff749b86c2c8aa8","mcp_get_code":{"code_sha256":"3ff749b86c2c8aa8"}}]}