{"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-ground-truth","entry":"load_ground_truth","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":10,"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":7,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":10,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":1,"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":"2609.13945","paper":"/paper/arxiv-2609-13945","title":"SAILOR: Solver-Assisted Interactive LLM-based Optimization Recovery","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"sshaghayeghs/SAILOR","path":"ast_solver/pipeline.py","file_url":"https://github.com/sshaghayeghs/SAILOR/blob/HEAD/ast_solver/pipeline.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cf4530ca628192cf","mcp_get_code":{"code_sha256":"cf4530ca628192cf"}},{"arxiv_id":"2607.02510","paper":"/paper/arxiv-2607-02510","title":"Online Safety Monitoring for LLMs","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"monasch/llm-monitor","path":"python_scripts/get_signal_prm.py","file_url":"https://github.com/monasch/llm-monitor/blob/HEAD/python_scripts/get_signal_prm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"35a984834e874c85","mcp_get_code":{"code_sha256":"35a984834e874c85"}},{"arxiv_id":"2603.21335","paper":"/paper/arxiv-2603-21335","title":"TimeTox: An LLM-Based Pipeline for Automated Extraction of Time Toxicity from Clinical Trial Protocols","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"sakethbuild/TimeTox","path":"agent_comparison.py","file_url":"https://github.com/sakethbuild/TimeTox/blob/HEAD/agent_comparison.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"acc5b9353a83890b","mcp_get_code":{"code_sha256":"acc5b9353a83890b"}},{"arxiv_id":"2601.06966","paper":"/paper/arxiv-2601-06966","title":"RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"AvatarMemory/RealMemBench","path":"eval/compute_llm_metrics_for_realmem.py","file_url":"https://github.com/AvatarMemory/RealMemBench/blob/HEAD/eval/compute_llm_metrics_for_realmem.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":"e78cd2d9a3dd4718","mcp_get_code":{"code_sha256":"e78cd2d9a3dd4718"}},{"arxiv_id":"2506.14035","paper":"/paper/simpledoc-multi-modal-document-understanding","title":"SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative Refinement","date":"2025-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ag2ai/SimpleDoc","path":"evaluation/evaluate_responses.py","file_url":"https://github.com/ag2ai/SimpleDoc/blob/HEAD/evaluation/evaluate_responses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a60837f27b20ddec","mcp_get_code":{"code_sha256":"a60837f27b20ddec"}},{"arxiv_id":"2305.14846","paper":"/paper/introducing-competition-to-boost-the-1","title":"Introducing Competition to Boost the Transferability of Targeted Adversarial Examples through Clean Feature Mixup","date":"2023-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dreamflake/cfm","path":"eval_attacks.py","file_url":"https://github.com/dreamflake/cfm/blob/HEAD/eval_attacks.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":"9e4f4d7edbf00ba0","mcp_get_code":{"code_sha256":"9e4f4d7edbf00ba0"}},{"arxiv_id":"2210.05968","paper":"/paper/boosting-the-transferability-of-adversarial-2","title":"Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation","date":"2022-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sclbd/transfer_attack_rap","path":"rap_attack.py","file_url":"https://github.com/sclbd/transfer_attack_rap/blob/HEAD/rap_attack.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9e4f4d7edbf00ba0","mcp_get_code":{"code_sha256":"9e4f4d7edbf00ba0"}},{"arxiv_id":"2103.14641","paper":"/paper/on-generating-transferable-targeted","title":"On Generating Transferable Targeted Perturbations","date":"2021-03-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZhengyuZhao/Targeted-Tansfer","path":"eval_ensemble.py","file_url":"https://github.com/ZhengyuZhao/Targeted-Tansfer/blob/HEAD/eval_ensemble.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":"9e4f4d7edbf00ba0","mcp_get_code":{"code_sha256":"9e4f4d7edbf00ba0"}},{"arxiv_id":"2012.11207","paper":"/paper/on-success-and-simplicity-a-second-look-at","title":"On Success and Simplicity: A Second Look at Transferable Targeted Attacks","date":"2020-12-21","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":"9e4f4d7edbf00ba0","mcp_get_code":{"code_sha256":"9e4f4d7edbf00ba0"}},{"arxiv_id":"aaai_25576","paper":null,"title":"arXiv:aaai_25576","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"LHRLAB/NQE","path":"src/new_evaluation/iter_qe_evaluation.py","file_url":"https://github.com/LHRLAB/NQE/blob/HEAD/src/new_evaluation/iter_qe_evaluation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d9f1fd0bfa8bd9f3","mcp_get_code":{"code_sha256":"d9f1fd0bfa8bd9f3"}}]}