{"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/aggregate-results","entry":"aggregate_results","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":3,"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":3,"n_samples_fingerprinted":0,"n_places":8,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":3,"unverified":4},"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":"2608.11775","paper":"/paper/arxiv-2608-11775","title":"The Sleeping Agent: What Gist-Based Context Compression Loses and Why","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"kyrkewood/sleeping-agent","path":"src/scoring.py","file_url":"https://github.com/kyrkewood/sleeping-agent/blob/HEAD/src/scoring.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b59e234b597bb369","mcp_get_code":{"code_sha256":"b59e234b597bb369"}},{"arxiv_id":"2605.24164","paper":"/paper/arxiv-2605-24164","title":"CUNY at CLPsych 2026: A Pipeline Approach to Classification and Summarization of Mental Health Changes","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"amirzia/clpsych26-cuny","path":"clpsych/task1/aggregate_results.py","file_url":"https://github.com/amirzia/clpsych26-cuny/blob/HEAD/clpsych/task1/aggregate_results.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cf56af99be81271c","mcp_get_code":{"code_sha256":"cf56af99be81271c"}},{"arxiv_id":"2602.05746","paper":"/paper/arxiv-2602-05746","title":"Learning to Inject: Automated Prompt Injection via Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"RPC2/AutoInject","path":"agentdojo/src/agentdojo/benchmark.py","file_url":"https://github.com/RPC2/AutoInject/blob/HEAD/agentdojo/src/agentdojo/benchmark.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"56998e8fc03773a1","mcp_get_code":{"code_sha256":"56998e8fc03773a1"}},{"arxiv_id":"2507.22438","paper":null,"title":"arXiv:2507.22438","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"kmax2001/EvSharp2Blur","path":"lib/core/step2_trainer.py","file_url":"https://github.com/kmax2001/EvSharp2Blur/blob/HEAD/lib/core/step2_trainer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"48bfca3303a1c9e5","mcp_get_code":{"code_sha256":"48bfca3303a1c9e5"}},{"arxiv_id":"2505.17166","paper":"/paper/vidore-benchmark-v2-raising-the-bar-for","title":"ViDoRe Benchmark V2: Raising the Bar for Visual Retrieval","date":"2025-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"illuin-tech/vidore-benchmark","path":"src/vidore_benchmark/pipeline_evaluation/evaluator.py","file_url":"https://github.com/illuin-tech/vidore-benchmark/blob/HEAD/src/vidore_benchmark/pipeline_evaluation/evaluator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bde3923a8fec6850","mcp_get_code":{"code_sha256":"bde3923a8fec6850"}},{"arxiv_id":"2406.05646","paper":"/paper/icu-sepsis-a-benchmark-mdp-built-from-real","title":"ICU-Sepsis: A Benchmark MDP Built from Real Medical Data","date":"2024-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"icu-sepsis/icu-sepsis","path":"packages/icu_sepsis_helpers/icu_sepsis_helpers/policy_examination/baselines_with_perturb.py","file_url":"https://github.com/icu-sepsis/icu-sepsis/blob/HEAD/packages/icu_sepsis_helpers/icu_sepsis_helpers/policy_examination/baselines_with_perturb.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ae498a45c4495a8d","mcp_get_code":{"code_sha256":"ae498a45c4495a8d"}},{"arxiv_id":"2105.06152","paper":"/paper/when-human-pose-estimation-meets-robustness","title":"When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks","date":"2021-05-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HRNet/HigherHRNet-Human-Pose-Estimation","path":"lib/core/inference.py","file_url":"https://github.com/HRNet/HigherHRNet-Human-Pose-Estimation/blob/HEAD/lib/core/inference.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b2deafbfd7c1f3fc","mcp_get_code":{"code_sha256":"b2deafbfd7c1f3fc"}},{"arxiv_id":"1908.10357","paper":"/paper/bottom-up-higher-resolution-networks-for","title":"HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation","date":"2019-08-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HRNet/Higher-HRNet-Human-Pose-Estimation","path":"lib/core/inference.py","file_url":"https://github.com/HRNet/Higher-HRNet-Human-Pose-Estimation/blob/HEAD/lib/core/inference.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b2deafbfd7c1f3fc","mcp_get_code":{"code_sha256":"b2deafbfd7c1f3fc"}}]}