{"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/evaluate-accuracy","entry":"evaluate_accuracy","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":17,"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":16,"n_samples_ran":5,"n_samples_fingerprinted":1,"n_places":18,"n_places_pointer_only":5,"by_status":{"ran_honours":3,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":2,"unverified":11},"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":"2608.19029","paper":"/paper/arxiv-2608-19029","title":"Adaptive Memory and Reflection Multi-Agent System for Medical Question Answering","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"mm-air/AMR-Agent","path":"evaluate.py","file_url":"https://github.com/mm-air/AMR-Agent/blob/HEAD/evaluate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6cb12c37db26f8c7","mcp_get_code":{"code_sha256":"6cb12c37db26f8c7"}},{"arxiv_id":"2509.24088","paper":"/paper/arxiv-2509-24088","title":"CORRECT: Condensed Error Recognition via Knowledge Transfer in Multi-agent Systems","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"UIUC-MLSys/CORRECT","path":"src/evaluate.py","file_url":"https://github.com/UIUC-MLSys/CORRECT/blob/HEAD/src/evaluate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"dae296eb6fedbbee","mcp_get_code":{"code_sha256":"dae296eb6fedbbee"}},{"arxiv_id":"2505.00212","paper":"/paper/which-agent-causes-task-failures-and-when-on","title":"Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems","date":"2025-04-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mingyin1/agents_failure_attribution","path":"Automated_FA/evaluate.py","file_url":"https://github.com/mingyin1/agents_failure_attribution/blob/HEAD/Automated_FA/evaluate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cc9af32b8ab59e05","mcp_get_code":{"code_sha256":"cc9af32b8ab59e05"}},{"arxiv_id":"2410.20886","paper":"/paper/codes-benchmarking-coupled-ode-surrogates","title":"CODES: Benchmarking Coupled ODE Surrogates","date":"2024-10-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"robin-janssen/codes-benchmark","path":"codes/benchmark/bench_fcts.py","file_url":"https://github.com/robin-janssen/codes-benchmark/blob/HEAD/codes/benchmark/bench_fcts.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"51fd95db84bf43ef","mcp_get_code":{"code_sha256":"51fd95db84bf43ef"}},{"arxiv_id":"2407.12588","paper":"/paper/benchmarking-robust-self-supervised-learning","title":"Benchmarking Robust Self-Supervised Learning Across Diverse Downstream Tasks","date":"2024-07-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"layer6ai-labs/ssl-robustness","path":"evaluators/evaluate.py","file_url":"https://github.com/layer6ai-labs/ssl-robustness/blob/HEAD/evaluators/evaluate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"558456af4ed51313","mcp_get_code":{"code_sha256":"558456af4ed51313"}},{"arxiv_id":"2305.14642","paper":"/paper/2305-14642","title":"Newton-Cotes Graph Neural Networks: On the Time Evolution of Dynamic Systems","date":"2023-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zjukg/ncgnn","path":"EqMotion/main_nbody_reasoning.py","file_url":"https://github.com/zjukg/ncgnn/blob/HEAD/EqMotion/main_nbody_reasoning.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"016b1e334d358460","mcp_get_code":{"code_sha256":"016b1e334d358460"}},{"arxiv_id":"2305.14642","paper":"/paper/2305-14642","title":"Newton-Cotes Graph Neural Networks: On the Time Evolution of Dynamic Systems","date":"2023-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zjukg/NCGNN","path":"EqMotion/main_nbody.py","file_url":"https://github.com/zjukg/NCGNN/blob/HEAD/EqMotion/main_nbody.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a4b4fa49d6e48181","mcp_get_code":{"code_sha256":"a4b4fa49d6e48181"}},{"arxiv_id":"2212.09254","paper":"/paper/textgrad-advancing-robustness-evaluation-in","title":"TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization","date":"2022-12-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ucsb-nlp-chang/textgrad","path":"robust_training.py","file_url":"https://github.com/ucsb-nlp-chang/textgrad/blob/HEAD/robust_training.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4fc953cf0a1a3b99","mcp_get_code":{"code_sha256":"4fc953cf0a1a3b99"}},{"arxiv_id":"2205.01841","paper":"/paper/great-truths-are-always-simple-a-rather-1","title":"Great Truths are Always Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models","date":"2022-05-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rucaibox/safe","path":"qagnn.py","file_url":"https://github.com/rucaibox/safe/blob/HEAD/qagnn.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2839d26e6f9412c8","mcp_get_code":{"code_sha256":"2839d26e6f9412c8"}},{"arxiv_id":"2204.13271","paper":"/paper/efficient-and-accurate-conversion-of-spiking","title":"Efficient and Accurate Conversion of Spiking Neural Network with Burst Spikes","date":"2022-04-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"brain-inspired-cognitive-engine/conversion_burst","path":"utils.py","file_url":"https://github.com/brain-inspired-cognitive-engine/conversion_burst/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d4a07d38b7cf02dc","mcp_get_code":{"code_sha256":"d4a07d38b7cf02dc"}},{"arxiv_id":"2202.12233","paper":"/paper/automatic-speaker-verification-spoofing-and","title":"Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation","date":"2022-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"takhemlata/ssl_anti-spoofing","path":"main_SSL_LA.py","file_url":"https://github.com/takhemlata/ssl_anti-spoofing/blob/HEAD/main_SSL_LA.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"abdb16a09c4042f4","mcp_get_code":{"code_sha256":"abdb16a09c4042f4"}},{"arxiv_id":"2112.02732","paper":"/paper/jointlk-joint-reasoning-with-language-models","title":"JointLK: Joint Reasoning with Language Models and Knowledge Graphs for Commonsense Question Answering","date":"2021-12-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yueqing-sun/jointlk","path":"jointlk.py","file_url":"https://github.com/yueqing-sun/jointlk/blob/HEAD/jointlk.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"086fa0038784db8c","mcp_get_code":{"code_sha256":"086fa0038784db8c"}},{"arxiv_id":"2106.11257","paper":"/paper/secure-distributed-training-at-scale","title":"Secure Distributed Training at Scale","date":"2021-06-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yandex-research/btard","path":"resnet/training_utils.py","file_url":"https://github.com/yandex-research/btard/blob/HEAD/resnet/training_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":"a904de8f2aa42d6f","mcp_get_code":{"code_sha256":"a904de8f2aa42d6f"}},{"arxiv_id":"2104.06378","paper":"/paper/qa-gnn-reasoning-with-language-models-and","title":"QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering","date":"2021-04-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"michiyasunaga/qagnn","path":"qagnn.py","file_url":"https://github.com/michiyasunaga/qagnn/blob/HEAD/qagnn.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"086fa0038784db8c","mcp_get_code":{"code_sha256":"086fa0038784db8c"}},{"arxiv_id":"2010.12873","paper":"/paper/learning-contextualized-knowledge-structures","title":"Learning Contextualized Knowledge Structures for Commonsense Reasoning","date":"2020-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"INK-USC/HGN","path":"hgn.py","file_url":"https://github.com/INK-USC/HGN/blob/HEAD/hgn.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"20ae9bc0ed8af203","mcp_get_code":{"code_sha256":"20ae9bc0ed8af203"}},{"arxiv_id":"1712.00559","paper":"/paper/progressive-neural-architecture-search","title":"Progressive Neural Architecture Search","date":"2017-12-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DataXujing/PNASNet_pytorch","path":"model.py","file_url":"https://github.com/DataXujing/PNASNet_pytorch/blob/HEAD/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"eeb1297e063ecfdf","mcp_get_code":{"code_sha256":"eeb1297e063ecfdf"}},{"arxiv_id":"aaai_26578","paper":null,"title":"arXiv:aaai_26578","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"mlvlab/QAT","path":"main_qat.py","file_url":"https://github.com/mlvlab/QAT/blob/HEAD/main_qat.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3998b926dccc833e","mcp_get_code":{"code_sha256":"3998b926dccc833e"}},{"arxiv_id":"2022.findings-naacl.131","paper":null,"title":"arXiv:2022.findings-naacl.131","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"RUCAIBox/SAFE","path":"qagnn.py","file_url":"https://github.com/RUCAIBox/SAFE/blob/HEAD/qagnn.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2839d26e6f9412c8","mcp_get_code":{"code_sha256":"2839d26e6f9412c8"}}]}