{"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/run-evaluation","entry":"run_evaluation","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":6,"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":4,"n_samples_fingerprinted":1,"n_places":8,"n_places_pointer_only":0,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":1,"unverified":2},"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":"2604.09443","paper":"/paper/arxiv-2604-09443","title":"Many-Tier Instruction Hierarchy in LLM Agents","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"JHU-CLSP/ManyIH","path":"manyih/instruction_following/evaluator.py","file_url":"https://github.com/JHU-CLSP/ManyIH/blob/HEAD/manyih/instruction_following/evaluator.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9e167ab18e6e27f8","mcp_get_code":{"code_sha256":"9e167ab18e6e27f8"}},{"arxiv_id":"2505.23671","paper":"/paper/gso-challenging-software-optimization-tasks","title":"GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agents","date":"2025-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gso-bench/gso","path":"src/gso/harness/opt_at_k.py","file_url":"https://github.com/gso-bench/gso/blob/HEAD/src/gso/harness/opt_at_k.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7d27e938dc504ce5","mcp_get_code":{"code_sha256":"7d27e938dc504ce5"}},{"arxiv_id":"2406.13865","paper":"/paper/surgicai-a-fine-grained-platform-for-data","title":"SurgicAI: A Hierarchical Platform for Fine-Grained Surgical Policy Learning and Benchmarking","date":null,"month_inferred_from_arxiv_id":"2024-06","title_source":"archive","repo":"surgical-robotics-ai/surgicai","path":"RL/Model_evaluation.py","file_url":"https://github.com/surgical-robotics-ai/surgicai/blob/HEAD/RL/Model_evaluation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f0f2653f55b43382","mcp_get_code":{"code_sha256":"f0f2653f55b43382"}},{"arxiv_id":"2401.03601","paper":"/paper/infobench-evaluating-instruction-following","title":"InFoBench: Evaluating Instruction Following Ability in Large Language Models","date":"2024-01-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qinyiwei/infobench","path":"evaluation.py","file_url":"https://github.com/qinyiwei/infobench/blob/HEAD/evaluation.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":"8c494e5dff290c89","mcp_get_code":{"code_sha256":"8c494e5dff290c89"}},{"arxiv_id":"2212.04497","paper":"/paper/unetr-delving-into-efficient-and-accurate-3d","title":"UNETR++: Delving into Efficient and Accurate 3D Medical Image Segmentation","date":"2022-12-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amshaker/unetr_plus_plus","path":"unetr_pp/evaluation/evaluator.py","file_url":"https://github.com/amshaker/unetr_plus_plus/blob/HEAD/unetr_pp/evaluation/evaluator.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e7033836f7ce1958","mcp_get_code":{"code_sha256":"e7033836f7ce1958"}},{"arxiv_id":"2109.03201","paper":"/paper/nnformer-interleaved-transformer-for","title":"nnFormer: Interleaved Transformer for Volumetric Segmentation","date":"2021-09-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"282857341/nnformer","path":"nnformer/evaluation/evaluator.py","file_url":"https://github.com/282857341/nnformer/blob/HEAD/nnformer/evaluation/evaluator.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":"e7033836f7ce1958","mcp_get_code":{"code_sha256":"e7033836f7ce1958"}},{"arxiv_id":"1809.10486","paper":"/paper/nnu-net-self-adapting-framework-for-u-net","title":"nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentation","date":"2018-09-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"justld/nnunet_paddle","path":"nnunet_tools/evaluator.py","file_url":"https://github.com/justld/nnunet_paddle/blob/HEAD/nnunet_tools/evaluator.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e7033836f7ce1958","mcp_get_code":{"code_sha256":"e7033836f7ce1958"}},{"arxiv_id":"1512.02595","paper":"/paper/deep-speech-2-end-to-end-speech-recognition","title":"Deep Speech 2: End-to-End Speech Recognition in English and Mandarin","date":"2015-12-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hkakitani/deepspeech.pytorch","path":"deepspeech_pytorch/testing.py","file_url":"https://github.com/hkakitani/deepspeech.pytorch/blob/HEAD/deepspeech_pytorch/testing.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d954560f1b1b7360","mcp_get_code":{"code_sha256":"d954560f1b1b7360"}}]}