{"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/calculate-average","entry":"calculate_average","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":5,"n_papers_ran":2,"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":5,"n_samples_ran":2,"n_samples_fingerprinted":1,"n_places":5,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"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":"2501.00321","paper":"/paper/ocrbench-v2-an-improved-benchmark-for","title":"OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning","date":"2024-12-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuliang-liu/multimodalocr","path":"OCRBench_v2/eval_scripts/get_score.py","file_url":"https://github.com/yuliang-liu/multimodalocr/blob/HEAD/OCRBench_v2/eval_scripts/get_score.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3242c8f10997c354","mcp_get_code":{"code_sha256":"3242c8f10997c354"}},{"arxiv_id":"2412.12151","paper":"/paper/smartcal-an-approach-to-self-aware-tool-use","title":"SMARTCAL: An Approach to Self-Aware Tool-Use Evaluation and Calibration","date":"2024-12-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Henrysyh2000/SMARTCAL","path":"ART_SM_CAL/create_sample.py","file_url":"https://github.com/Henrysyh2000/SMARTCAL/blob/HEAD/ART_SM_CAL/create_sample.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"da6cb4abeef41a45","mcp_get_code":{"code_sha256":"da6cb4abeef41a45"}},{"arxiv_id":"2411.01842","paper":"/paper/elastst-towards-robust-varied-horizon","title":"ElasTST: Towards Robust Varied-Horizon Forecasting with Elastic Time-Series Transformer","date":"2024-11-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/ProbTS","path":"probts/utils/save_utils.py","file_url":"https://github.com/microsoft/ProbTS/blob/HEAD/probts/utils/save_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"76c6745b9b380415","mcp_get_code":{"code_sha256":"76c6745b9b380415"}},{"arxiv_id":"2402.09664","paper":"/paper/codemind-a-framework-to-challenge-large","title":"CodeMind: Evaluating Large Language Models for Code Reasoning","date":"2024-02-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"intelligent-cat-lab/codemind","path":"dataset/classeval/ClassEval_4@AssessmentSystem.add_course_score/transformation.py","file_url":"https://github.com/intelligent-cat-lab/codemind/blob/HEAD/dataset/classeval/ClassEval_4%40AssessmentSystem.add_course_score/transformation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NCSA","inline_ok":false,"code_sha256_prefix":"fc0f16f3d89d8f5d","mcp_get_code":{"code_sha256":"fc0f16f3d89d8f5d"}},{"arxiv_id":"2003.12909","paper":"/paper/policy-teaching-via-environment-poisoning","title":"Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning","date":"2020-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"adishs/icml2020_rl-policy-teaching_code","path":"teaching_online.py","file_url":"https://github.com/adishs/icml2020_rl-policy-teaching_code/blob/HEAD/teaching_online.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":"5ddb7a19339e6e8c","mcp_get_code":{"code_sha256":"5ddb7a19339e6e8c"}}]}