{"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/extract-metrics","entry":"extract_metrics","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":1,"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":1,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":0,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"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":"2504.13630","paper":"/paper/remedy-learning-machine-translation","title":"Remedy: Learning Machine Translation Evaluation from Human Preferences with Reward Modeling","date":"2025-04-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Smu-Tan/Remedy","path":"remedy/toolbox/eval_wmt/extract_result_wmt22.py","file_url":"https://github.com/Smu-Tan/Remedy/blob/HEAD/remedy/toolbox/eval_wmt/extract_result_wmt22.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":"c2108c8a06f7aff7","mcp_get_code":{"code_sha256":"c2108c8a06f7aff7"}},{"arxiv_id":"2504.13630","paper":"/paper/remedy-learning-machine-translation","title":"Remedy: Learning Machine Translation Evaluation from Human Preferences with Reward Modeling","date":"2025-04-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Smu-Tan/Remedy","path":"remedy/toolbox/eval_wmt/extract_result_wmt23.py","file_url":"https://github.com/Smu-Tan/Remedy/blob/HEAD/remedy/toolbox/eval_wmt/extract_result_wmt23.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":"78e2a60b74bbece6","mcp_get_code":{"code_sha256":"78e2a60b74bbece6"}},{"arxiv_id":"2503.14443","paper":"/paper/envbench-a-benchmark-for-automated","title":"EnvBench: A Benchmark for Automated Environment Setup","date":"2025-03-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JetBrains-Research/EnvBench","path":"env_setup_utils/analysis/analyze_results.py","file_url":"https://github.com/JetBrains-Research/EnvBench/blob/HEAD/env_setup_utils/analysis/analyze_results.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1b334e6d73872069","mcp_get_code":{"code_sha256":"1b334e6d73872069"}},{"arxiv_id":"2409.20353","paper":"/paper/cableinspect-ad-an-expert-annotated-anomaly","title":"CableInspect-AD: An Expert-Annotated Anomaly Detection Dataset","date":"2024-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mila-iqia/cableinspect-ad-code","path":"src/anomaly_detector/evaluation_utils.py","file_url":"https://github.com/mila-iqia/cableinspect-ad-code/blob/HEAD/src/anomaly_detector/evaluation_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a8e594894de43df9","mcp_get_code":{"code_sha256":"a8e594894de43df9"}},{"arxiv_id":"2305.07759","paper":"/paper/tinystories-how-small-can-language-models-be","title":"TinyStories: How Small Can Language Models Be and Still Speak Coherent English?","date":"2023-05-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vizuaraai/tiny-stories-regional","path":"results/compare_models_statistics.py","file_url":"https://github.com/vizuaraai/tiny-stories-regional/blob/HEAD/results/compare_models_statistics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e88f4b6f04069085","mcp_get_code":{"code_sha256":"e88f4b6f04069085"}},{"arxiv_id":"2106.01202","paper":"/paper/framing-rnn-as-a-kernel-method-a-neural-ode","title":"Framing RNN as a kernel method: A neural ODE approach","date":"2021-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"afermanian/rnn-kernel","path":"utils.py","file_url":"https://github.com/afermanian/rnn-kernel/blob/HEAD/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":"81bff8f9801b44b8","mcp_get_code":{"code_sha256":"81bff8f9801b44b8"}}]}