{"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/evaluator","entry":"Evaluator","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":9,"n_samples_ran":4,"n_samples_fingerprinted":0,"n_places":9,"n_places_pointer_only":8,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":4,"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":"2606.24999","paper":"/paper/arxiv-2606-24999","title":"Zeroth-Order Deep Learning for PDEs A Zeroth-Order Deep Learning Method for Fully Nonlinear Parabolic Partial Differential Equations with Unknown Coefficients","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"du-ouyang/ZO4PDE","path":"zeroth/solver.py","file_url":"https://github.com/du-ouyang/ZO4PDE/blob/HEAD/zeroth/solver.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f11705f9eabdaf78","mcp_get_code":{"code_sha256":"f11705f9eabdaf78"}},{"arxiv_id":"2501.12619","paper":"/paper/distillation-quantification-for-large","title":"Distillation Quantification for Large Language Models","date":"2025-01-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Aegis1863/LLMs-Distillation-Quantification","path":"easyjailbreak/metrics/Evaluator/Evaluator_ClassificationGetScore.py","file_url":"https://github.com/Aegis1863/LLMs-Distillation-Quantification/blob/HEAD/easyjailbreak/metrics/Evaluator/Evaluator_ClassificationGetScore.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9758dd55551e8559","mcp_get_code":{"code_sha256":"9758dd55551e8559"}},{"arxiv_id":"2406.17216","paper":"/paper/machine-unlearning-fails-to-remove-data","title":"Machine Unlearning Fails to Remove Data Poisoning Attacks","date":"2024-06-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"martinpawel/openunlearn","path":"openunlearn/evaluators/catalog/witches_poison/witches_poison.py","file_url":"https://github.com/martinpawel/openunlearn/blob/HEAD/openunlearn/evaluators/catalog/witches_poison/witches_poison.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0e864600725e860a","mcp_get_code":{"code_sha256":"0e864600725e860a"}},{"arxiv_id":"2303.16634","paper":"/paper/gpteval-nlg-evaluation-using-gpt-4-with","title":"G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment","date":"2023-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"megagonlabs/llm-longeval","path":"eval/evaluator.py","file_url":"https://github.com/megagonlabs/llm-longeval/blob/HEAD/eval/evaluator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"c1344440d3eb8ce8","mcp_get_code":{"code_sha256":"c1344440d3eb8ce8"}},{"arxiv_id":"2106.03084","paper":"/paper/combining-static-word-embeddings-and","title":"Combining Static Word Embeddings and Contextual Representations for Bilingual Lexicon Induction","date":"2021-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"joelmoniz/BLISS","path":"bliss/models/models.py","file_url":"https://github.com/joelmoniz/BLISS/blob/HEAD/bliss/models/models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"739c2f7e50496420","mcp_get_code":{"code_sha256":"739c2f7e50496420"}},{"arxiv_id":"2102.08248","paper":"/paper/hierarchical-vaes-know-what-they-don-t-know","title":"Hierarchical VAEs Know What They Don't Know","date":"2021-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HenryLHH/HVAE-OOD","path":"oodd/evaluators/evaluator.py","file_url":"https://github.com/HenryLHH/HVAE-OOD/blob/HEAD/oodd/evaluators/evaluator.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"206ee3d6cd55d66b","mcp_get_code":{"code_sha256":"206ee3d6cd55d66b"}},{"arxiv_id":"2102.08248","paper":"/paper/hierarchical-vaes-know-what-they-don-t-know","title":"Hierarchical VAEs Know What They Don't Know","date":"2021-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JakobHavtorn/hvae-oodd","path":"oodd/evaluators/evaluator.py","file_url":"https://github.com/JakobHavtorn/hvae-oodd/blob/HEAD/oodd/evaluators/evaluator.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dc6ee9ad5fc8272b","mcp_get_code":{"code_sha256":"dc6ee9ad5fc8272b"}},{"arxiv_id":"1509.02971","paper":"/paper/continuous-control-with-deep-reinforcement","title":"Continuous control with deep reinforcement learning","date":"2015-09-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fshamshirdar/pytorch-rdpg","path":"rdpg.py","file_url":"https://github.com/fshamshirdar/pytorch-rdpg/blob/HEAD/rdpg.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ff0baff75d5cb615","mcp_get_code":{"code_sha256":"ff0baff75d5cb615"}},{"arxiv_id":"2024.findings-acl.462","paper":null,"title":"arXiv:2024.findings-acl.462","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"AI-EDU-LAB/E-EVAL","path":"code/evaluator_series/evaluators/evaluator.py","file_url":"https://github.com/AI-EDU-LAB/E-EVAL/blob/HEAD/code/evaluator_series/evaluators/evaluator.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"844f3b3b35c61612","mcp_get_code":{"code_sha256":"844f3b3b35c61612"}}]}