{"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/flat-accuracy","entry":"flat_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":5,"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":1,"n_samples_ran":1,"n_samples_fingerprinted":1,"n_places":5,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":1,"ran":0,"unverified":0},"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":"2505.11586","paper":"/paper/the-ripple-effect-on-unforeseen-complications","title":"The Ripple Effect: On Unforeseen Complications of Backdoor Attacks","date":"2025-05-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhangrui4041/backdoor_complications","path":"complication_reduction_train.py","file_url":"https://github.com/zhangrui4041/backdoor_complications/blob/HEAD/complication_reduction_train.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f3e68336634b8642","mcp_get_code":{"code_sha256":"f3e68336634b8642"}},{"arxiv_id":"2405.06459","paper":"/paper/are-eeg-to-text-models-working","title":"Are EEG-to-Text Models Working?","date":"2024-05-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mikewangwzhl/eeg-to-text","path":"eval_sentiment.py","file_url":"https://github.com/mikewangwzhl/eeg-to-text/blob/HEAD/eval_sentiment.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f3e68336634b8642","mcp_get_code":{"code_sha256":"f3e68336634b8642"}},{"arxiv_id":"2109.05897","paper":"/paper/question-answering-over-electronic-devices-a","title":"Question Answering over Electronic Devices: A New Benchmark Dataset and a Multi-Task Learning based QA Framework","date":"2021-09-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"abhi1nandy2/emnlp-2021-findings","path":"fine_tuning_variants_scripts/AR_sentence_wise.py","file_url":"https://github.com/abhi1nandy2/emnlp-2021-findings/blob/HEAD/fine_tuning_variants_scripts/AR_sentence_wise.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f3e68336634b8642","mcp_get_code":{"code_sha256":"f3e68336634b8642"}},{"arxiv_id":"2002.10361","paper":"/paper/multilingual-twitter-corpus-and-baselines-for","title":"Multilingual Twitter Corpus and Baselines for Evaluating Demographic Bias in Hate Speech Recognition","date":"2020-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiaoleihuang/Multilingual_Fairness_LREC","path":"bert.py","file_url":"https://github.com/xiaoleihuang/Multilingual_Fairness_LREC/blob/HEAD/bert.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f3e68336634b8642","mcp_get_code":{"code_sha256":"f3e68336634b8642"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aws-samples/amazon-sagemaker-bert-pytorch","path":"code/train_deploy.py","file_url":"https://github.com/aws-samples/amazon-sagemaker-bert-pytorch/blob/HEAD/code/train_deploy.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT-0","inline_ok":true,"code_sha256_prefix":"f3e68336634b8642","mcp_get_code":{"code_sha256":"f3e68336634b8642"}}]}