{"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/prepare-datasets","entry":"prepare_datasets","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":13,"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":12,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":14,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":1,"unverified":9},"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":"2604.23627","paper":"/paper/arxiv-2604-23627","title":"Neural Grammatical Error Correction for Romanian","date":"2026-04-26","month_inferred_from_arxiv_id":null,"title_source":"syntology","repo":"TeodorMihai/RoGEC","path":"transformer/dataset.py","file_url":"https://github.com/TeodorMihai/RoGEC/blob/HEAD/transformer/dataset.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":"695abdff0f8b6e82","mcp_get_code":{"code_sha256":"695abdff0f8b6e82"}},{"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":"utils/preprocess.py","file_url":"https://github.com/zhangrui4041/backdoor_complications/blob/HEAD/utils/preprocess.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2246abeb87811106","mcp_get_code":{"code_sha256":"2246abeb87811106"}},{"arxiv_id":"2505.10518","paper":"/paper/multi-token-prediction-needs-registers","title":"Multi-Token Prediction Needs Registers","date":"2025-05-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nasosger/mutor","path":"language_modeling/src/dataloaders_mutor.py","file_url":"https://github.com/nasosger/mutor/blob/HEAD/language_modeling/src/dataloaders_mutor.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9294b12a2eccb090","mcp_get_code":{"code_sha256":"9294b12a2eccb090"}},{"arxiv_id":"2502.19670","paper":"/paper/training-robust-graph-neural-networks-by","title":"Training Robust Graph Neural Networks by Modeling Noise Dependencies","date":"2025-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WtaoZhao/GraphGLOW","path":"src/core/model_handler.py","file_url":"https://github.com/WtaoZhao/GraphGLOW/blob/HEAD/src/core/model_handler.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b450d45f806dd32a","mcp_get_code":{"code_sha256":"b450d45f806dd32a"}},{"arxiv_id":"2502.02789","paper":"/paper/speculative-prefill-turbocharging-ttft-with","title":"Speculative Prefill: Turbocharging TTFT with Lightweight and Training-Free Token Importance Estimation","date":"2025-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Jingyu6/speculative_prefill","path":"eval/qps_client.py","file_url":"https://github.com/Jingyu6/speculative_prefill/blob/HEAD/eval/qps_client.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ec827626111b4b80","mcp_get_code":{"code_sha256":"ec827626111b4b80"}},{"arxiv_id":"2307.08507","paper":"/paper/efficient-and-accurate-optimal-transport-with","title":"Efficient and Accurate Optimal Transport with Mirror Descent and Conjugate Gradients","date":"2023-07-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"adaptive-agents-lab/mdot-pncg","path":"mnist_experiments.py","file_url":"https://github.com/adaptive-agents-lab/mdot-pncg/blob/HEAD/mnist_experiments.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1564dfe3c1ffac88","mcp_get_code":{"code_sha256":"1564dfe3c1ffac88"}},{"arxiv_id":"2307.00175","paper":"/paper/still-no-lie-detector-for-language-models","title":"Still No Lie Detector for Language Models: Probing Empirical and Conceptual Roadblocks","date":"2023-06-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"5b5f6a3969b72cda","mcp_get_code":{"code_sha256":"5b5f6a3969b72cda"}},{"arxiv_id":"2304.13734","paper":"/paper/the-internal-state-of-an-llm-knows-when-its","title":"The Internal State of an LLM Knows When It's Lying","date":"2023-04-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"balevinstein/probes","path":"TrainProbes.py","file_url":"https://github.com/balevinstein/probes/blob/HEAD/TrainProbes.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":"5b5f6a3969b72cda","mcp_get_code":{"code_sha256":"5b5f6a3969b72cda"}},{"arxiv_id":"2210.00875","paper":"/paper/untargeted-backdoor-watermark-towards","title":"Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protection","date":"2022-09-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"THUYimingLi/Untargeted_Backdoor_Watermark","path":"UBW-C/eval_loss.py","file_url":"https://github.com/THUYimingLi/Untargeted_Backdoor_Watermark/blob/HEAD/UBW-C/eval_loss.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":"46fc2d22eb1e47be","mcp_get_code":{"code_sha256":"46fc2d22eb1e47be"}},{"arxiv_id":"2210.00875","paper":"/paper/untargeted-backdoor-watermark-towards","title":"Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protection","date":"2022-09-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"THUYimingLi/Untargeted_Backdoor_Watermark","path":"UBW-C/eval_ASR.py","file_url":"https://github.com/THUYimingLi/Untargeted_Backdoor_Watermark/blob/HEAD/UBW-C/eval_ASR.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":"5ba9825ab6ff7eca","mcp_get_code":{"code_sha256":"5ba9825ab6ff7eca"}},{"arxiv_id":"2006.13009","paper":"/paper/iterative-deep-graph-learning-for-graph-1","title":"Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings","date":"2020-06-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hugochan/IDGL","path":"src/core/utils/data_utils.py","file_url":"https://github.com/hugochan/IDGL/blob/HEAD/src/core/utils/data_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":"7533b3dc9f5bbfd6","mcp_get_code":{"code_sha256":"7533b3dc9f5bbfd6"}},{"arxiv_id":"1908.04942","paper":"/paper/reinforcement-learning-based-graph-to","title":"Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation","date":"2019-08-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hugochan/RL-based-Graph2Seq-for-NQG","path":"src/core/utils/data_utils.py","file_url":"https://github.com/hugochan/RL-based-Graph2Seq-for-NQG/blob/HEAD/src/core/utils/data_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":"2988ee69e45e3e36","mcp_get_code":{"code_sha256":"2988ee69e45e3e36"}},{"arxiv_id":"1806.09231","paper":"/paper/clebsch-gordan-nets-a-fully-fourier-space","title":"Clebsch-Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Network","date":"2018-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zlin7/CGNet","path":"Shrec17/Shrec17_main_fast.py","file_url":"https://github.com/zlin7/CGNet/blob/HEAD/Shrec17/Shrec17_main_fast.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":"033566c62f5f23ae","mcp_get_code":{"code_sha256":"033566c62f5f23ae"}},{"arxiv_id":"2024.findings-naacl.294","paper":null,"title":"arXiv:2024.findings-naacl.294","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"balevinstein/Probes","path":"TrainProbes.py","file_url":"https://github.com/balevinstein/Probes/blob/HEAD/TrainProbes.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":"5b5f6a3969b72cda","mcp_get_code":{"code_sha256":"5b5f6a3969b72cda"}}]}