{"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/clean-data","entry":"clean_data","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":13,"n_samples_ran":5,"n_samples_fingerprinted":1,"n_places":13,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":5,"unverified":8},"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":"2606.12900","paper":"/paper/arxiv-2606-12900","title":"Zero-source LLM Hallucination Detection with Human-like Criteria Probing","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"TRISKEL10N/HCPD","path":"src/open_r1/hal_dataset_generation.py","file_url":"https://github.com/TRISKEL10N/HCPD/blob/HEAD/src/open_r1/hal_dataset_generation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"3e2ef215dad5385b","mcp_get_code":{"code_sha256":"3e2ef215dad5385b"}},{"arxiv_id":"2605.01317","paper":"/paper/arxiv-2605-01317","title":"Sentiment Analysis of Mobile Legends App Reviews Using Machine Learning and LSTM-Based Deep Learning Models","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Viramhrani/pba2026-Kelompok16","path":"src/pycaret_model.py","file_url":"https://github.com/Viramhrani/pba2026-Kelompok16/blob/HEAD/src/pycaret_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3c5eb5f4b5cc6324","mcp_get_code":{"code_sha256":"3c5eb5f4b5cc6324"}},{"arxiv_id":"2602.22101","paper":"/paper/arxiv-2602-22101","title":"On Imbalanced Regression with Hoeffding Trees","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"marinaAlchirch/DSFA_2026","path":"Code/california_housing_dataset_cleaning.py","file_url":"https://github.com/marinaAlchirch/DSFA_2026/blob/HEAD/Code/california_housing_dataset_cleaning.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"601cfd6fd3147f1d","mcp_get_code":{"code_sha256":"601cfd6fd3147f1d"}},{"arxiv_id":"2601.12119","paper":"/paper/arxiv-2601-12119","title":"CARLA-Round: A Multi-Factor Simulation Dataset for Roundabout Trajectory Prediction","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Rebecca689/CARLA-Round","path":"2clean_and_merge_v2.py","file_url":"https://github.com/Rebecca689/CARLA-Round/blob/HEAD/2clean_and_merge_v2.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"72aea2fd83432ae7","mcp_get_code":{"code_sha256":"72aea2fd83432ae7"}},{"arxiv_id":"2402.17302","paper":"/paper/can-llm-generate-culturally-relevant","title":"Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese","date":"2024-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rifkiaputri/id-csqa","path":"generation/rephrase.py","file_url":"https://github.com/rifkiaputri/id-csqa/blob/HEAD/generation/rephrase.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0ad74b0ae3b4f7a3","mcp_get_code":{"code_sha256":"0ad74b0ae3b4f7a3"}},{"arxiv_id":"2401.04621","paper":"/paper/debugbench-evaluating-debugging-capability-of","title":"DebugBench: Evaluating Debugging Capability of Large Language Models","date":"2024-01-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thunlp/debugbench","path":"dataset_construction/clean_comments.py","file_url":"https://github.com/thunlp/debugbench/blob/HEAD/dataset_construction/clean_comments.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":"39624643acd840a9","mcp_get_code":{"code_sha256":"39624643acd840a9"}},{"arxiv_id":"2310.07602","paper":"/paper/dual-radar-a-multi-modal-dataset-with-dual-4d","title":"Dual Radar: A Multi-modal Dataset with Dual 4D Radar for Autonomous Driving","date":"2023-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"adept-thu/dual-radar","path":"pcdet/datasets/dual_radar/kitti_object_eval_python/eval1.py","file_url":"https://github.com/adept-thu/dual-radar/blob/HEAD/pcdet/datasets/dual_radar/kitti_object_eval_python/eval1.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":"7a89af4cf8defd62","mcp_get_code":{"code_sha256":"7a89af4cf8defd62"}},{"arxiv_id":"2206.05050","paper":"/paper/improved-approximation-for-fair-correlation","title":"Improved Approximation for Fair Correlation Clustering","date":"2022-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"moonin12/improved_fair_correlation_clustering","path":"utils/old_read_write_utils.py","file_url":"https://github.com/moonin12/improved_fair_correlation_clustering/blob/HEAD/utils/old_read_write_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"37e838e6c3aa3fed","mcp_get_code":{"code_sha256":"37e838e6c3aa3fed"}},{"arxiv_id":"2205.11601","paper":"/paper/challenges-in-measuring-bias-via-open-ended","title":"Challenges in Measuring Bias via Open-Ended Language Generation","date":"2022-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"feyzaakyurek/bias-textgen","path":"compute_tox_sent.py","file_url":"https://github.com/feyzaakyurek/bias-textgen/blob/HEAD/compute_tox_sent.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a67a255367faf57e","mcp_get_code":{"code_sha256":"a67a255367faf57e"}},{"arxiv_id":"2104.10956","paper":"/paper/fcos3d-fully-convolutional-one-stage","title":"FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection","date":"2021-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AllenPeng0209/deeproute_competition","path":"mmdet3d/core/evaluation/deeproute_utils/deeproute_eval.py","file_url":"https://github.com/AllenPeng0209/deeproute_competition/blob/HEAD/mmdet3d/core/evaluation/deeproute_utils/deeproute_eval.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":"853d5d97b4442543","mcp_get_code":{"code_sha256":"853d5d97b4442543"}},{"arxiv_id":"2103.15326","paper":"/paper/fooling-lidar-perception-via-adversarial","title":"Fooling LiDAR Perception via Adversarial Trajectory Perturbation","date":"2021-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ai4ce/FLAT","path":"evaluate.py","file_url":"https://github.com/ai4ce/FLAT/blob/HEAD/evaluate.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":"2e99fa2a1601452e","mcp_get_code":{"code_sha256":"2e99fa2a1601452e"}},{"arxiv_id":"2025.emnlp-main.292","paper":null,"title":"arXiv:2025.emnlp-main.292","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"RUC-NLPIR/OmniEval","path":"data_generator/dataset_clean.py","file_url":"https://github.com/RUC-NLPIR/OmniEval/blob/HEAD/data_generator/dataset_clean.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"daeef6551d5fdb7f","mcp_get_code":{"code_sha256":"daeef6551d5fdb7f"}},{"arxiv_id":"2025.acl-long.1159","paper":null,"title":"arXiv:2025.acl-long.1159","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"ulab-uiuc/GoR","path":"data_process.py","file_url":"https://github.com/ulab-uiuc/GoR/blob/HEAD/data_process.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5f3f4fbd640d5d3c","mcp_get_code":{"code_sha256":"5f3f4fbd640d5d3c"}}]}