{"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/augment-data","entry":"augment_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":7,"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":7,"n_samples_ran":3,"n_samples_fingerprinted":1,"n_places":7,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":0,"ran":0,"unverified":4},"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":"2411.04986","paper":"/paper/the-semantic-hub-hypothesis-language-models","title":"The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities","date":"2024-11-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZhaofengWu/semantic-hub","path":"multilingual/similarity.py","file_url":"https://github.com/ZhaofengWu/semantic-hub/blob/HEAD/multilingual/similarity.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":"51ceab4ea3055e92","mcp_get_code":{"code_sha256":"51ceab4ea3055e92"}},{"arxiv_id":"2410.23996","paper":"/paper/an-information-criterion-for-controlled","title":"An Information Criterion for Controlled Disentanglement of Multimodal Data","date":"2024-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uhlerlab/disentangledssl","path":"synthetic_task/algorithms.py","file_url":"https://github.com/uhlerlab/disentangledssl/blob/HEAD/synthetic_task/algorithms.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fbaeedfcd82946ff","mcp_get_code":{"code_sha256":"fbaeedfcd82946ff"}},{"arxiv_id":"2410.19818","paper":"/paper/unimts-unified-pre-training-for-motion-time","title":"UniMTS: Unified Pre-training for Motion Time Series","date":"2024-10-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiyuanzh/unimts","path":"utils.py","file_url":"https://github.com/xiyuanzh/unimts/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a7a90479c224d2be","mcp_get_code":{"code_sha256":"a7a90479c224d2be"}},{"arxiv_id":"1911.03221","paper":"/paper/dreem-open-datasets-multi-scored-sleep","title":"Dreem Open Datasets: Multi-Scored Sleep Datasets to compare Human and Automated sleep staging","date":"2019-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Dreem-Organization/dreem-learning-open","path":"dreem_learning_open/datasets/data_augmentation.py","file_url":"https://github.com/Dreem-Organization/dreem-learning-open/blob/HEAD/dreem_learning_open/datasets/data_augmentation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8ae689bec5854251","mcp_get_code":{"code_sha256":"8ae689bec5854251"}},{"arxiv_id":"1908.07898","paper":"/paper/190807898","title":"Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets","date":"2019-08-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mega002/annotator_bias","path":"obqa_create_data_splits.py","file_url":"https://github.com/mega002/annotator_bias/blob/HEAD/obqa_create_data_splits.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":"b58e8237e5875f5d","mcp_get_code":{"code_sha256":"b58e8237e5875f5d"}},{"arxiv_id":"1906.05841","paper":"/paper/deep-reinforcement-learning-for-industrial","title":"Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewards","date":"2019-06-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mizolotu/SmartExcavator","path":"select_demonstration.py","file_url":"https://github.com/mizolotu/SmartExcavator/blob/HEAD/select_demonstration.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"9f1afcb162e28be2","mcp_get_code":{"code_sha256":"9f1afcb162e28be2"}},{"arxiv_id":"1905.12019","paper":"/paper/unified-probabilistic-deep-continual-learning","title":"Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set Recognition","date":"2019-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MrtnMndt/OCDVAEContinualLearning","path":"lib/Training/augmentation.py","file_url":"https://github.com/MrtnMndt/OCDVAEContinualLearning/blob/HEAD/lib/Training/augmentation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"acecd7a6217e354d","mcp_get_code":{"code_sha256":"acecd7a6217e354d"}}]}