{"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/mask-tokens","entry":"mask_tokens","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":12,"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":5,"n_samples_fingerprinted":0,"n_places":12,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":0,"ran":2,"unverified":7},"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":"2607.20057","paper":"/paper/arxiv-2607-20057","title":"Antigen-specific Antibody Multi-modal Foundation Model for Functional Antibody Design","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"XL-S224/AAMFM","path":"src/cpt/training/masking.py","file_url":"https://github.com/XL-S224/AAMFM/blob/HEAD/src/cpt/training/masking.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ac2f32e7c4b80284","mcp_get_code":{"code_sha256":"ac2f32e7c4b80284"}},{"arxiv_id":"2505.07610","paper":"/paper/concept-level-explainability-for-auditing","title":"Concept-Level Explainability for Auditing & Steering LLM Responses","date":"2025-05-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"k-amara/conceptx","path":"src/faithfulness.py","file_url":"https://github.com/k-amara/conceptx/blob/HEAD/src/faithfulness.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":"e8af2d39efba1586","mcp_get_code":{"code_sha256":"e8af2d39efba1586"}},{"arxiv_id":"2403.11901","paper":"/paper/larimar-large-language-models-with-episodic","title":"Larimar: Large Language Models with Episodic Memory Control","date":"2024-03-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IBM/larimar","path":"larimar_base/lightning_model.py","file_url":"https://github.com/IBM/larimar/blob/HEAD/larimar_base/lightning_model.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":"649a7fe08874330c","mcp_get_code":{"code_sha256":"649a7fe08874330c"}},{"arxiv_id":"2308.09363","paper":"/paper/open-vocabulary-video-question-answering-a","title":"Open-vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models","date":"2023-08-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mlvlab/OVQA","path":"util/misc.py","file_url":"https://github.com/mlvlab/OVQA/blob/HEAD/util/misc.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e42c9680fb0f8054","mcp_get_code":{"code_sha256":"e42c9680fb0f8054"}},{"arxiv_id":"2110.01256","paper":"/paper/revisiting-self-training-for-few-shot","title":"Revisiting Self-Training for Few-Shot Learning of Language Model","date":"2021-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"matthewcym/sflm","path":"src/utils.py","file_url":"https://github.com/matthewcym/sflm/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cbf3175e3ec772a0","mcp_get_code":{"code_sha256":"cbf3175e3ec772a0"}},{"arxiv_id":"2107.03444","paper":"/paper/keep-it-simple-unsupervised-simplification-of-1","title":"Keep it Simple: Unsupervised Simplification of Multi-Paragraph Text","date":"2021-07-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tingofurro/keep_it_simple","path":"utils_masking.py","file_url":"https://github.com/tingofurro/keep_it_simple/blob/HEAD/utils_masking.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":"aae67c85186c7e28","mcp_get_code":{"code_sha256":"aae67c85186c7e28"}},{"arxiv_id":"2106.01561","paper":"/paper/can-generative-pre-trained-language-models","title":"Can Generative Pre-trained Language Models Serve as Knowledge Bases for Closed-book QA?","date":"2021-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wangcunxiang/Can-PLM-Serve-as-KB-for-CBQA","path":"simpletransformers/language_modeling/language_modeling_utils.py","file_url":"https://github.com/wangcunxiang/Can-PLM-Serve-as-KB-for-CBQA/blob/HEAD/simpletransformers/language_modeling/language_modeling_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":"e4a3df6f2b78aa86","mcp_get_code":{"code_sha256":"e4a3df6f2b78aa86"}},{"arxiv_id":"2010.05324","paper":"/paper/multilingual-offensive-language","title":"Multilingual Offensive Language Identification with Cross-lingual Embeddings","date":"2020-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tharindudr/DeepOffense","path":"deepoffense/language_modeling/language_modeling_utils.py","file_url":"https://github.com/tharindudr/DeepOffense/blob/HEAD/deepoffense/language_modeling/language_modeling_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":"37e86e14623d0254","mcp_get_code":{"code_sha256":"37e86e14623d0254"}},{"arxiv_id":"2003.10555","paper":"/paper/electra-pre-training-text-encoders-as-1","title":"ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators","date":"2020-03-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"richarddwang/electra_pytorch","path":"pretrain.py","file_url":"https://github.com/richarddwang/electra_pytorch/blob/HEAD/pretrain.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b195c0bc58a304ad","mcp_get_code":{"code_sha256":"b195c0bc58a304ad"}},{"arxiv_id":"1902.07814","paper":"/paper/learning-dual-retrieval-module-for-semi","title":"Learning Dual Retrieval Module for Semi-supervised Relation Extraction","date":"2019-02-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"INK-USC/DualRE","path":"utils/data_utils.py","file_url":"https://github.com/INK-USC/DualRE/blob/HEAD/utils/data_utils.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":"cfdea81e0b0366a4","mcp_get_code":{"code_sha256":"cfdea81e0b0366a4"}},{"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":"jungomi/swiss-language-model","path":"dataset.py","file_url":"https://github.com/jungomi/swiss-language-model/blob/HEAD/dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9426851b703fea8b","mcp_get_code":{"code_sha256":"9426851b703fea8b"}},{"arxiv_id":"2021.findings-emnlp.386","paper":null,"title":"arXiv:2021.findings-emnlp.386","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"lbe0613/GCC","path":"pretrain/run_pretrain.py","file_url":"https://github.com/lbe0613/GCC/blob/HEAD/pretrain/run_pretrain.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c99cf98ff40740f5","mcp_get_code":{"code_sha256":"c99cf98ff40740f5"}}]}