{"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/get-vocab","entry":"get_vocab","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":15,"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":16,"n_samples_ran":3,"n_samples_fingerprinted":1,"n_places":16,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":1,"unverified":13},"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":"2410.15618","paper":"/paper/erasing-undesirable-concepts-in-diffusion","title":"Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation","date":"2024-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tuananhbui89/Erasing-Adversarial-Preservation","path":"gen_embedding_matrix.py","file_url":"https://github.com/tuananhbui89/Erasing-Adversarial-Preservation/blob/HEAD/gen_embedding_matrix.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0be5dca592f6fd54","mcp_get_code":{"code_sha256":"0be5dca592f6fd54"}},{"arxiv_id":"2406.01506","paper":"/paper/the-geometry-of-categorical-and-hierarchical","title":"The Geometry of Categorical and Hierarchical Concepts in Large Language Models","date":"2024-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kihopark/llm_categorical_hierarchical_representations","path":"hierarchical/from_models.py","file_url":"https://github.com/kihopark/llm_categorical_hierarchical_representations/blob/HEAD/hierarchical/from_models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"44eb460ae27cb634","mcp_get_code":{"code_sha256":"44eb460ae27cb634"}},{"arxiv_id":"2311.09205","paper":"/paper/when-is-multilinguality-a-curse-language","title":"When Is Multilinguality a Curse? Language Modeling for 250 High- and Low-Resource Languages","date":"2023-11-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tylerachang/curse-of-multilinguality","path":"utils/data_utils.py","file_url":"https://github.com/tylerachang/curse-of-multilinguality/blob/HEAD/utils/data_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3b25fd0a90ff7a19","mcp_get_code":{"code_sha256":"3b25fd0a90ff7a19"}},{"arxiv_id":"2307.04408","paper":"/paper/tim-teaching-large-language-models-to","title":"TIM: Teaching Large Language Models to Translate with Comparison","date":"2023-07-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lemon0830/tim","path":"inference/infer_bloom.py","file_url":"https://github.com/lemon0830/tim/blob/HEAD/inference/infer_bloom.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c542067848f10eda","mcp_get_code":{"code_sha256":"c542067848f10eda"}},{"arxiv_id":"2212.09736","paper":"/paper/don-t-generate-discriminate-a-proposal-for","title":"Don't Generate, Discriminate: A Proposal for Grounding Language Models to Real-World Environments","date":"2022-12-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dki-lab/pangu","path":"utils/kb_environment.py","file_url":"https://github.com/dki-lab/pangu/blob/HEAD/utils/kb_environment.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"60f81fdf6a4800c6","mcp_get_code":{"code_sha256":"60f81fdf6a4800c6"}},{"arxiv_id":"2103.15059","paper":"/paper/a-comprehensive-survey-on-knowledge-graph","title":"A Benchmark and Comprehensive Survey on Knowledge Graph Entity Alignment via Representation Learning","date":"2021-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ruizhang-ai/EA_for_KG","path":"code/experiment_2.py","file_url":"https://github.com/ruizhang-ai/EA_for_KG/blob/HEAD/code/experiment_2.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"a76fd6e5be073e0f","mcp_get_code":{"code_sha256":"a76fd6e5be073e0f"}},{"arxiv_id":"2008.11790","paper":"/paper/mutagan-a-seq2seq-gan-framework-to-predict","title":"MutaGAN: A Seq2seq GAN Framework to Predict Mutations of Evolving Protein Populations","date":"2020-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"1hachem/mutaGAN","path":"src/encode.py","file_url":"https://github.com/1hachem/mutaGAN/blob/HEAD/src/encode.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2af3d0d3b56301ba","mcp_get_code":{"code_sha256":"2af3d0d3b56301ba"}},{"arxiv_id":"2001.01941","paper":"/paper/paraphrase-generation-with-latent-bag-of-1","title":"Paraphrase Generation with Latent Bag of Words","date":"2020-01-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"FranxYao/dgm_latent_bow","path":"src/nlp_pipeline.py","file_url":"https://github.com/FranxYao/dgm_latent_bow/blob/HEAD/src/nlp_pipeline.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b6b052efd0a759e4","mcp_get_code":{"code_sha256":"b6b052efd0a759e4"}},{"arxiv_id":"1911.00720","paper":"/paper/zen-pre-training-chinese-text-encoder","title":"ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations","date":"2019-11-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cuhksz-nlp/het-mc","path":"hetmc_helper.py","file_url":"https://github.com/cuhksz-nlp/het-mc/blob/HEAD/hetmc_helper.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"99b87b401d1fae1e","mcp_get_code":{"code_sha256":"99b87b401d1fae1e"}},{"arxiv_id":"1907.08268","paper":"/paper/discrete-object-generation-with-reversible","title":"Discrete Object Generation with Reversible Inductive Construction","date":"2019-07-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PrincetonLIPS/reversible-inductive-construction","path":"code/genric/data_utils.py","file_url":"https://github.com/PrincetonLIPS/reversible-inductive-construction/blob/HEAD/code/genric/data_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f8f8fa3bcc697f45","mcp_get_code":{"code_sha256":"f8f8fa3bcc697f45"}},{"arxiv_id":"1905.12688","paper":"/paper/choosing-transfer-languages-for-cross-lingual","title":"Choosing Transfer Languages for Cross-Lingual Learning","date":"2019-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"neulab/langrank","path":"index_el_datasets.py","file_url":"https://github.com/neulab/langrank/blob/HEAD/index_el_datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"f965bfedef5c61cb","mcp_get_code":{"code_sha256":"f965bfedef5c61cb"}},{"arxiv_id":"1905.12688","paper":"/paper/choosing-transfer-languages-for-cross-lingual","title":"Choosing Transfer Languages for Cross-Lingual Learning","date":"2019-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"neulab/langrank","path":"index_parsing_datasets.py","file_url":"https://github.com/neulab/langrank/blob/HEAD/index_parsing_datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"6bc91b03eb6e1adf","mcp_get_code":{"code_sha256":"6bc91b03eb6e1adf"}},{"arxiv_id":"1809.05679","paper":"/paper/graph-convolutional-networks-for-text","title":"Graph Convolutional Networks for Text Classification","date":"2018-09-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"codeKgu/text-gcn","path":"build_graph.py","file_url":"https://github.com/codeKgu/text-gcn/blob/HEAD/build_graph.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f0aeffa095b44a3a","mcp_get_code":{"code_sha256":"f0aeffa095b44a3a"}},{"arxiv_id":"1603.01360","paper":"/paper/neural-architectures-for-named-entity","title":"Neural Architectures for Named Entity Recognition","date":"2016-03-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"riedlma/sequence_tagging","path":"model/data_utils.py","file_url":"https://github.com/riedlma/sequence_tagging/blob/HEAD/model/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":"85e5be88dbd9ad46","mcp_get_code":{"code_sha256":"85e5be88dbd9ad46"}},{"arxiv_id":"1411.4952","paper":"/paper/from-captions-to-visual-concepts-and-back","title":"From Captions to Visual Concepts and Back","date":"2014-11-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"s-gupta/visual-concepts","path":"preprocess.py","file_url":"https://github.com/s-gupta/visual-concepts/blob/HEAD/preprocess.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"c63e11043a0ae6b7","mcp_get_code":{"code_sha256":"c63e11043a0ae6b7"}},{"arxiv_id":"1409.3215","paper":"/paper/sequence-to-sequence-learning-with-neural","title":"Sequence to Sequence Learning with Neural Networks","date":"2014-09-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"la-serene/English-German-Translation-System","path":"tokenizer.py","file_url":"https://github.com/la-serene/English-German-Translation-System/blob/HEAD/tokenizer.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":"a6697bcb0adf201d","mcp_get_code":{"code_sha256":"a6697bcb0adf201d"}}]}