{"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-pretrained-tokenizer","entry":"get_pretrained_tokenizer","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":9,"n_papers_ran":0,"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":6,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":9,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":6},"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":"2404.13039","paper":"/paper/lapa-latent-prompt-assist-model-for-medical","title":"LaPA: Latent Prompt Assist Model For Medical Visual Question Answering","date":"2024-04-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"garygutc/lapa_model","path":"m3ae/datamodules/base_datamodule.py","file_url":"https://github.com/garygutc/lapa_model/blob/HEAD/m3ae/datamodules/base_datamodule.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7620b2fb3b2800ef","mcp_get_code":{"code_sha256":"7620b2fb3b2800ef"}},{"arxiv_id":"2401.13298","paper":"/paper/towards-explainable-harmful-meme-detection","title":"Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models","date":"2024-01-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hkbunlp/explainhm-www2024","path":"src/datamodules/datamodule_base.py","file_url":"https://github.com/hkbunlp/explainhm-www2024/blob/HEAD/src/datamodules/datamodule_base.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":"fb1f56a05ab8f4eb","mcp_get_code":{"code_sha256":"fb1f56a05ab8f4eb"}},{"arxiv_id":"2311.18832","paper":"/paper/exploiting-diffusion-prior-for-generalizable","title":"Exploiting Diffusion Prior for Generalizable Dense Prediction","date":"2023-11-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shinying/dest","path":"src/datamodules/datamodule_base.py","file_url":"https://github.com/shinying/dest/blob/HEAD/src/datamodules/datamodule_base.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"57a540dd0e7dc627","mcp_get_code":{"code_sha256":"57a540dd0e7dc627"}},{"arxiv_id":"2309.02691","paper":"/paper/a-joint-study-of-phrase-grounding-and-task","title":"A Joint Study of Phrase Grounding and Task Performance in Vision and Language Models","date":"2023-09-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lil-lab/phrase_grounding","path":"src/datamodules/datamodule_base.py","file_url":"https://github.com/lil-lab/phrase_grounding/blob/HEAD/src/datamodules/datamodule_base.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"110be10502200f87","mcp_get_code":{"code_sha256":"110be10502200f87"}},{"arxiv_id":"2309.01420","paper":"/paper/unified-pre-training-with-pseudo-texts-for-1","title":"Unified Pre-training with Pseudo Texts for Text-To-Image Person Re-identification","date":"2023-09-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhiyinshao-h/unipt","path":"vilt/datamodules/datamodule_base.py","file_url":"https://github.com/zhiyinshao-h/unipt/blob/HEAD/vilt/datamodules/datamodule_base.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":"6cc26ba2dedcb73e","mcp_get_code":{"code_sha256":"6cc26ba2dedcb73e"}},{"arxiv_id":"2206.08657","paper":"/paper/bridge-tower-building-bridges-between","title":"BridgeTower: Building Bridges Between Encoders in Vision-Language Representation Learning","date":"2022-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/BridgeTower","path":"src/datamodules/datamodule_base.py","file_url":"https://github.com/microsoft/BridgeTower/blob/HEAD/src/datamodules/datamodule_base.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0e69b0ec152ff79a","mcp_get_code":{"code_sha256":"0e69b0ec152ff79a"}},{"arxiv_id":"Luo_LexLIP_Lexicon-Bottlenecked_Language-Image_Pre-Training_for_Large-Scale_Image-Text_Sparse_Retrieval_ICCV_2023_paper","paper":null,"title":"arXiv:Luo_LexLIP_Lexicon-Bottlenecked_Language-Image_Pre-Training_for_Large-Scale_Image-Text_Sparse_Retrieval_ICCV_2023_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"ChiYeungLaw/LexLIP-ICCV23","path":"Phase1/src/datamodules/datamodule_base.py","file_url":"https://github.com/ChiYeungLaw/LexLIP-ICCV23/blob/HEAD/Phase1/src/datamodules/datamodule_base.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":"6cc26ba2dedcb73e","mcp_get_code":{"code_sha256":"6cc26ba2dedcb73e"}},{"arxiv_id":"Dou_An_Empirical_Study_of_Training_End-to-End_Vision-and-Language_Transformers_CVPR_2022_paper","paper":null,"title":"arXiv:Dou_An_Empirical_Study_of_Training_End-to-End_Vision-and-Language_Transformers_CVPR_2022_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"zdou0830/METER","path":"meter/datamodules/datamodule_base.py","file_url":"https://github.com/zdou0830/METER/blob/HEAD/meter/datamodules/datamodule_base.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"0e69b0ec152ff79a","mcp_get_code":{"code_sha256":"0e69b0ec152ff79a"}},{"arxiv_id":"2024.findings-naacl.162","paper":null,"title":"arXiv:2024.findings-naacl.162","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"declare-lab/Sealing","path":"all-in-one/AllInOne/datamodules/datamodule_base.py","file_url":"https://github.com/declare-lab/Sealing/blob/HEAD/all-in-one/AllInOne/datamodules/datamodule_base.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6cc26ba2dedcb73e","mcp_get_code":{"code_sha256":"6cc26ba2dedcb73e"}}]}