{"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/transformermlp","entry":"TransformerMLP","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":5,"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":5,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":0,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":3,"unverified":2},"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":"2111.06377","paper":"/paper/masked-autoencoders-are-scalable-vision","title":"Masked Autoencoders Are Scalable Vision Learners","date":"2021-11-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DarshanDeshpande/jax-models","path":"jax_models/models/masked_autoencoder.py","file_url":"https://github.com/DarshanDeshpande/jax-models/blob/HEAD/jax_models/models/masked_autoencoder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d250b23f4ed3fd00","mcp_get_code":{"code_sha256":"d250b23f4ed3fd00"}},{"arxiv_id":"2105.15203","paper":"/paper/segformer-simple-and-efficient-design-for","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","date":"2021-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DarshanDeshpande/jax-models","path":"jax_models/models/segformer.py","file_url":"https://github.com/DarshanDeshpande/jax-models/blob/HEAD/jax_models/models/segformer.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":"6afe61dba51eef77","mcp_get_code":{"code_sha256":"6afe61dba51eef77"}},{"arxiv_id":"2105.01601","paper":"/paper/mlp-mixer-an-all-mlp-architecture-for-vision","title":"MLP-Mixer: An all-MLP Architecture for Vision","date":"2021-05-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DarshanDeshpande/jax-models","path":"jax_models/models/mlp_mixer.py","file_url":"https://github.com/DarshanDeshpande/jax-models/blob/HEAD/jax_models/models/mlp_mixer.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":"9ce28eaaca4b3ee7","mcp_get_code":{"code_sha256":"9ce28eaaca4b3ee7"}},{"arxiv_id":"2103.14030","paper":"/paper/swin-transformer-hierarchical-vision","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","date":"2021-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DarshanDeshpande/jax-models","path":"jax_models/models/swin_transformer.py","file_url":"https://github.com/DarshanDeshpande/jax-models/blob/HEAD/jax_models/models/swin_transformer.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":"a95290f88e2807cc","mcp_get_code":{"code_sha256":"a95290f88e2807cc"}},{"arxiv_id":"2102.12122","paper":"/paper/pyramid-vision-transformer-a-versatile","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","date":"2021-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DarshanDeshpande/jax-models","path":"jax_models/models/pvit.py","file_url":"https://github.com/DarshanDeshpande/jax-models/blob/HEAD/jax_models/models/pvit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"374179113e51b201","mcp_get_code":{"code_sha256":"374179113e51b201"}}]}