{"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/tokenizer","entry":"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":16,"n_papers_ran":7,"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":7,"n_samples_fingerprinted":2,"n_places":16,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":7,"unverified":9},"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":"2506.10707","paper":"/paper/contexttab-a-semantics-aware-tabular-in","title":"ConTextTab: A Semantics-Aware Tabular In-Context Learner","date":"2025-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SAP-samples/sap-rpt-1-oss","path":"sap_rpt_oss/model/embeddings.py","file_url":"https://github.com/SAP-samples/sap-rpt-1-oss/blob/HEAD/sap_rpt_oss/model/embeddings.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":"2abe05cf0d9e528a","mcp_get_code":{"code_sha256":"2abe05cf0d9e528a"}},{"arxiv_id":"2502.01591","paper":"/paper/improving-transformer-world-models-for-data","title":"Improving Transformer World Models for Data-Efficient RL","date":"2025-02-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eloialonso/iris","path":"src/models/tokenizer/tokenizer.py","file_url":"https://github.com/eloialonso/iris/blob/HEAD/src/models/tokenizer/tokenizer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"a823cb01993404cf","mcp_get_code":{"code_sha256":"a823cb01993404cf"}},{"arxiv_id":"2411.01006","paper":"/paper/abstracted-shapes-as-tokens-a-generalizable","title":"Abstracted Shapes as Tokens -- A Generalizable and Interpretable Model for Time-series Classification","date":"2024-11-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yunshiwen/vqshape","path":"vqshape/model.py","file_url":"https://github.com/yunshiwen/vqshape/blob/HEAD/vqshape/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5b84e11d45ccaa5b","mcp_get_code":{"code_sha256":"5b84e11d45ccaa5b"}},{"arxiv_id":"2410.05711","paper":"/paper/diffusion-auto-regressive-transformer-for","title":"Diffusion Auto-regressive Transformer for Effective Self-supervised Time Series Forecasting","date":"2024-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mingyue-cheng/timemae","path":"model/TimeMAE.py","file_url":"https://github.com/mingyue-cheng/timemae/blob/HEAD/model/TimeMAE.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1a49d94878ef7d04","mcp_get_code":{"code_sha256":"1a49d94878ef7d04"}},{"arxiv_id":"2410.05016","paper":"/paper/t-jepa-augmentation-free-self-supervised","title":"T-JEPA: Augmentation-Free Self-Supervised Learning for Tabular Data","date":"2024-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jose-melo/t-jepa","path":"src/encoder.py","file_url":"https://github.com/jose-melo/t-jepa/blob/HEAD/src/encoder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c7213c185d77231d","mcp_get_code":{"code_sha256":"c7213c185d77231d"}},{"arxiv_id":"2406.17647","paper":"/paper/variationist-exploring-multifaceted-variation","title":"Variationist: Exploring Multifaceted Variation and Bias in Written Language Data","date":"2024-06-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dhfbk/variationist","path":"variationist/inspector.py","file_url":"https://github.com/dhfbk/variationist/blob/HEAD/variationist/inspector.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c2d6938443e721f4","mcp_get_code":{"code_sha256":"c2d6938443e721f4"}},{"arxiv_id":"2403.01570","paper":"/paper/serval-synergy-learning-between-vertical","title":"SERVAL: Synergy Learning between Vertical Models and LLMs towards Oracle-Level Zero-shot Medical Prediction","date":"2024-03-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jyansir/sersal","path":"models/t2g.py","file_url":"https://github.com/jyansir/sersal/blob/HEAD/models/t2g.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d0e255c6c68af4b2","mcp_get_code":{"code_sha256":"d0e255c6c68af4b2"}},{"arxiv_id":"2402.07865","paper":"/paper/prismatic-vlms-investigating-the-design-space","title":"Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models","date":"2024-02-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tri-ml/vlm-evaluation","path":"vlm_eval/models/prismatic.py","file_url":"https://github.com/tri-ml/vlm-evaluation/blob/HEAD/vlm_eval/models/prismatic.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"e0633b98873dbfc7","mcp_get_code":{"code_sha256":"e0633b98873dbfc7"}},{"arxiv_id":"2402.02355","paper":"/paper/symbol-generating-flexible-black-box","title":"Symbol: Generating Flexible Black-Box Optimizers through Symbolic Equation Learning","date":"2024-02-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gmc-drl/symbol","path":"expr/expression.py","file_url":"https://github.com/gmc-drl/symbol/blob/HEAD/expr/expression.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ac2eca8bc3b28fea","mcp_get_code":{"code_sha256":"ac2eca8bc3b28fea"}},{"arxiv_id":"2209.00588","paper":"/paper/transformers-are-sample-efficient-world","title":"Transformers are Sample-Efficient World Models","date":"2022-09-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eloialonso/iris","path":"src/models/world_model.py","file_url":"https://github.com/eloialonso/iris/blob/HEAD/src/models/world_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"79b0b0b918ab2ac4","mcp_get_code":{"code_sha256":"79b0b0b918ab2ac4"}},{"arxiv_id":"2207.12598","paper":"/paper/classifier-free-diffusion-guidance","title":"Classifier-Free Diffusion Guidance","date":"2022-07-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kjsman/stable-diffusion-pytorch","path":"stable_diffusion_pytorch/pipeline.py","file_url":"https://github.com/kjsman/stable-diffusion-pytorch/blob/HEAD/stable_diffusion_pytorch/pipeline.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"05ee784f97ca2b95","mcp_get_code":{"code_sha256":"05ee784f97ca2b95"}},{"arxiv_id":"2207.06966","paper":"/paper/scene-text-recognition-with-permuted","title":"Scene Text Recognition with Permuted Autoregressive Sequence Models","date":"2022-07-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"baudm/parseq","path":"strhub/models/parseq/model.py","file_url":"https://github.com/baudm/parseq/blob/HEAD/strhub/models/parseq/model.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":"7daac2bdca87bc4f","mcp_get_code":{"code_sha256":"7daac2bdca87bc4f"}},{"arxiv_id":"2101.00294","paper":"/paper/reader-guided-passage-reranking-for-open","title":"Rider: Reader-Guided Passage Reranking for Open-Domain Question Answering","date":"2021-01-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"morningmoni/GAR","path":"rider/rider.py","file_url":"https://github.com/morningmoni/GAR/blob/HEAD/rider/rider.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"07d173914062fa25","mcp_get_code":{"code_sha256":"07d173914062fa25"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SHI-Labs/Compact-Transformers","path":"src/vit.py","file_url":"https://github.com/SHI-Labs/Compact-Transformers/blob/HEAD/src/vit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"89f043dddf4da04c","mcp_get_code":{"code_sha256":"89f043dddf4da04c"}},{"arxiv_id":"2006.04558","paper":"/paper/fastspeech-2-fast-and-high-quality-end-to-end","title":"FastSpeech 2: Fast and High-Quality End-to-End Text to Speech","date":"2020-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tartunlp/transformertts","path":"src/transformer_tts/model/forward_model.py","file_url":"https://github.com/tartunlp/transformertts/blob/HEAD/src/transformer_tts/model/forward_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"6e41883c2988e191","mcp_get_code":{"code_sha256":"6e41883c2988e191"}},{"arxiv_id":"1508.07909","paper":"/paper/neural-machine-translation-of-rare-words-with","title":"Neural Machine Translation of Rare Words with Subword Units","date":"2015-08-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"karpathy/minbpe","path":"minbpe/base.py","file_url":"https://github.com/karpathy/minbpe/blob/HEAD/minbpe/base.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"293d3695d53b0cb1","mcp_get_code":{"code_sha256":"293d3695d53b0cb1"}}]}