{"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/tokenembedding","entry":"TokenEmbedding","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":11,"n_papers_ran":10,"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":18,"n_samples_ran":17,"n_samples_fingerprinted":3,"n_places":18,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":17,"unverified":1},"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":"2606.21973","paper":"/paper/arxiv-2606-21973","title":"SPOTR: Spatio-temporal Pooling One-Token Reconstruction for Universal Physiological Signal Self-supervised Learning","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"PKUDigitalHealth/HeartLang","path":"modeling_pretrain.py","file_url":"https://github.com/PKUDigitalHealth/HeartLang/blob/HEAD/modeling_pretrain.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"aae10c401a510e87","mcp_get_code":{"code_sha256":"aae10c401a510e87"}},{"arxiv_id":"2403.00131","paper":"/paper/units-building-a-unified-time-series-model","title":"UniTS: A Unified Multi-Task Time Series Model","date":"2024-02-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thuml/Time-Series-Library","path":"models/TimeMixer.py","file_url":"https://github.com/thuml/Time-Series-Library/blob/HEAD/models/TimeMixer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"588a4a8475ed63a0","mcp_get_code":{"code_sha256":"588a4a8475ed63a0"}},{"arxiv_id":"2402.02104","paper":"/paper/learning-structure-aware-representations-of","title":"Learning Structure-Aware Representations of Dependent Types","date":"2024-02-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"konstantinoskokos/quill","path":"src/quill/nn/model.py","file_url":"https://github.com/konstantinoskokos/quill/blob/HEAD/src/quill/nn/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"29f310dfa3baa3c0","mcp_get_code":{"code_sha256":"29f310dfa3baa3c0"}},{"arxiv_id":"2301.07945","paper":"/paper/pdformer-propagation-delay-aware-dynamic-long","title":"PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Prediction","date":"2023-01-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BUAABIGSCity/PDFormer","path":"libcity/model/traffic_flow_prediction/PDFormer.py","file_url":"https://github.com/BUAABIGSCity/PDFormer/blob/HEAD/libcity/model/traffic_flow_prediction/PDFormer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"77819d970a28b38d","mcp_get_code":{"code_sha256":"77819d970a28b38d"}},{"arxiv_id":"2212.08151","paper":"/paper/first-de-trend-then-attend-rethinking","title":"First De-Trend then Attend: Rethinking Attention for Time-Series Forecasting","date":"2022-12-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BeBeYourLove/TDformer","path":"model/TDformer.py","file_url":"https://github.com/BeBeYourLove/TDformer/blob/HEAD/model/TDformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a06a4f88ba660a18","mcp_get_code":{"code_sha256":"a06a4f88ba660a18"}},{"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":"7d1582338e324271","mcp_get_code":{"code_sha256":"7d1582338e324271"}},{"arxiv_id":"2106.13008","paper":"/paper/autoformer-decomposition-transformers-with","title":"Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting","date":"2021-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thuml/autoformer","path":"models/Autoformer.py","file_url":"https://github.com/thuml/autoformer/blob/HEAD/models/Autoformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7c956e353b5b9e7c","mcp_get_code":{"code_sha256":"7c956e353b5b9e7c"}},{"arxiv_id":"2012.07436","paper":"/paper/informer-beyond-efficient-transformer-for","title":"Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting","date":"2020-12-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"martinwhl/Informer-PyTorch-Lightning","path":"models/informer/model.py","file_url":"https://github.com/martinwhl/Informer-PyTorch-Lightning/blob/HEAD/models/informer/model.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":"b27ba004293a09c9","mcp_get_code":{"code_sha256":"b27ba004293a09c9"}},{"arxiv_id":"2012.07436","paper":"/paper/informer-beyond-efficient-transformer-for","title":"Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting","date":"2020-12-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"larsbentsen/fftransformer","path":"models/Informer.py","file_url":"https://github.com/larsbentsen/fftransformer/blob/HEAD/models/Informer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5757cd5e31be6f96","mcp_get_code":{"code_sha256":"5757cd5e31be6f96"}},{"arxiv_id":"2012.07436","paper":"/paper/informer-beyond-efficient-transformer-for","title":"Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting","date":"2020-12-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AndrzejMiskow/TradeAI","path":"prediction_service/transformers/models.py","file_url":"https://github.com/AndrzejMiskow/TradeAI/blob/HEAD/prediction_service/transformers/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ffff571f678f5301","mcp_get_code":{"code_sha256":"ffff571f678f5301"}},{"arxiv_id":"2012.07436","paper":"/paper/informer-beyond-efficient-transformer-for","title":"Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting","date":"2020-12-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tianhai123/Informer-Tensorflow","path":"models/model.py","file_url":"https://github.com/tianhai123/Informer-Tensorflow/blob/HEAD/models/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":"db188ee2de158d14","mcp_get_code":{"code_sha256":"db188ee2de158d14"}},{"arxiv_id":"2012.07436","paper":"/paper/informer-beyond-efficient-transformer-for","title":"Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting","date":"2020-12-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhouhaoyi/Informer2020","path":"models/model.py","file_url":"https://github.com/zhouhaoyi/Informer2020/blob/HEAD/models/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1f7e24f214af5f8f","mcp_get_code":{"code_sha256":"1f7e24f214af5f8f"}},{"arxiv_id":"2004.05150","paper":"/paper/longformer-the-long-document-transformer","title":"Longformer: The Long-Document Transformer","date":"2020-04-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AIResearchHub/transformergallery","path":"transformer/longformer.py","file_url":"https://github.com/AIResearchHub/transformergallery/blob/HEAD/transformer/longformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0840d53a3e87bbd0","mcp_get_code":{"code_sha256":"0840d53a3e87bbd0"}},{"arxiv_id":"1909.11942","paper":"/paper/albert-a-lite-bert-for-self-supervised","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","date":"2019-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xinyooo/ALBERT4Rec","path":"models/albert_modules/albert.py","file_url":"https://github.com/xinyooo/ALBERT4Rec/blob/HEAD/models/albert_modules/albert.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"80bf93fd89246988","mcp_get_code":{"code_sha256":"80bf93fd89246988"}},{"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":"fanchenyou/transformer-study","path":"transformer_bert_from_scratch_5.py","file_url":"https://github.com/fanchenyou/transformer-study/blob/HEAD/transformer_bert_from_scratch_5.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6ac09cf3d33d9991","mcp_get_code":{"code_sha256":"6ac09cf3d33d9991"}},{"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":"codertimo/BERT-pytorch","path":"bert_pytorch/model/bert.py","file_url":"https://github.com/codertimo/BERT-pytorch/blob/HEAD/bert_pytorch/model/bert.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":"5f83a220fada640e","mcp_get_code":{"code_sha256":"5f83a220fada640e"}},{"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":"Linar23/Research_work","path":"nn/embedding/bert.py","file_url":"https://github.com/Linar23/Research_work/blob/HEAD/nn/embedding/bert.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"19ed76f032cfa56a","mcp_get_code":{"code_sha256":"19ed76f032cfa56a"}},{"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":"re-search/DocProduct","path":"keras_bert/bert.py","file_url":"https://github.com/re-search/DocProduct/blob/HEAD/keras_bert/bert.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dfc55eabce3cbf08","mcp_get_code":{"code_sha256":"dfc55eabce3cbf08"}}]}