{"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/rotaryembedding","entry":"RotaryEmbedding","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":27,"n_papers_ran":24,"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":32,"n_samples_ran":29,"n_samples_fingerprinted":9,"n_places":32,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":29,"unverified":3},"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":"2607.26504","paper":"/paper/arxiv-2607-26504","title":"From Interface to Inference: Eliciting Any-Order Inference from Any-Order Models","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"SeunggeunKimkr/genuine-any-order","path":"LatentMDM/model/latent_mdm.py","file_url":"https://github.com/SeunggeunKimkr/genuine-any-order/blob/HEAD/LatentMDM/model/latent_mdm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"eafa1d1973ed3a8a","mcp_get_code":{"code_sha256":"eafa1d1973ed3a8a"}},{"arxiv_id":"2606.21911","paper":"/paper/arxiv-2606-21911","title":"The Pitfall of Scaling Up: Uncovering and Mitigating Popularity Bias Amplification in Scaling Transformer-based Recommenders","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"Tiny-Snow/GenRec","path":"src/genrec/models/model_seqrec/sasrec_sprint.py","file_url":"https://github.com/Tiny-Snow/GenRec/blob/HEAD/src/genrec/models/model_seqrec/sasrec_sprint.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"75ded7213e219c95","mcp_get_code":{"code_sha256":"75ded7213e219c95"}},{"arxiv_id":"2606.11860","paper":"/paper/arxiv-2606-11860","title":"REPAIR: Predictive Self-Supervised Representation Learning in Chess","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"Artificial-Chrisi/RePAIR","path":"networks.py","file_url":"https://github.com/Artificial-Chrisi/RePAIR/blob/HEAD/networks.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0d1c3f56a4f58883","mcp_get_code":{"code_sha256":"0d1c3f56a4f58883"}},{"arxiv_id":"2606.01495","paper":"/paper/arxiv-2606-01495","title":"CART: Context-Anchored Recurrent Transformer * A Parameter-Efficient Architecture with Learned Stability","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"ccapps42/CART","path":"model/cart.py","file_url":"https://github.com/ccapps42/CART/blob/HEAD/model/cart.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"97fbea8bac3c5277","mcp_get_code":{"code_sha256":"97fbea8bac3c5277"}},{"arxiv_id":"2605.17811","paper":"/paper/arxiv-2605-17811","title":"One Model, Two Roles: Emergent Specialization in a Shared Recurrent Transformer","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"juchengshen/air","path":"models/air/air_1net_L2x_H2x_input_token_prepend.py","file_url":"https://github.com/juchengshen/air/blob/HEAD/models/air/air_1net_L2x_H2x_input_token_prepend.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":"ecf65cb1949cf62e","mcp_get_code":{"code_sha256":"ecf65cb1949cf62e"}},{"arxiv_id":"2604.21649","paper":"/paper/arxiv-2604-21649","title":"GS-Quant: Granular Semantic and Generative Structural Quantization for Knowledge Graph Completion","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"mikumifa/GS-Quant","path":"codebook/rqvae.py","file_url":"https://github.com/mikumifa/GS-Quant/blob/HEAD/codebook/rqvae.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":"0affb407d05e5940","mcp_get_code":{"code_sha256":"0affb407d05e5940"}},{"arxiv_id":"2603.11950","paper":"/paper/arxiv-2603-11950","title":"Learning Transferable Sensor Models via Language-Informed Pretraining","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"yuc0805/SLIP","path":"modeling_slip.py","file_url":"https://github.com/yuc0805/SLIP/blob/HEAD/modeling_slip.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9e771963d3668d07","mcp_get_code":{"code_sha256":"9e771963d3668d07"}},{"arxiv_id":"2602.04680","paper":"/paper/arxiv-2602-04680","title":"Audio ControlNet for Fine-Grained Audio Generation and Editing","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"haidog-yaqub/EzAudio","path":"src/models/controlnet.py","file_url":"https://github.com/haidog-yaqub/EzAudio/blob/HEAD/src/models/controlnet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4edb80e5146622da","mcp_get_code":{"code_sha256":"4edb80e5146622da"}},{"arxiv_id":"2601.21681","paper":"/paper/arxiv-2601-21681","title":"LLM4Fluid: Large Language Models as Generalizable Neural Solvers for Fluid Dynamics","date":"2026-01-29","month_inferred_from_arxiv_id":null,"title_source":"syntology","repo":"BaratiLab/FactFormer","path":"libs/factorization_module.py","file_url":"https://github.com/BaratiLab/FactFormer/blob/HEAD/libs/factorization_module.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5e01bb00ee32827d","mcp_get_code":{"code_sha256":"5e01bb00ee32827d"}},{"arxiv_id":"2509.24332","paper":"/paper/arxiv-2509-24332","title":"Towards Generalizable PDE Dynamics Forecasting via Physics-Guided Invariant Learning","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"LSY-Cython/iMOOE","path":"models/framework.py","file_url":"https://github.com/LSY-Cython/iMOOE/blob/HEAD/models/framework.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"be50842198a872a7","mcp_get_code":{"code_sha256":"be50842198a872a7"}},{"arxiv_id":"2506.10351","paper":"/paper/physiowave-a-multi-scale-wavelet-transformer","title":"PhysioWave: A Multi-Scale Wavelet-Transformer for Physiological Signal Representation","date":"2025-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ForeverBlue816/PhysioWave","path":"model.py","file_url":"https://github.com/ForeverBlue816/PhysioWave/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a85798cf89cbf21d","mcp_get_code":{"code_sha256":"a85798cf89cbf21d"}},{"arxiv_id":"2503.18938","paper":"/paper/adaworld-learning-adaptable-world-models-with","title":"AdaWorld: Learning Adaptable World Models with Latent Actions","date":"2025-03-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"little-podi/adaworld","path":"lam/lam/modules/lam.py","file_url":"https://github.com/little-podi/adaworld/blob/HEAD/lam/lam/modules/lam.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":"8ad0a69c31d2ece7","mcp_get_code":{"code_sha256":"8ad0a69c31d2ece7"}},{"arxiv_id":"2502.10425","paper":"/paper/neuron-platonic-intrinsic-representation-from","title":"Neuron Platonic Intrinsic Representation From Dynamics Using Contrastive Learning","date":"2025-02-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ww20hust/NeurPIR","path":"src/models/encoder.py","file_url":"https://github.com/ww20hust/NeurPIR/blob/HEAD/src/models/encoder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d86a8451f50566b4","mcp_get_code":{"code_sha256":"d86a8451f50566b4"}},{"arxiv_id":"2411.03859","paper":"/paper/unitraj-universal-human-trajectory-modeling","title":"UniTraj: Learning a Universal Trajectory Foundation Model from Billion-Scale Worldwide Traces","date":"2024-11-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Yasoz/UniTraj","path":"utils/unitraj.py","file_url":"https://github.com/Yasoz/UniTraj/blob/HEAD/utils/unitraj.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":"d49696560619a2d2","mcp_get_code":{"code_sha256":"d49696560619a2d2"}},{"arxiv_id":"2410.11842","paper":"/paper/moh-multi-head-attention-as-mixture-of-head","title":"MoH: Multi-Head Attention as Mixture-of-Head Attention","date":"2024-10-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"skyworkai/moe-plus-plus","path":"MoE++/modeling_moe_plus_plus.py","file_url":"https://github.com/skyworkai/moe-plus-plus/blob/HEAD/MoE%2B%2B/modeling_moe_plus_plus.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":"4390a52a532857aa","mcp_get_code":{"code_sha256":"4390a52a532857aa"}},{"arxiv_id":"2410.10254","paper":"/paper/lolcats-on-low-rank-linearizing-of-large","title":"LoLCATs: On Low-Rank Linearizing of Large Language Models","date":"2024-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hazyresearch/lolcats","path":"src/model/linear_attention/linear_window_attention_sw_linear.py","file_url":"https://github.com/hazyresearch/lolcats/blob/HEAD/src/model/linear_attention/linear_window_attention_sw_linear.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":"c2be9851321e656a","mcp_get_code":{"code_sha256":"c2be9851321e656a"}},{"arxiv_id":"2409.12191","paper":"/paper/qwen2-vl-enhancing-vision-language-model-s","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","date":"2024-09-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"baichuan-inc/Baichuan-Omni-1.5","path":"baichuan-omni/model/modeling_omni.py","file_url":"https://github.com/baichuan-inc/Baichuan-Omni-1.5/blob/HEAD/baichuan-omni/model/modeling_omni.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":"7bc2a2784aabedc7","mcp_get_code":{"code_sha256":"7bc2a2784aabedc7"}},{"arxiv_id":"2405.20671","paper":"/paper/position-coupling-leveraging-task-structure","title":"Position Coupling: Improving Length Generalization of Arithmetic Transformers Using Task Structure","date":"2024-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hanseuljo/position-coupling","path":"src/model/modeling/positional_embeddings.py","file_url":"https://github.com/hanseuljo/position-coupling/blob/HEAD/src/model/modeling/positional_embeddings.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"832341bae4409ffe","mcp_get_code":{"code_sha256":"832341bae4409ffe"}},{"arxiv_id":"2402.15220","paper":"/paper/chunkattention-efficient-self-attention-with","title":"ChunkAttention: Efficient Self-Attention with Prefix-Aware KV Cache and Two-Phase Partition","date":"2024-02-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/chunk-attention","path":"src/chunk_attn/models/llama_hf/modeling_llama.py","file_url":"https://github.com/microsoft/chunk-attention/blob/HEAD/src/chunk_attn/models/llama_hf/modeling_llama.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"de4dc6b3c9f22350","mcp_get_code":{"code_sha256":"de4dc6b3c9f22350"}},{"arxiv_id":"2302.13971","paper":"/paper/llama-open-and-efficient-foundation-language-1","title":"LLaMA: Open and Efficient Foundation Language Models","date":"2023-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"akanyaani/miniLLAMA","path":"model.py","file_url":"https://github.com/akanyaani/miniLLAMA/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fd513b4604a55972","mcp_get_code":{"code_sha256":"fd513b4604a55972"}},{"arxiv_id":"2204.02311","paper":"/paper/palm-scaling-language-modeling-with-pathways-1","title":"PaLM: Scaling Language Modeling with Pathways","date":"2022-04-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"conceptofmind/PaLM-flax","path":"palm_flax/palm_flax.py","file_url":"https://github.com/conceptofmind/PaLM-flax/blob/HEAD/palm_flax/palm_flax.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c327a17241c2969e","mcp_get_code":{"code_sha256":"c327a17241c2969e"}},{"arxiv_id":"2204.02311","paper":"/paper/palm-scaling-language-modeling-with-pathways-1","title":"PaLM: Scaling Language Modeling with Pathways","date":"2022-04-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/CoCa-pytorch","path":"coca_pytorch/coca_pytorch.py","file_url":"https://github.com/lucidrains/CoCa-pytorch/blob/HEAD/coca_pytorch/coca_pytorch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"231817c8d194a68b","mcp_get_code":{"code_sha256":"231817c8d194a68b"}},{"arxiv_id":"2203.07852","paper":"/paper/block-recurrent-transformers","title":"Block-Recurrent Transformers","date":"2022-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/block-recurrent-transformer-pytorch","path":"block_recurrent_transformer_pytorch/block_recurrent_transformer_pytorch.py","file_url":"https://github.com/lucidrains/block-recurrent-transformer-pytorch/blob/HEAD/block_recurrent_transformer_pytorch/block_recurrent_transformer_pytorch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c779f10c971c5655","mcp_get_code":{"code_sha256":"c779f10c971c5655"}},{"arxiv_id":"2202.07765","paper":"/paper/general-purpose-long-context-autoregressive","title":"General-purpose, long-context autoregressive modeling with Perceiver AR","date":"2022-02-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/perceiver-ar-pytorch","path":"perceiver_ar_pytorch/perceiver_ar_pytorch.py","file_url":"https://github.com/lucidrains/perceiver-ar-pytorch/blob/HEAD/perceiver_ar_pytorch/perceiver_ar_pytorch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f8c62fb6aaac766d","mcp_get_code":{"code_sha256":"f8c62fb6aaac766d"}},{"arxiv_id":"2112.04426","paper":"/paper/improving-language-models-by-retrieving-from","title":"Improving language models by retrieving from trillions of tokens","date":"2021-12-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/RETRO-pytorch","path":"retro_pytorch/retro_pytorch.py","file_url":"https://github.com/lucidrains/RETRO-pytorch/blob/HEAD/retro_pytorch/retro_pytorch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9fbc41d552de00c6","mcp_get_code":{"code_sha256":"9fbc41d552de00c6"}},{"arxiv_id":"2104.09864","paper":"/paper/roformer-enhanced-transformer-with-rotary","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","date":"2021-04-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AryaAftab/rotary-embedding-tensorflow","path":"rotary_embedding_tensorflow/rotary_embedding_tensorflow.py","file_url":"https://github.com/AryaAftab/rotary-embedding-tensorflow/blob/HEAD/rotary_embedding_tensorflow/rotary_embedding_tensorflow.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0fe09c685e79fefc","mcp_get_code":{"code_sha256":"0fe09c685e79fefc"}},{"arxiv_id":"2104.09864","paper":"/paper/roformer-enhanced-transformer-with-rotary","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","date":"2021-04-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"varungumma/fairseq","path":"fairseq/modules/rotary_embedding.py","file_url":"https://github.com/varungumma/fairseq/blob/HEAD/fairseq/modules/rotary_embedding.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dbb6d6a0d27a25f4","mcp_get_code":{"code_sha256":"dbb6d6a0d27a25f4"}},{"arxiv_id":"2104.09864","paper":"/paper/roformer-enhanced-transformer-with-rotary","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","date":"2021-04-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"airi-institute/gena_lm","path":"src/gena_lm/modeling_bert.py","file_url":"https://github.com/airi-institute/gena_lm/blob/HEAD/src/gena_lm/modeling_bert.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9a156a004cf5913c","mcp_get_code":{"code_sha256":"9a156a004cf5913c"}},{"arxiv_id":"2104.09864","paper":"/paper/roformer-enhanced-transformer-with-rotary","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","date":"2021-04-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/rotary-embedding-torch","path":"rotary_embedding_torch/rotary_embedding_torch.py","file_url":"https://github.com/lucidrains/rotary-embedding-torch/blob/HEAD/rotary_embedding_torch/rotary_embedding_torch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0a4292dfdf0c449d","mcp_get_code":{"code_sha256":"0a4292dfdf0c449d"}},{"arxiv_id":"2104.09864","paper":"/paper/roformer-enhanced-transformer-with-rotary","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","date":"2021-04-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"baichuan-inc/baichuan-7b","path":"models/modeling_baichuan.py","file_url":"https://github.com/baichuan-inc/baichuan-7b/blob/HEAD/models/modeling_baichuan.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":"d05c5eb6cdfb5b97","mcp_get_code":{"code_sha256":"d05c5eb6cdfb5b97"}},{"arxiv_id":"2103.01209","paper":"/paper/generative-adversarial-transformers","title":"Generative Adversarial Transformers","date":"2021-03-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/transganformer","path":"transganformer/transganformer.py","file_url":"https://github.com/lucidrains/transganformer/blob/HEAD/transganformer/transganformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f655a887963da4f4","mcp_get_code":{"code_sha256":"f655a887963da4f4"}},{"arxiv_id":"2102.05095","paper":"/paper/is-space-time-attention-all-you-need-for","title":"Is Space-Time Attention All You Need for Video Understanding?","date":"2021-02-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/TimeSformer-pytorch","path":"timesformer_pytorch/timesformer_pytorch.py","file_url":"https://github.com/lucidrains/TimeSformer-pytorch/blob/HEAD/timesformer_pytorch/timesformer_pytorch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4e0216fcf6abef9d","mcp_get_code":{"code_sha256":"4e0216fcf6abef9d"}}]}