Home › Code › CausalSelfAttention

CausalSelfAttention

Syntologyentry name in harvested coderead from the graph 2026-09-24

CausalSelfAttention appears in the code Syntology harvested for 28 papers, as 32 distinct code bodies found in 32 places (a place is one code body under one paper). At least one of them ran in 23 of the papers; 5 of the code bodies carry a behaviour fingerprint.

What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named CausalSelfAttention do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

Syntology ran 27 of the 32 distinct code bodies named CausalSelfAttention; 5 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
0ran · our draft was wrong
0ran · fixture could not drive it
27ran
5unverified
5fingerprinted

Licence is a property of each copy, so it is counted per place: 14 of the 32 places are pointer only (Syntology does not serve that copy's text). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.

“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page.

Papers

28 papers shown of 28, newest first; 32 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive, and the graph's for 7 papers added by Syntology. Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's code_sha256, Syntology's identity for that exact code: an agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

PaperDateFileStatus SyntologyLicence
Gated Recurrent Transformers: Expressive Depth through Recurrent Modulation added by Syntology 2026-08 (from id) Amr-Hegazy1/gated-recurrent-transformer/model.py cf67a1a0d7a92283 ran · metamorphic tier: deterministic no licence file found · pointer only
How to Scale Mixture-of-Experts: From µP to the Maximally Scale-Stable Parameterization added by Syntology 2026-05 (from id) vankadara-lab/mssp-moe/transformer-moe-experiments/model.py 79206b63d6c2a4cc ran MIT (permissive)
Toward Consistent World Models with Multi-Token Prediction and Latent Semantic Enhancement added by Syntology 2026-04 (from id) QiminZhong/LSE-MTP/model.py 783559fa04a5409b ran no licence file found · pointer only
SpinGQE: A generative quantum eigensolver for spin Hamiltonians added by Syntology 2026-03 (from id) Mindbeam-AI/SpinGQE/SpinGQE.py 768cae7bf6f49689 ran no licence file found · pointer only
Emergency Preemption Without Online Exploration: A Decision Transformer Approach added by Syntology 2026-03 (from id) AnthonySu/decision-transformer-traffic/src/models/madt.py 6d7951efe561a3b4 ran · metamorphic tier: deterministic no licence file found · pointer only
HiMaCon: Discovering Hierarchical Manipulation Concepts from Unlabeled Multi-Modal Data added by Syntology 2025-10 (from id) zrllrz/HiMaCon/src/hminfocon.py af5af5f52454b307 ran Apache-2.0 (permissive)
Language Model Based Text-to-Audio Generation: Anti-Causally Aligned Collaborative Residual Transformers added by Syntology 2025-10 (from id) wjc2830/Siren/src/siren/model.py 0f22591f0eeeaeb3 unverified no licence file found · pointer only
Any-Order GPT as Masked Diffusion Model: Decoupling Formulation and Architecture 24 Jun 2025 scxue/AO-GPT-MDM/model_AOGPT_AdaLN6_NoRep_cond_128_trunc_qknorm.py 311dd4150ecf301e ran no licence file found · pointer only
Generative Auto-Bidding with Value-Guided Explorations 20 Apr 2025 applied-machine-learning-lab/gave/code/bidding_train_env/baseline/dt/dt.py e1d87efc6af581e3 ran no licence file found · pointer only
Towards Learning High-Precision Least Squares Algorithms with Sequence Models 15 Mar 2025 HazyResearch/precision-ls/src/models/gpt2.py 099feb2cb11280c5 ran MIT (permissive)
Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing 25 Nov 2024 songweige/TATS/tats/tats_transformer.py 0dcc3d2b5989bb48 ran fingerprinted MIT (permissive)
From Text to Pose to Image: Improving Diffusion Model Control and Quality 19 Nov 2024 clement-bonnet/text-to-pose/t2p/model.py 023c96154955c6a3 ran · metamorphic tier: deterministic MIT (permissive)
Progressive Pretext Task Learning for Human Trajectory Prediction 16 Jul 2024 iSEE-Laboratory/PPT/models/model.py 545a9e074c969fcb ran MIT (permissive)
Attention with Markov: A Framework for Principled Analysis of Transformers via Markov Chains 6 Feb 2024 bond1995/markov/Markov-LLM-k/src/models/base.py 19f2a8bc1fab2872 ran no licence file found · pointer only
De novo Drug Design using Reinforcement Learning with Multiple GPT Agents 21 Dec 2023 hxyfighter/molrl-mgpt/codes/model.py 58787d8bc93d2270 ran · metamorphic tier: deterministic no licence file found · pointer only
TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting 8 Oct 2023 liaoyuhua/tempo-pytorch/src/model.py 78c68ccc3b7915e0 unverified MIT (permissive)
Learning to Solve Constraint Satisfaction Problems with Recurrent Transformer 10 Jul 2023 azreasoners/recurrent_transformer/mingpt/model.py db4f6eb0540de0f8 ran MIT (permissive)
Think Before You Act: Decision Transformers with Working Memory 24 May 2023 luciferkonn/dt_mem/src/model.py c59ed427653b94b7 unverified MIT (permissive)
Explaining RL Decisions with Trajectories 6 May 2023 karim-abdel/fact/Breakout/mk_patch_decision_transformer_atari.py 690f3d0fe57d14fd ran fingerprinted no licence file found · pointer only
LLaMA: Open and Efficient Foundation Language Models 27 Feb 2023 Lightning-AI/lit-llama/lit_llama/model.py 5a58d3796ebd39f1 unverified Apache-2.0 (permissive)
One Fits All:Power General Time Series Analysis by Pretrained LM 23 Feb 2023 liaoyuhua/GPT-TS/src/model.py ad66bcf4514af931 ran no licence file found · pointer only
Generative Pretraining for Black-Box Optimization 22 Jun 2022 siddarthk97/bonet/mingpt/model_discrete.py 774a4c768efc371a ran no licence file found · pointer only
Bootstrapped Transformer for Offline Reinforcement Learning 17 Jun 2022 jannerm/trajectory-transformer/trajectory/models/transformers.py 855bb84cf5832f74 ran · metamorphic tier: invariant MIT (permissive)
Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding 2 Mar 2022 DQiaole/ZITS_inpainting/src/models/TSR_model.py 374b0040c780395d ran fingerprinted Apache-2.0 (permissive)
Representing Long-Range Context for Graph Neural Networks with Global Attention 21 Jan 2022 ucbrise/graphtrans/models/gnn_transformer.py 54f4034695672c97 ran Apache-2.0 (permissive)
Decision Transformer: Reinforcement Learning via Sequence Modeling 2 Jun 2021 yun-kwak/decision-transformer-jax/dt_jax/gpt.py 143914639aea2cb9 unverified MIT (permissive)
High-Fidelity Pluralistic Image Completion with Transformers 25 Mar 2021 karynaur/High-Fidelity-Pluralistic-ICT/transformer/model.py fb2f67ff573fae6f ran fingerprinted no licence file found · pointer only
High-Fidelity Pluralistic Image Completion with Transformers 25 Mar 2021 raywzy/ICT/Transformer/models/model.py 4e88ff3b87c736b3 ran fingerprinted no licence file found · pointer only
Attention Is All You Need 12 Jun 2017 hannibal046/nanorwkv/modeling_gpt.py ade15669c2944986 ran · metamorphic tier: deterministic MIT (permissive)
Attention Is All You Need 12 Jun 2017 karpathy/makemore/makemore.py 1891051ae1596526 ran MIT (permissive)
Attention Is All You Need 12 Jun 2017 karpathy/minGPT/mingpt/model.py 78af90d15381d27e ran MIT (permissive)
Attention Is All You Need 12 Jun 2017 akanyaani/minGPTF/mingptf/model.py 39042b872a709fbe ran MIT (permissive)

This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the harvest. "Pointer only" means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections