Home › Code › grad

grad

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

grad appears in the code Syntology harvested for 23 papers, as 20 distinct code bodies found in 25 places (a place is one code body under one paper). At least one of them ran in 8 of the papers; 4 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 grad 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 9 of the 20 distinct code bodies named grad; 11 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
1ran · violated contract
3ran · our draft was wrong
2ran · fixture could not drive it
3ran
11unverified
4fingerprinted

Licence is a property of each copy, so it is counted per place: 6 of the 25 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

23 papers shown of 23, newest first; 25 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. 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
Zeroth-Order Optimization Finds Flat Minima 5 Jun 2025 Liang137/FlatZero/test_func/run_toy.py f05d08ea970e9e2f unverified MIT (permissive)
Self-Distilled Depth Refinement with Noisy Poisson Fusion 26 Sep 2024 lijia7/sddr/utils/loss.py fc7d07b4f4b62c14 ran fingerprinted no licence file found · pointer only
Reinforcement Learning from Delayed Observations via World Models 18 Mar 2024 indylab/delayeddreamer/dreamerv3/ninjax.py 1ad869363216c281 unverified MIT (permissive)
Mastering Memory Tasks with World Models 7 Mar 2024 chandar-lab/Recall2Imagine/recall2imagine/ninjax.py 1ad869363216c281 unverified MIT (permissive)
How to Make the Gradients Small Privately: Improved Rates for Differentially Private Non-Convex Optimization 17 Feb 2024 lowya/how-to-make-the-gradients-small-privately/mod_smallgradients_trig_icml24_V3.py 5d5c9ec5efaf2f23 ran fingerprinted CC0-1.0 (permissive)
HarmonyDream: Task Harmonization Inside World Models 30 Sep 2023 thuml/HarmonyDream/dreamerv3-jax/dreamerv3/ninjax.py 1ad869363216c281 unverified MIT (permissive)
SafeDreamer: Safe Reinforcement Learning with World Models 14 Jul 2023 PKU-Alignment/SafeDreamer/SafeDreamer/ninjax.py 1ad869363216c281 unverified Apache-2.0 (permissive)
Informed POMDP: Leveraging Additional Information in Model-Based RL 20 Jun 2023 glambrechts/informed-dreamer/dreamerv3/ninjax.py 1ad869363216c281 unverified MIT (permissive)
DiffPack: A Torsional Diffusion Model for Autoregressive Protein Side-Chain Packing 1 Jun 2023 DeepGraphLearning/DiffPack/diffpack/schedule.py 35d120ffc51b9534 unverified MIT (permissive)
Communication Efficient Distributed Newton Method with Fast Convergence Rates 2023-05 (from id) 7ccliu/c2eden/a9a.convex.py 92fe91e9375f75e3 ran · our draft was wrong no licence file found · pointer only
Communication Efficient Distributed Newton Method with Fast Convergence Rates 2023-05 (from id) 7ccliu/c2eden/a9a.nonconvex.py 756164c90fc0bde4 ran · our draft was wrong no licence file found · pointer only
Video Prediction Models as Rewards for Reinforcement Learning 23 May 2023 Alescontrela/viper_rl/viper_rl/dreamerv3/ninjax.py afd5fe78d3d65a81 unverified MIT (permissive)
Safe Reinforcement Learning via Probabilistic Logic Shields 6 Mar 2023 sacktock/ambs/dreamerV3-base/ninjax.py 1ad869363216c281 unverified MIT (permissive)
Low-Precision Stochastic Gradient Langevin Dynamics 20 Jun 2022 ruqizhang/low-precision-sgld/gaussian/gaussian.py 0f4ae257ee7047a9 ran · violated contract fingerprinted no licence file found · pointer only
Kantorovich Strikes Back! Wasserstein GANs are not Optimal Transport? 15 Jun 2022 justkolesov/Wasserstein1Benchmark/src/utils.py e3248168eb0e100b unverified MIT (permissive)
Explainable Artificial Intelligence for Bayesian Neural Networks: Towards trustworthy predictions of ocean dynamics 30 Apr 2022 maikejulie/DNN4Cli/THOR/BayesianApproach/shap_ensemble.py 99af607d774eb893 unverified MIT (permissive)
Perturb-and-max-product: Sampling and learning in discrete energy-based models 3 Nov 2021 vicariousinc/perturb_and_max_product/pmap/rbm_modeling.py ba817fe401de23e8 unverified MIT (permissive)
Stochastic Optimization under Distributional Drift 16 Aug 2021 joshuacutler/TimeDriftExperiments/LogisticRegression/LR.py e106aedb0c789b9b ran · fixture could not drive it no licence file found · pointer only
AR-DAE: Towards Unbiased Neural Entropy Gradient Estimation 9 Jun 2020 lim0606/pytorch-ardae-rl/models/graddae/mlp.py 6481d3c86e5d4089 ran · our draft was wrong no licence file found · pointer only
Meta-Learning with Warped Gradient Descent 30 Aug 2019 flennerhag/warpgrad/src/warpgrad/warpgrad/utils.py 9031a2aac8c79c7a unverified Apache-2.0 (permissive)
Beyond Alternating Updates for Matrix Factorization with Inertial Bregman Proximal Gradient Algorithms 22 May 2019 mmahesh/cocain-bpg-matrix-factorization/my_functions.py 7de0fb631a5ab4ea unverified BSD-3-Clause (permissive)
Convex-Concave Backtracking for Inertial Bregman Proximal Gradient Algorithms in Non-Convex Optimization 6 Apr 2019 mmahesh/cocain-bpg-escapes-spurious-stationary-points/my_functions.py 64e23227316b67fc ran · fixture could not drive it fingerprinted BSD-3-Clause (permissive)
Convex-Concave Backtracking for Inertial Bregman Proximal Gradient Algorithms in Non-Convex Optimization 6 Apr 2019 mmahesh/cocain-bpg-phase-retrieval/my_functions.py 1b20d466ab5027ec unverified BSD-3-Clause (permissive)
Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data 18 Jan 2019 cics-nd/pde-surrogate/models/darcy.py bd3f3e9983573cd2 unverified MIT (permissive)
DARTS: Differentiable Architecture Search 24 Jun 2018 leopard-ai/betty/betty/hypergradient/darts.py 28b087ea0aa9ba9d ran Apache-2.0 (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