grad_scale
grad_scale appears in the code Syntology harvested for 16 papers, as 7 distinct code bodies found in 17 places (a place is one code body under one paper). At least one of them ran in 14 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 grad_scale 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 5 of the 7 distinct code bodies named grad_scale; 2 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:
Licence is a property of each copy, so it is counted per place: 12 of the 17 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
16 papers shown of 16, newest first; 17 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; 1 papers have no page here and are shown by arXiv id only. 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.
| Paper | Date | File | Status Syntology | Licence |
|---|---|---|---|---|
| Quantized Spike-driven Transformer | 23 Jan 2025 | identical code first harvested elsewhere d75564df9359ef7b |
ran · honoured contract fingerprinted | licence of this copy not recorded |
| TaQ-DiT: Time-aware Quantization for Diffusion Transformers | 21 Nov 2024 | 6xy-liu/Taq-DiT/quant/quantization/fake_quant.py 043c3be8a95e065c |
ran · our draft was wrong fingerprinted | no licence file found · pointer only |
| Integer-Valued Training and Spike-Driven Inference Spiking Neural Network for High-performance and Energy-efficient Object Detection | 30 Jul 2024 | biclab/spikeyolo/SpikeYOLO_for_Gen1/_quan_base_plus.py d75564df9359ef7b |
ran · honoured contract fingerprinted | AGPL-3.0 (copyleft) · pointer only |
| SpikeZIP-TF: Conversion is All You Need for Transformer-based SNN | 5 Jun 2024 | Intelligent-Computing-Research-Group/SpikeZIP-TF/spike_quan_layer.py a488bae52f1bfd5d |
ran · honoured contract fingerprinted | no licence file found · pointer only |
| BinaryDM: Accurate Weight Binarization for Efficient Diffusion Models | 8 Apr 2024 | xingyu-zheng/binarydm/ours_util.py d75564df9359ef7b |
ran · honoured contract fingerprinted | no licence file found · pointer only |
| GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting | 13 Mar 2024 | Xinjie-Q/GaussianImage/quantize.py a291c2776caf3a35 |
ran fingerprinted | MIT (permissive) |
| Boosting Neural Representations for Videos with a Conditional Decoder | 28 Feb 2024 | Xinjie-Q/Boosting-NeRV/lib/transform_ops.py a291c2776caf3a35 |
ran fingerprinted | Apache-2.0 (permissive) |
| EQ-Net: Elastic Quantization Neural Networks | 15 Aug 2023 | xuke225/EQ-Net/module/base_lsq.py f287df11a2dad0bc |
ran fingerprinted | no licence file found · pointer only |
| Oscillation-free Quantization for Low-bit Vision Transformers | 4 Feb 2023 | identical code first harvested elsewhere a488bae52f1bfd5d |
ran · honoured contract fingerprinted | licence of this copy not recorded |
| Mixed-Precision Neural Network Quantization via Learned Layer-wise Importance | 16 Mar 2022 | identical code first harvested elsewhere a488bae52f1bfd5d |
ran · honoured contract fingerprinted | licence of this copy not recorded |
| Q-ViT: Fully Differentiable Quantization for Vision Transformer | 19 Jan 2022 | zhexinli/Q-ViT-DeiT/quantization/lsq_layer.py d75564df9359ef7b |
ran · honoured contract fingerprinted | Apache-2.0 recorded; this copy not marked cleared · pointer only |
| Denoising Diffusion Probabilistic Models | 19 Jun 2020 | lvyufeng/denoising-diffusion-mindspore/ddm/amp.py 17220aac4f6143a3 |
unverified | MIT (permissive) |
| LSQ+: Improving low-bit quantization through learnable offsets and better initialization | 20 Apr 2020 | identical code first harvested elsewhere a488bae52f1bfd5d |
ran · honoured contract fingerprinted | licence of this copy not recorded |
| Modeling Tabular data using Conditional GAN | 1 Jul 2019 | lvyufeng/CTGAN-MindSpore/ctgan/amp.py a80d09bcb2ebc36f |
unverified | MIT (permissive) |
| Learned Step Size Quantization | 21 Feb 2019 | jiyoonkm/columnquant/LSQ.py a488bae52f1bfd5d |
ran · honoured contract fingerprinted | no licence file found · pointer only |
| Learned Step Size Quantization | 21 Feb 2019 | hustzxd/LSQuantization/lsq.py d75564df9359ef7b |
ran · honoured contract fingerprinted | no licence file found · pointer only |
| arXiv:aaai_28109 | YanjingLi0202/Bi-ViT/_binary_base_plus.py d75564df9359ef7b |
ran · honoured contract fingerprinted | 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