Home › Code › BaseTrainer

BaseTrainer

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

BaseTrainer appears in the code Syntology harvested for 16 papers, as 16 distinct code bodies found in 16 places (a place is one code body under one paper). At least one of them ran in 7 of the papers; 0 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 BaseTrainer 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 7 of the 16 distinct code bodies named BaseTrainer; 9 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
7ran
9unverified
0fingerprinted

Licence is a property of each copy, so it is counted per place: 7 of the 16 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; 16 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 4 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
Neural Parameter Calibration for Finite-State Mean Field Games added by Syntology 2026-06 (from id) KachmanLab/MFGParameterCalibration/src/calibration/BaseTrainer.py 18835f28278eb0a9 ran MIT (permissive)
Deep Learning as Neural Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learning added by Syntology 2026-05 (from id) IdePHICS/Neural-LoFi-Theory/src/train_hierarchically/training/kernel_spectral.py 5241b31e984ec04a unverified MIT (permissive)
SAFE: Stable Alignment Finetuning with Entropy-Aware Predictive Control for RLHF Combining Double Soft-Min Critics with Adaptive KL Thresholding added by Syntology 2026-02 (from id) ryyzn9/SAFE/safe/trainers/safe.py 5e6545e6f0ce1a83 unverified no licence file found · pointer only
Private Zeroth-Order Optimization with Public Data added by Syntology 2025-11 (from id) xuchengong/pazo/experiments/pazo-p.py bd6d028a5f2b25c7 unverified MIT (permissive)
Training Hamiltonian neural networks without backpropagation 26 Nov 2024 AlphaGergedan/Sampling-HNNs/src/trainer/sampler.py e8879005ea7b17a5 unverified MIT (permissive)
Diffusion Bridge AutoEncoders for Unsupervised Representation Learning 27 May 2024 ckczzj/PDAE/trainer/train_representation_learning.py 59d0f7c7bd4e6720 unverified no licence file found · pointer only
Selective Focus: Investigating Semantics Sensitivity in Post-training Quantization for Lane Detection 10 May 2024 PannenetsF/SelectiveFocus/pad/utils/runners/lane_det_quant_trainer.py ddbb781402a89bb4 unverified no licence file found · pointer only
Tangent Model Composition for Ensembling and Continual Fine-tuning 16 Jul 2023 tianyu139/tangent-model-composition/tangent_trainer.py f090911c87dea79d ran MIT (permissive)
Unsupervised Representation Learning from Pre-trained Diffusion Probabilistic Models 26 Dec 2022 yue-zhongqi/diti/trainer/representation_learning_trainer.py 4169604fb1fae5cb unverified no licence file found · pointer only
Differentially Private Adaptive Optimization with Delayed Preconditioners 1 Dec 2022 kenziyuliu/dp2/trainers/dp2_adagrad.py dca6afaa2e23a3be unverified Apache-2.0 (permissive)
Towards Sequence-Level Training for Visual Tracking 11 Aug 2022 byminji/SLTtrack/ltr/trainers/slt_transt_trainer.py b1a9819a687a220f ran GPL-3.0 (copyleft) · pointer only
Controlling Conditional Language Models without Catastrophic Forgetting 1 Dec 2021 naver/gdc/cdpg/cdpg/pointwise_gdc.py 4e11394481ba47b3 ran licence not identified · pointer only
Searching for an Effective Defender: Benchmarking Defense against Adversarial Word Substitution 29 Aug 2021 RockyLzy/TextDefender/trainer/ascc.py 875a0b28ba40c0a5 ran MIT (permissive)
Semantically Coherent Out-of-Distribution Detection 26 Aug 2021 Jingkang50/ICCV21_SCOOD/scood/trainers/udg_trainer.py ca74574f5cf44300 ran MIT (permissive)
MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptation 25 Mar 2021 microsoft/UDA/trainer/da/toalign.py e4d8b30d56dbb7f3 unverified MIT (permissive)
A Distributional Approach to Controlled Text Generation 21 Dec 2020 naver/gdc/dpg/gdc/gdc/gdc.py 825da61438abc2b7 ran licence not identified · pointer only

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