Home › Code › save_checkpoint

save_checkpoint

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

save_checkpoint appears in the code Syntology harvested for 36 papers, as 31 distinct code bodies found in 37 places (a place is one code body under one paper). At least one of them ran in 5 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 save_checkpoint 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 4 of the 31 distinct code bodies named save_checkpoint; 27 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
2ran · our draft was wrong
0ran · fixture could not drive it
2ran
27unverified
0fingerprinted

Licence is a property of each copy, so it is counted per place: 20 of the 37 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

36 papers shown of 36, newest first; 37 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 6 papers added by Syntology; 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.

PaperDateFileStatus SyntologyLicence
Learning as Observable Matrix Dynamics: Diffusive Relaxations versus Phase Transitions added by Syntology 2026-06 (from id) ighalp/observable-matrix-dynamics-ml/omd/ml_fdm/io_utils.py 59b800653812f7db ran no licence file found · pointer only
Reconstructing Randomly Masked Spectra Helps DNNs Identify Discriminant Wavenumbers added by Syntology 2026-06 (from id) Chaoscendence/TeaNet/code/train_model.py e52190ad3ffc2484 unverified MIT (permissive)
MedCore: Boundary-Preserving Medical Core Pruning for MedSAM added by Syntology 2026-05 (from id) cenweizhang/MedCore/medcore_pruning/checkpoints.py ec89cd9780053c16 unverified Apache-2.0 (permissive)
When PINNs Go Wrong: Pseudo-Time Stepping Against Spurious Solutions added by Syntology 2026-04 (from id) sifanexisted/jaxpi2/jaxpi/training.py def1f0e6fabc5bbd unverified Apache-2.0 (permissive)
Hard Labels In! Rethinking the Role of Hard Labels in Mitigating Local Semantic Drift added by Syntology 2025-12 (from id) Jiacheng8/HALD/validate/train_fkd.py 9a03064558c4c3e2 unverified MIT (permissive)
GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning added by Syntology 2025-10 (from id) yiming421/inductnode/src/checkpoint_utils.py 7ec3e23a89419def unverified no licence file found · pointer only
Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement 29 Sep 2024 OPTML-Group/Unlearn-Saliency/Classification/unlearn/GA_prune.py 632b4796f64ea2f5 unverified MIT (permissive)
Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding 14 May 2024 tencent/hunyuandit/hydit/train_deepspeed_controlnet.py 02d43c51b3337304 ran licence not identified · pointer only
InfoMatch: Entropy Neural Estimation for Semi-Supervised Image Classification 17 Apr 2024 kunzhan/InfoMatch/infoMatch_STL.py 853f415fdc5443ea unverified no licence file found · pointer only
Empowering Collaborative Filtering with Principled Adversarial Contrastive Loss 28 Oct 2023 lehengthu/advinfonce/train_AdvInfoNCE.py 380a5cea5655f733 ran · our draft was wrong MIT (permissive)
Dynamic Residual Classifier for Class Incremental Learning 25 Aug 2023 chen-xw/drc-cil/models/mafdrc.py 811051c5958cdae5 unverified no licence file found · pointer only
CAME: Contrastive Automated Model Evaluation 22 Aug 2023 pengr/contrastive_autoeval/simclr.py 94a1d7b37497a828 unverified MIT (permissive)
CausalLM is not optimal for in-context learning 14 Aug 2023 google-research/causallm_icl/model_trainer.py 6f0e9bed65917eba unverified Apache-2.0 (permissive)
Confronting Ambiguity in 6D Object Pose Estimation via Score-Based Diffusion on SE(3) 25 May 2023 Ending2015a/liepose-diffusion/src/liepose/exp/testbed.py 94b060b77aaacebb unverified MIT (permissive)
Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions 15 May 2023 val-iisc/saddle-longtail/GLMC-2023/Trainer.py 909b8d6eeb4f3bb4 unverified MIT (permissive)
Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions 15 May 2023 ynu-yangpeng/GLMC/GLMC-2023/Trainer.py c5a1cf535d31085e unverified no licence file found · pointer only
Simulated Annealing in Early Layers Leads to Better Generalization 10 Apr 2023 amiiir-sarfi/seal/core.py 6fcb2d5ec5bc611b unverified no licence file found · pointer only
Invariant Collaborative Filtering to Popularity Distribution Shift 10 Feb 2023 anzhang314/invcf/main_synthetic.py 380a5cea5655f733 ran · our draft was wrong MIT (permissive)
Tailoring Molecules for Protein Pockets: a Transformer-based Generative Solution for Structured-based Drug Design 30 Aug 2022 hankerwu/tamgent/fairseq/checkpoint_utils.py e0fc19049e28e843 unverified MIT recorded; this copy not marked cleared · pointer only
When Counting Meets HMER: Counting-Aware Network for Handwritten Mathematical Expression Recognition 23 Jul 2022 LBH1024/CAN/utils.py beb2b433b3cefd2f unverified MIT (permissive)
Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation 6 Jun 2022 Jxu-Thu/DIITTO/fairseq/checkpoint_utils.py b3616a62387703cb unverified MIT recorded; this copy not marked cleared · pointer only
Contrastive Test-Time Adaptation 21 Apr 2022 DianCh/AdaContrast/target.py df95bf057b7a70cf unverified no licence file found · pointer only
Rethinking Architecture Selection in Differentiable NAS 10 Aug 2021 ruocwang/darts-pt/sota/cnn/projection.py ccb4bfbd6a962ba5 unverified Apache-2.0 (permissive)
Normalizing Flows for Knockoff-free Controlled Feature Selection 3 Jun 2021 msesia/deepknockoffs/DeepKnockoffs/DeepKnockoffs/machine.py 96f1fefe68df3674 unverified GPL-3.0 (copyleft) · pointer only
Context-Aware Cross-Attention for Non-Autoregressive Translation 2 Nov 2020 alphadl/CCAN/fairseq/checkpoint_utils.py 7256f41709277ec8 unverified Apache-2.0 (permissive)
The Open Catalyst 2020 (OC20) Dataset and Community Challenges 20 Oct 2020 gasteigerjo/ocp/ocpmodels/common/utils.py c6a184c02a3bee1a unverified MIT recorded; this copy not marked cleared · pointer only
A Multilingual Parallel Corpora Collection Effort for Indian Languages 15 Jul 2020 jerinphilip/fairseq-ilmt/fairseq/checkpoint_utils.py b3616a62387703cb unverified MIT recorded; this copy not marked cleared · pointer only
MC-BERT: Efficient Language Pre-Training via a Meta Controller 10 Jun 2020 MC-BERT/MC-BERT/fairseq/checkpoint_utils.py 7962926224c37b79 unverified MIT recorded; this copy not marked cleared · pointer only
Graph Random Neural Network for Semi-Supervised Learning on Graphs 22 May 2020 junzhuang-code/graphss/graphSS/models_SS.py 5b8f6ae013697a25 unverified MIT (permissive)
Lexically Constrained Neural Machine Translation with Levenshtein Transformer 27 Apr 2020 raymondhs/constrained-levt/fairseq/checkpoint_utils.py 4f5f25fa5d5cab34 unverified MIT recorded; this copy not marked cleared · pointer only
Designing Network Design Spaces 30 Mar 2020 Alessiacosmos/Basic-RegNet-pytorch/utils/checkpoint.py a0cc9cf5cccaf75a unverified MIT (permissive)
Learning to Encode Position for Transformer with Continuous Dynamical Model 13 Mar 2020 xuanqing94/FLOATER/fairseq/checkpoint_utils.py b3616a62387703cb unverified MIT recorded; this copy not marked cleared · pointer only
A Simple Framework for Contrastive Learning of Visual Representations 13 Feb 2020 Mayurji/SimCLR/SimCLR.py 7e7b54ff38780a53 unverified GPL-3.0 (copyleft) · pointer only
KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation 13 Nov 2019 THU-KEG/KEPLER/fairseq/checkpoint_utils.py b3616a62387703cb unverified MIT recorded; this copy not marked cleared · pointer only
fairseq: A Fast, Extensible Toolkit for Sequence Modeling 1 Apr 2019 lucylow/En_francais_si_vous_plait-/fairseq/checkpoint_utils.py b3616a62387703cb unverified MIT recorded; this copy not marked cleared · pointer only
DeepMiner: Discovering Interpretable Representations for Mammogram Classification and Explanation 31 May 2018 jimmyyhwu/ddsm-visual-primitives/training/train_2class.py 1a35008b98473504 ran · our draft was wrong MIT (permissive)
arXiv:aaai_21409 xssstory/SeqCo/fairseq/checkpoint_utils.py 4f5f25fa5d5cab34 unverified MIT recorded; this copy not marked cleared · 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