Home › Code › cross_entropy_loss

cross_entropy_loss

Syntologyentry name in harvested code

Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

cross_entropy_loss appears in the code Syntology harvested for 58 papers, as 49 distinct code bodies found in 58 places (a place is one code body under one paper). Of the 58 papers, 48 with a sample that ran: 32 with a run with no instrument failure, 16 where every run was a failure of Syntology's instrument. 6 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 cross_entropy_loss 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; get_code(code_sha256="…") returns this sample's fingerprint on the shared battery, with the battery's shuffled null and lift; not shown on this site (how to connect). "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

The 49 distinct code bodies named cross_entropy_loss: 42 ran (of which 0 constructed an object rather than computing a result; 28 with no instrument failure: 0 honoured, 2 violated, 26 with no contract checked; 14 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
2ran · violated contract
11ran · our draft was wrong
3ran; the contract check could not run
26ran
7unverified
6fingerprinted

Licence is a property of each copy, so it is counted per place: 24 of the 58 places are pointer only (Syntology does not serve that copy's text); at 1 of them this paper's copy is under a permissive licence, but the stored copy of the same code that Syntology serves is not cleared for its text (hover the licence cell for why). 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 “the contract check could not run” (RAISES, DEP_MISSING or TIMEOUT; hover a row's label for which) 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; “with no instrument failure” is honoured, violated and ran with no contract checked. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Papers

58 papers shown of 58, newest first; 58 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; 2 papers have no page here and are shown by their id only (arXiv: for an arXiv id; an id from another venue, such as ACL Anthology or AAAI, is named as that venue's id, never as an arXiv id). 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. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

PaperDateFileStatus SyntologyLicence
MDN: Parallelizing Stepwise Momentum for Delta Linear Attention added by Syntology 7 May 2026 HuuYuLong/MomentumDeltaNet/flame/torchtitan/components/loss.py e0b6e383f758e9a0 unverified no licence file found · pointer only
The Million-Label NER: Breaking Scale Barriers with GLiNER bi-encoder added by Syntology 2026-02 (from id) urchade/GLiNER/gliner/modeling/loss_functions.py bb1f6cd5ab3e0c98 ran Apache-2.0 (permissive)
Faithful Bi-Directional Model Steering via Distribution Matching and Distributed Interchange Interventions added by Syntology 2026-02 (from id) colored-dye/concept_das/cdas/models/das_model.py 7380c0f50e9f778c ran MIT (permissive)
Outcome-Aware Spectral Feature Learning for Instrumental Variable Regression added by Syntology 2025-12 (from id) Wornbard/AugSpecIV/learning/losses.py c50540858bc7e459 unverified no licence file found · pointer only
MonoMVSNet: Monocular Priors Guided Multi-View Stereo Network 15 Jul 2025 JianfeiJ/MonoMVSNet/models/monomvsnet.py 41f59aee24980c21 ran MIT (permissive)
A Variational Framework for Improving Naturalness in Generative Spoken Language Models 17 Jun 2025 b04901014/vae-gslm/training_lib/losses.py 4bd9184f85f7e83d ran MIT (permissive)
Trap-MID: Trapdoor-based Defense against Model Inversion Attacks 13 Nov 2024 ntuaislab/Trap-MID/plgmi/losses.py c808ba0601a877e8 ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only
Publishing Neural Networks in Drug Discovery Might Compromise Training Data Privacy 22 Oct 2024 aidotse/leakpro/leakpro/attacks/utils/gan_losses.py 40e19414623504e2 ran · our draft was wrong licence not identified · pointer only
Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning 9 Oct 2024 OPTML-Group/Unlearn-Simple/synthetic/unlearn_utils.py 04d9dfc17842cf17 ran MIT (permissive)
Decoder ensembling for learned latent geometries 14 Aug 2024 mustass/ensertainty/src/ensertainty/training/losses.py 69df12e202c46837 ran · violated contract fingerprinted licence not identified · pointer only
Learn from the Learnt: Source-Free Active Domain Adaptation via Contrastive Sampling and Visual Persistence 26 Jul 2024 lyumengyao/lftl/mining/contrastive_sampling.py a84c8b8443596255 ran · our draft was wrong no licence file found · pointer only
Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs 22 Jul 2024 aengusl/latent-adversarial-training/latent_at/utils.py 2d4f7e1c015733a4 ran · our draft was wrong MIT (permissive)
Why Warmup the Learning Rate? Underlying Mechanisms and Improvements 13 Jun 2024 dayal-kalra/why-warmup/vision/mechanisms/utils/loss_utils.py 26d13d6c867ba7fa ran · violated contract fingerprinted MIT (permissive)
The Platonic Representation Hypothesis 13 May 2024 minyoungg/platonic-rep/utils.py a7bd49b153fe597c ran no licence file found · pointer only
Scaling Laws for Galaxy Images 3 Apr 2024 identical code first harvested elsewhere a68ecd1f369223b8 unverified licence of this copy not recorded
Fairness Without Harm: An Influence-Guided Active Sampling Approach 20 Feb 2024 ucsc-real/fairnesswithoutharm/src/metrics.py bbab883e9f27b305 ran · our draft was wrong no licence file found · pointer only
Policy Learning for Off-Dynamics RL with Deficient Support 16 Feb 2024 linhlpv/DADS/dads.py a359c6a7c05c7ea0 unverified no licence file found · pointer only
Vivim: a Video Vision Mamba for Medical Video Segmentation 25 Jan 2024 scott-yjyang/vivim/loss.py e4f26582292cf067 unverified licence not identified · pointer only
EarthVQA: Towards Queryable Earth via Relational Reasoning-Based Remote Sensing Visual Question Answering 19 Dec 2023 Junjue-Wang/EarthVQA/module/loss.py 4133a26ae05f4dd9 ran · our draft was wrong no licence file found · pointer only
A Study on the Calibration of In-context Learning 7 Dec 2023 hlzhang109/icl-calibration/calibrate/verified_calibration.py 19422cfbfee41729 ran; the contract check could not run (RAISES) MIT (permissive)
Critical Influence of Overparameterization on Sharpness-aware Minimization 29 Nov 2023 log-postech/sam-overparam/train_utils.py 6f369ebdcbe5c0a3 ran no licence file found · pointer only
Label-Only Model Inversion Attacks via Knowledge Transfer 30 Oct 2023 ngoc-nguyen-0/LOKT_neurips2023/plg_tacgan.py c808ba0601a877e8 ran · our draft was wrong no licence file found · pointer only
Specify Robust Causal Representation from Mixed Observations 21 Oct 2023 ymy4323460/cari/utils.py 6bfc467eb2d2b427 unverified no licence file found · pointer only
When Epipolar Constraint Meets Non-local Operators in Multi-View Stereo 29 Sep 2023 tqtqliu/et-mvsnet/models/MVS4Net.py 41f59aee24980c21 ran MIT (permissive)
Galaxy Zoo DESI: Detailed Morphology Measurements for 8.7M Galaxies in the DESI Legacy Imaging Surveys 2023-09 (from id) identical code first harvested elsewhere a68ecd1f369223b8 unverified licence of this copy not recorded
Multi-grained Temporal Prototype Learning for Few-shot Video Object Segmentation 20 Sep 2023 nankepan/VIPMT/libs/utils/loss.py 2d13347de310a810 ran no licence file found · pointer only
Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learning 8 Aug 2023 hanjaekim98/cot/models/cot.py 86116ff1c363bbaf ran fingerprinted no licence file found · pointer only
Bidirectional Looking with A Novel Double Exponential Moving Average to Adaptive and Non-adaptive Momentum Optimizers 2 Jul 2023 chernyn/admeta-optimizer/admeta-code/admeta-cifar/pytorch_image_classification/losses/label_smoothing.py bc8c7f73dc3f1039 ran BSD-2-Clause (permissive)
Recasting Self-Attention with Holographic Reduced Representations 31 May 2023 neuromorphiccomputationresearchprogram/hrrformer/image/hrrformer_mgpu.py 11b73c012ece44e7 ran fingerprinted Apache-2.0 (permissive)
C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptation 30 Mar 2023 nazmul-karim170/C-SFDA_Source-Free-Domain-Adaptation/target_csfda.py 1d0329a2deb6eac4 ran · our draft was wrong MIT (permissive)
On the Efficacy of Differentially Private Few-shot Image Classification 2 Feb 2023 cambridge-mlg/dp-few-shot/src/utils.py a521b8c61c81ecdd ran MIT (permissive)
Free Lunch for Domain Adversarial Training: Environment Label Smoothing 1 Feb 2023 yfzhang114/Environment-Label-Smoothing/Domain_Generalization/domainbed/algorithms.py f0b9793b30a672e0 ran · our draft was wrong no licence file found · pointer only
Contrastive Test-Time Adaptation 21 Apr 2022 DianCh/AdaContrast/target.py 7f2f33aeb9dd8ed3 ran · our draft was wrong no licence file found · pointer only
Learning Multiple Dense Prediction Tasks from Partially Annotated Data 29 Nov 2021 vico-uoe/mtpsl/model/mapfns.py ae00279e3bc33623 ran MIT (permissive)
Practical Galaxy Morphology Tools from Deep Supervised Representation Learning 25 Oct 2021 identical code first harvested elsewhere a68ecd1f369223b8 unverified licence of this copy not recorded
Cross Domain Robot Imitation with Invariant Representation 13 Sep 2021 zhaohengyin/irgail_example/imitation_learning/network/utils.py b4cee438c3091f1c ran MIT (permissive)
Deep Learning on a Data Diet: Finding Important Examples Early in Training 15 Jul 2021 mansheej/data_diet/data_diet/metrics.py b9fe6d146beff6d7 ran fingerprinted Apache-2.0 (permissive)
How many degrees of freedom do we need to train deep networks: a loss landscape perspective 13 Jul 2021 ganguli-lab/degrees-of-freedom/lottery_subspace.py 82620ac387a3de49 ran · our draft was wrong no licence file found · pointer only
Memory Efficient Meta-Learning with Large Images 2 Jul 2021 cambridge-mlg/LITE/src/utils.py a521b8c61c81ecdd ran MIT (permissive)
Universal Representation Learning from Multiple Domains for Few-shot Classification 25 Mar 2021 tmlr-group/CoPA/models/pa.py ab00127e0e9d1905 ran · our draft was wrong MIT (permissive)
Galaxy Zoo DECaLS: Detailed Visual Morphology Measurements from Volunteers and Deep Learning for 314,000 Galaxies 16 Feb 2021 mwalmsley/zoobot/zoobot/pytorch/training/finetune.py a68ecd1f369223b8 unverified GPL-3.0 (copyleft) · pointer only
Cross-Domain Sentiment Classification with In-Domain Contrastive Learning 5 Dec 2020 CasparSwift/CLIM/loss.py bffe7f13e375927e ran · metamorphic tier: invariant no licence file found · pointer only
Loss re-scaling VQA: Revisiting the LanguagePrior Problem from a Class-imbalance View 30 Oct 2020 guoyang9/class-imbalance-VQA/utils/losses.py bd13bf1e7cf15819 ran Apache-2.0 (permissive)
Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild 23 Jul 2020 YoungXIAO13/PoseContrast/src/model/model_utils.py af5785faecdf4e41 ran MIT (permissive)
A Survey of Information Cascade Analysis: Models, Predictions, and Recent Advances 22 May 2020 Xovee/hdgnn/codes/gnn_train/tools.py 6dab6885871344ad ran MIT (permissive)
Selecting Relevant Features from a Multi-domain Representation for Few-shot Classification 20 Mar 2020 dvornikita/SUR/models/losses.py ab00127e0e9d1905 ran · our draft was wrong MIT (permissive)
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence 21 Jan 2020 gomezzz/distmsmatch/MSMatch/models/fixmatch/FixMatch.py 774112e52d064668 ran; the contract check could not run (RAISES) MIT (permissive)
Harmonic Convolutional Networks based on Discrete Cosine Transform 18 Jan 2020 matej-ulicny/harmonic-networks/bsds/functions.py 508c627527d31817 ran BSD-3-Clause (permissive)
Evaluating Protein Transfer Learning with TAPE 19 Jun 2019 googleinterns/protein-embedding-retrieval/contextual_lenses/loss_fns.py af86e14bcdd0eee9 ran Apache-2.0 (permissive)
Pose from Shape: Deep Pose Estimation for Arbitrary 3D Objects 12 Jun 2019 YoungXIAO13/PoseFromShape/auxiliary/loss.py af5785faecdf4e41 ran MIT (permissive)
End-to-End Wireframe Parsing 8 May 2019 zhou13/lcnn/lcnn/models/multitask_learner.py 0d148fed48dc7e0f ran MIT (permissive)
Learning Compressed Transforms with Low Displacement Rank 4 Oct 2018 HazyResearch/structured-nets/pytorch/utils.py 8ef54cdb8384cbab ran fingerprinted Apache-2.0 (permissive)
On Calibration of Modern Neural Networks 14 Jun 2017 saurabhgarg1996/calibration/calibration/calibrators.py 155f63d9cf89a950 ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive)
Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking 6 Sep 2016 hh23333/tsd/loss/parsing_loss.py 89da1a43b987162b ran MIT (permissive)
Variational Inference with Normalizing Flows 21 May 2015 Aditya-kiran/ResNet-VAE/code/losses.py 70fc47d8442de3fe unverified MIT (permissive)
Holistically-Nested Edge Detection 24 Apr 2015 meteorshowers/hed-pytorch/functions.py 508c627527d31817 ran MIT (permissive)
AAAI id aaai_5479 thunlp/QAjudge/model/loss.py d0e9f4c84e69fbf5 ran MIT (permissive)
ACL Anthology id 2022.findings-acl.116 vistec-AI/Thai-NNER/model/loss.py fc13a6fe4c6c8129 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is under a permissive licence, but the stored copy of the same code that Syntology serves is not cleared for its text. 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