Home › Code › loss_fn

loss_fn

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.

loss_fn appears in the code Syntology harvested for 55 papers, as 53 distinct code bodies found in 60 places (a place is one code body under one paper). Of the 55 papers, 40 with a sample that ran: 22 with a run with no instrument failure, 18 where every run was a failure of Syntology's instrument. 15 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 loss_fn 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 53 distinct code bodies named loss_fn: 39 ran (of which 0 constructed an object rather than computing a result; 26 with no instrument failure: 9 honoured, 1 violated, 16 with no contract checked; 13 where Syntology's instrument failed) · 14 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:

9ran · honoured contract
1ran · violated contract
6ran · our draft was wrong
7ran; the contract check could not run
16ran
14unverified
15fingerprinted

Licence is a property of each copy, so it is counted per place: 32 of the 60 places are pointer only (Syntology does not serve that copy's text); at 4 of those 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

55 papers shown of 55, newest first; 60 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 5 papers added by Syntology; 3 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
Epiplexity Guided Data Selection and Generation for Out-of-Distribution Generalization added by Syntology 2026-08 (from id) eysu35/EpiSelect/src/data_selectors/episelect.py 24dca89866b40710 ran; the contract check could not run (RAISES) fingerprinted MIT (permissive)
The Evaluation Protocol Determines the Result: An Independent Reproduction of LeWorldModel on TwoRoom added by Syntology 2026-08 (from id) joyjeet-singh/tinylab/model.py 267adf54ec9d665f ran · honoured contract no licence file found · pointer only
Characterize Then Distill: Mechanistic Reasoning in Large Output Spaces added by Syntology 2026-06 (from id) research-anon-487/xcube/xcube/l2r/gradients.py 0232ac1b45031e9d unverified Apache-2.0 (permissive)
Fed-Listing: Federated Label Distribution Inference in Graph Neural Networks added by Syntology 2026-02 (from id) suprimnakarmi/Fed-Listing/source_code/Fed-listing/attack_model.py 0d135e52412c80a3 ran no licence file found · pointer only
ACTG-ARL: Differentially Private Conditional Text Generation with RL-Boosted Control added by Syntology 2025-10 (from id) tanyuqian/synthetic-private-data/finetune.py 9de7ddca8f9bbc3c ran no licence file found · pointer only
arXiv:2507.07101 2025-07 (from id) martin-marek/batch-size/finetuning/finetune.py a2462470e0c5e406 unverified MIT (permissive)
TraSCE: Trajectory Steering for Concept Erasure 10 Dec 2024 anubhav1997/trasce/generate_images_concept_erasure.py 1784b58cb375899c ran · honoured contract fingerprinted no licence file found · pointer only
Rethinking Pruning Large Language Models: Benefits and Pitfalls of Reconstruction Error Minimization 21 Jun 2024 log-postech/rethinking-llm-pruning/lib/llama/finetune.py 4daf7035d84ce598 ran · honoured contract fingerprinted no licence file found · pointer only
WellDunn: On the Robustness and Explainability of Language Models and Large Language Models in Identifying Wellness Dimensions 17 Jun 2024 vedantpalit/WellDunn/LLMs_WellXplain/Llama_experiment.py 3459c1b6589faba2 ran · violated contract fingerprinted no licence file found · pointer only
Neural Context Flows for Meta-Learning of Dynamical Systems 3 May 2024 ddrous/ncflow/ncf/learner.py 31b333bdcc0116c5 unverified MIT (permissive)
Metric-Guided Conformal Bounds for Probabilistic Image Reconstruction 23 Apr 2024 matthewyccheung/conformal-metric/bias/synthetic.py 7085be724669ed9a unverified MIT (permissive)
Distributionally Generative Augmentation for Fair Facial Attribute Classification 11 Mar 2024 heqianpei/DiGA/BYOL/BYOL.py 00cae89471470576 ran · our draft was wrong fingerprinted no licence file found · pointer only
CLAPSep: Leveraging Contrastive Pre-trained Model for Multi-Modal Query-Conditioned Target Sound Extraction 27 Feb 2024 aisaka0v0/clapsep/model/CLAPSep.py 9a053c56d1d332e3 ran fingerprinted MIT (permissive)
NeuralDiffuser: Neuroscience-inspired Diffusion Guidance for fMRI Visual Reconstruction 21 Feb 2024 haoyyli/neuraldiffuser/src/recon.py bb53e8b539584939 ran · honoured contract fingerprinted no licence file found · pointer only
It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition 8 Feb 2024 Hypotheses-Paradise/UADF/finetune/adapter.py b3207d2a276b9a79 ran; the contract check could not run (RAISES) · metamorphic tier: invariant Apache-2.0 (permissive) here; the stored copy is pointer only
In-Context Reinforcement Learning for Variable Action Spaces 20 Dec 2023 identical code first harvested elsewhere 213b8058df2e85bf ran; the contract check could not run (RAISES) · metamorphic tier: invariant licence of this copy not recorded
Grokking Group Multiplication with Cosets 11 Dec 2023 dashstander/sn-grok/calculate_cosets.py 65a18a30de63b6e8 ran MIT (permissive)
Cappy: Outperforming and Boosting Large Multi-Task LMs with a Small Scorer 12 Nov 2023 tanyuqian/cappy/cappy_bigbench.py f73fe4e70456b114 ran · our draft was wrong Apache-2.0 (permissive)
Uncovering Intermediate Variables in Transformers using Circuit Probing 7 Nov 2023 mlepori1/circuit_probing/src/train_algorithmic_models.py fd76c5e635c1455a ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only
Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination 6 Nov 2023 heimine/pnc_dln/linear_probe.py 84b336c1b357cf00 ran fingerprinted no licence file found · pointer only
Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination 6 Nov 2023 heimine/pnc_dln/train_cifar.py 158ee19e017d75ab ran no licence file found · pointer only
Diffusion Models as Stochastic Quantization in Lattice Field Theory 29 Sep 2023 anguswlx/dmassq/loss.py 73ec3b826b113561 ran MIT (permissive)
Embodied Task Planning with Large Language Models 4 Jul 2023 Gary3410/TaPA/finetune/adapter.py b3207d2a276b9a79 ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only
MoMo: Momentum Models for Adaptive Learning Rates 12 May 2023 fabian-sp/MoMo/example.py 2ec9e2662f3e2b31 ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive)
FOSI: Hybrid First and Second Order Optimization 16 Feb 2023 hsivan/fosi/examples/fosi_torch_example.py a0b5a0ec8b3915d2 unverified Apache-2.0 (permissive)
In-context Reinforcement Learning with Algorithm Distillation 25 Oct 2022 corl-team/headless-ad/src/gridworld/algorithms/headless_ad.py 213b8058df2e85bf ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only
SAM as an Optimal Relaxation of Bayes 4 Oct 2022 team-approx-bayes/bayesian-sam/demo2d.py ea6ded110b209017 unverified GPL-3.0 (copyleft) · pointer only
ArgLegalSumm: Improving Abstractive Summarization of Legal Documents with Argument Mining 4 Sep 2022 engsalem/arglegalsumm/src/argument_classification/argument_classifier.py 0b4f809b4b200f41 ran · honoured contract no licence file found · pointer only
SDWPF: A Dataset for Spatial Dynamic Wind Power Forecasting Challenge at KDD Cup 2022 8 Aug 2022 jseaj/2dxformer/run_model.py c9c18a8a3248d43b ran · our draft was wrong fingerprinted MIT (permissive)
Global-Reasoned Multi-Task Learning Model for Surgical Scene Understanding 28 Jan 2022 identical code first harvested elsewhere 94bf8cb7d4647820 unverified licence of this copy not recorded
Self-Distilled Self-Supervised Representation Learning 25 Nov 2021 hagiss/sdssl/pl_train_byol.py 00cae89471470576 ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
Self-Distilled Self-Supervised Representation Learning 25 Nov 2021 hagiss/sdssl/pl_train_moco.py e53d0d8dc48485af ran fingerprinted MIT (permissive)
A Bayesian generative neural network framework for epidemic inference problems 5 Nov 2021 ocadni/annfore/annfore/learn/losses.py 8260a897032b015e ran Apache-2.0 (permissive)
Learning Temporally-Consistent Representations for Data-Efficient Reinforcement Learning 11 Oct 2021 anon-researcher-repo/ksl/ksl/ksl.py 00cae89471470576 ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
Unsupervised Motion Representation Learning with Capsule Autoencoders 1 Oct 2021 ziweixu/capsulemotion/lib/mcae/model.py 3aa0d94122193b9e ran; the contract check could not run (RAISES) · metamorphic tier: deterministic MIT (permissive)
Graph neural networks for laminar flow prediction around random 2D shapes 2021-07 (from id) jviquerat/gnn_laminar_flow/training_utils.py b8913be9e4152f50 unverified MIT (permissive)
Large-Scale Representation Learning on Graphs via Bootstrapping 12 Feb 2021 Namkyeong/BGRL_Pytorch/models.py 00cae89471470576 ran · our draft was wrong fingerprinted no licence file found · pointer only
RAFT-3D: Scene Flow using Rigid-Motion Embeddings 1 Dec 2020 princeton-vl/RAFT-3D/scripts/train_things.py 5573a1cb760609a7 unverified BSD-3-Clause (permissive)
Semi-supervised Batch Active Learning via Bilevel Optimization 19 Oct 2020 zalanborsos/bilevel_coresets/batch_active_learning/nystrom_example.py 02c73252d050997f ran · honoured contract fingerprinted MIT (permissive)
Learning and Reasoning with the Graph Structure Representation in Robotic Surgery 7 Jul 2020 mobarakol/Surgical_SceneGraph_Generation/evaluation_metrics.py 94bf8cb7d4647820 unverified no licence file found · pointer only
Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification 17 Mar 2020 akshitac8/tfvaegan/train_actions.py aaa55fee4c12babe ran MIT (permissive)
Adversarial Attacks on Probabilistic Autoregressive Forecasting Models 8 Mar 2020 eth-sri/probabilistic-forecasts-attacks/Electricity/model/net.py dbccb94ff0308fed ran Apache-2.0 (permissive)
Revisiting Knowledge Distillation via Label Smoothing Regularization 25 Sep 2019 yuanli2333/Teacher-free-Knowledge-Distillation/model/resnet.py 2fabab362b4fd333 ran MIT (permissive)
Revisiting Knowledge Distillation via Label Smoothing Regularization 25 Sep 2019 yuanli2333/Teacher-free-Knowledge-Distillation/model/resnext.py 135ebbf5ed793416 ran MIT (permissive)
Revisiting Knowledge Distillation via Label Smoothing Regularization 25 Sep 2019 yuanli2333/Teacher-free-Knowledge-Distillation/model/wrn.py 106d033266830257 ran MIT (permissive)
Deep Signature Transforms 21 May 2019 patrick-kidger/Deep-Signature-Transforms/src/signature_inversion.py 56be8c2cedfe1979 ran · our draft was wrong Apache-2.0 (permissive)
Symmetry-Based Disentangled Representation Learning requires Interaction with Environments 30 Mar 2019 Caselles/NeurIPS19-SBDRL/code/learn_4_dim_linear_disentangled_representation/01_train_vae_sans_cos_sin.py 4ea78db60dcc3a18 unverified MIT (permissive)
DeepZip: Lossless Data Compression using Recurrent Neural Networks 20 Nov 2018 mohit1997/DeepZip/src/trainer.py d10e845597405b7e unverified MIT (permissive)
Towards Empathetic Open-domain Conversation Models: a New Benchmark and Dataset 1 Nov 2018 facebookresearch/EmpatheticDialogues/retrieval_train.py bb348efa3df2be58 ran · our draft was wrong fingerprinted licence not identified · pointer only
Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation 17 Apr 2018 hhe-distance/AIF-CNN/for_ntu/model/AIF_CNN.py 420f3c8dfea9f457 ran · our draft was wrong no licence file found · pointer only
Deep Learning using Rectified Linear Units (ReLU) 22 Mar 2018 AFAgarap/relu-classifier/models/neural_net.py 5b6e064a9ab90fe4 ran Apache-2.0 (permissive)
Disentangled Sequential Autoencoder 8 Mar 2018 mazzzystar/Disentangled-Sequential-Autoencoder/disVAE.py 4360bbfc62d0fcb0 ran · honoured contract fingerprinted no licence file found · pointer only
Disentangled Sequential Autoencoder 8 Mar 2018 yatindandi/Disentangled-Sequential-Autoencoder/trainer.py 26aff04580832904 ran · honoured contract fingerprinted no licence file found · pointer only
Regularizing and Optimizing LSTM Language Models 7 Aug 2017 vganesh46/awd-lstm-pytorch-implementation/model/net.py f7bb4492f97bc8b6 unverified no licence file found · pointer only
Poincaré Embeddings for Learning Hierarchical Representations 22 May 2017 drewwilimitis/hyperbolic-learning/hyperbolic_svm/hsvm.py d580486bed607544 unverified no licence file found · pointer only
Conditional Image Generation with PixelCNN Decoders 16 Jun 2016 kamenbliznashki/pixel_models/pixelcnn.py bd3e6d44a59d468d ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only
Asynchronous Methods for Deep Reinforcement Learning 4 Feb 2016 N0r9st/a2c-jax/jax_a2c/a2c.py ccd9cd7b44c7155d unverified no licence file found · pointer only
Long Short-Term Memory-Networks for Machine Reading 25 Jan 2016 oneil512/lstmn/lstmn.py f50416d9707b5c6f ran · honoured contract fingerprinted no licence file found · pointer only
ACL Anthology id 2024.naacl-long.343 king-yyf/CMeKG_tools/model_re/medical_re.py f062fd0bb6d5640e ran MIT (permissive)
ACL Anthology id 2021.acl-long.402 yanzhangnlp/BSL/sentence_transformers/losses/BYOLoss.py 00cae89471470576 ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is 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 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