Home › Code › calc_loss

calc_loss

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

calc_loss appears in the code Syntology harvested for 35 papers, as 31 distinct code bodies found in 41 places (a place is one code body under one paper). At least one of them ran in 20 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 calc_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; 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 15 of the 31 distinct code bodies named calc_loss; 16 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

2ran · honoured contract
0ran · violated contract
4ran · our draft was wrong
4ran · fixture could not drive it
5ran
16unverified
5fingerprinted

Licence is a property of each copy, so it is counted per place: 12 of the 41 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

35 papers shown of 35, newest first; 41 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. 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
Transferable Adversarial Attacks on SAM and Its Downstream Models 26 Oct 2024 xiasong0501/grat/one_sample_train.py 40f56fce40b517b1 unverified MIT (permissive)
Token-wise Influential Training Data Retrieval for Large Language Models 20 May 2024 huawei-lin/RapidIn/RapidIn/calc_inner.py 3b9e99e67f054149 ran licence not identified · pointer only
GO4Align: Group Optimization for Multi-Task Alignment 9 Apr 2024 identical code first harvested elsewhere c6155037f0a674c4 ran · our draft was wrong licence of this copy not recorded
Unleashing the Potential of SAM for Medical Adaptation via Hierarchical Decoding 27 Mar 2024 cccccczh404/h-sam/trainer.py ad5471db7ab93cbf ran MIT (permissive)
BLO-SAM: Bi-level Optimization Based Overfitting-Preventing Finetuning of SAM 26 Feb 2024 importzl/blo-sam/trainer.py ad5471db7ab93cbf ran no licence file found · pointer only
BLO-SAM: Bi-level Optimization Based Overfitting-Preventing Finetuning of SAM 26 Feb 2024 importzl/blo-sam/prompt.py 5c939eca7a512176 ran no licence file found · pointer only
Recovering the Pre-Fine-Tuning Weights of Generative Models 15 Feb 2024 eliahuhorwitz/Spectral-DeTuning/spectral_detuning.py 69b972e54e2a148f ran · our draft was wrong fingerprinted licence not identified · pointer only
FairSeg: A Large-Scale Medical Image Segmentation Dataset for Fairness Learning Using Segment Anything Model with Fair Error-Bound Scaling 3 Nov 2023 harvard-ophthalmology-ai-lab/fairseg/TransUNet/trainer.py ad5471db7ab93cbf ran no licence file found · pointer only
Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task 13 Oct 2023 phys-ai/concept_graphs/plotting.py 42a12d0a4bf4d2e0 ran no licence file found · pointer only
DTPP: Differentiable Joint Conditional Prediction and Cost Evaluation for Tree Policy Planning in Autonomous Driving 2023-10 (from id) mczhi/dtpp/train_utils.py 60ae27a9d035f0e0 unverified Apache-2.0 (permissive)
MA-SAM: Modality-agnostic SAM Adaptation for 3D Medical Image Segmentation 16 Sep 2023 cchen-cc/ma-sam/MA-SAM/trainer.py ad5471db7ab93cbf ran Apache-2.0 (permissive)
Single-User Injection for Invisible Shilling Attack against Recommender Systems 21 Aug 2023 kdegroup/sui-attack/models/influence/influence_function.py 7d9344ac520f8918 ran · fixture could not drive it MIT (permissive)
Improvable Gap Balancing for Multi-Task Learning 28 Jul 2023 identical code first harvested elsewhere c6155037f0a674c4 ran · our draft was wrong licence of this copy not recorded
Universal and Transferable Adversarial Attacks on Aligned Language Models 27 Jul 2023 sj21j/Regularized_Relaxation/pgd.py bbec7a51e90453b0 unverified MIT (permissive)
Universal and Transferable Adversarial Attacks on Aligned Language Models 27 Jul 2023 sj21j/Regularized_Relaxation/softprompt.py e496788013a04ab0 unverified MIT (permissive)
Ladder Fine-tuning approach for SAM integrating complementary network 22 Jun 2023 11yxk/sam-lst/trainer.py ad5471db7ab93cbf ran MIT (permissive)
Building the Bridge of Schrödinger: A Continuous Entropic Optimal Transport Benchmark 16 Jun 2023 ngushchin/entropicotbenchmark/benchmark/glow_train.py 5450899cdebae728 unverified MIT (permissive)
FAMO: Fast Adaptive Multitask Optimization 6 Jun 2023 cranial-xix/famo/experiments/nyuv2/trainer.py c6155037f0a674c4 ran · our draft was wrong MIT (permissive)
Direction-oriented Multi-objective Learning: Simple and Provable Stochastic Algorithms 28 May 2023 ml-opt-lab/sdmgrad/experiments/cityscapes/trainer.py 0a0f4c8898070a9d unverified MIT (permissive)
All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentation 25 May 2023 LiyaoTang/ERDA/models/head.py 87082c78c01cdcc8 unverified MIT (permissive)
Neural Face Rigging for Animating and Retargeting Facial Meshes in the Wild 15 May 2023 dafei-qin/NFR_pytorch/FWH_run.py df2d65dfef54b47d unverified MIT (permissive)
Customized Segment Anything Model for Medical Image Segmentation 26 Apr 2023 hitachinsk/samed/SAMed_h/trainer.py ad5471db7ab93cbf ran MIT (permissive)
Enabling the discovery of fast transients: A kilonova science module for the Fink broker 2022-10 (from id) b-biswas/kndetect/kndetect/features.py 94ef65b0db65b453 unverified BSD-3-Clause (permissive)
Leveraging Instance Features for Label Aggregation in Programmatic Weak Supervision 6 Oct 2022 JieyuZ2/wrench/wrench/endmodel/cosine.py ad14014186a0bf9e unverified Apache-2.0 (permissive)
When can I Speak? Predicting initiation points for spoken dialogue agents 7 Aug 2022 siyan-sylvia-li/icarus_final/icarus_gmm_trainer.py a563b5d8b711445b ran · fixture could not drive it MIT (permissive)
When can I Speak? Predicting initiation points for spoken dialogue agents 7 Aug 2022 siyan-sylvia-li/icarus_final/icarus_heatmap_trainer.py 28b2e0c2fab85f9c ran · honoured contract fingerprinted MIT (permissive)
When can I Speak? Predicting initiation points for spoken dialogue agents 7 Aug 2022 siyan-sylvia-li/icarus_final/icarus_min_trainer.py 4d417aa3b42feb48 ran · fixture could not drive it fingerprinted MIT (permissive)
Out-of-Distribution Detection with Deep Nearest Neighbors 13 Apr 2022 deeplearning-wisc/knn-ood/util/score.py 7d9344ac520f8918 ran · fixture could not drive it no licence file found · pointer only
Show Me More Details: Discovering Hierarchies of Procedures from Semi-structured Web Data 14 Mar 2022 shuyanzhou/wikihow_hierarchy/reranking/inference.py b64372507baf6d77 ran fingerprinted no licence file found · pointer only
Quasi-Balanced Self-Training on Noise-Aware Synthesis of Object Point Clouds for Closing Domain Gap 8 Mar 2022 Gorilla-Lab-SCUT/QS3/DefCls.py 1f8af716d9bd010b unverified MIT (permissive)
Quasi-Balanced Self-Training on Noise-Aware Synthesis of Object Point Clouds for Closing Domain Gap 8 Mar 2022 Gorilla-Lab-SCUT/QS3/PCM.py f3c8ecae4d1fc6b1 unverified MIT (permissive)
Quasi-Balanced Self-Training on Noise-Aware Synthesis of Object Point Clouds for Closing Domain Gap 8 Mar 2022 Gorilla-Lab-SCUT/QS3/PosReg.py 6a987abc783d48a4 unverified MIT (permissive)
FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows 15 Nov 2021 RistoranteRist/FastFlow/utils.py a1c1c89b7d27cf53 unverified MIT (permissive)
Geometry-Aware Self-Training for Unsupervised Domain Adaptationon Object Point Clouds 20 Aug 2021 zou-longkun/gast/NormReg.py 8109d1bb8e51e851 ran · fixture could not drive it no licence file found · pointer only
Distilling the Knowledge from Conditional Normalizing Flows 24 Jun 2021 yandex-research/distill-nf/waveglow/models/waveglow.py 4e8785b3c11abfe7 unverified Apache-2.0 (permissive)
On Sample Based Explanation Methods for NLP:Efficiency, Faithfulness, and Semantic Evaluation 9 Jun 2021 IBM/TracInF/code/pif/influence_functions/hvp_grad.py 726d0822a9e90aaf ran · our draft was wrong Apache-2.0 (permissive)
Understanding Instance-based Interpretability of Variational Auto-Encoders 29 May 2021 fengnima/vae-tracin-pytorch/tracin.py 5380fb72510af9a7 ran · our draft was wrong fingerprinted MIT (permissive)
Fourier Neural Operator for Parametric Partial Differential Equations 18 Oct 2020 sala-group/autows-bench-101/wrench/endmodel/cosine.py ad14014186a0bf9e unverified Apache-2.0 (permissive)
Self-Supervised Learning for Domain Adaptation on Point-Clouds 29 Mar 2020 IdanAchituve/DefRec_and_PCM/DefRec_and_PCM/PCM.py c74c1b9644da78ce ran · honoured contract no licence file found · pointer only
NICE: Noise Injection and Clamping Estimation for Neural Network Quantization 29 Sep 2018 Lancer555/NICE/loss.py 528eda19fa60bac0 unverified MIT (permissive)
Glow: Generative Flow with Invertible 1x1 Convolutions 9 Jul 2018 eyalbetzalel/GLOW/train_local_pc.py 5450899cdebae728 unverified 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 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