Home › Code › log_sum_exp

log_sum_exp

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

log_sum_exp appears in the code Syntology harvested for 51 papers, as 36 distinct code bodies found in 56 places (a place is one code body under one paper). At least one of them ran in 31 of the papers; 8 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 log_sum_exp 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 36 distinct code bodies named log_sum_exp; 21 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

2ran · honoured contract
0ran · violated contract
9ran · our draft was wrong
0ran · fixture could not drive it
4ran
21unverified
8fingerprinted

Licence is a property of each copy, so it is counted per place: 11 of the 56 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

51 papers shown of 51, newest first; 56 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 1 papers added by Syntology; 5 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
Unlearning What Matters: Token-Level Attribution for Precise Language Model Unlearning added by Syntology 2026-05 (from id) nlp-uoregon/trankit/trankit/layers/crf_layer.py f9126d3e4828acad unverified Apache-2.0 (permissive)
arXiv:2507.12075 2025-07 (from id) booknlp/booknlp/booknlp/common/crf.py 457e7ee196816a9e unverified MIT (permissive)
Graph Diffusion Policy Optimization 26 Feb 2024 sail-sg/gdpo/model/infomax.py c03feba6bc4986f6 unverified no licence file found · pointer only
Counterfactual Generation with Identifiability Guarantees 23 Feb 2024 hanqi-qi/matte/models/flow_network.py e2a46cef5131cdc0 ran no licence file found · pointer only
Weakly Supervised Semantic Parsing with Execution-based Spurious Program Filtering 2 Nov 2023 klee972/exec-filter/wikitable/weaksp_em19/wikitable/model/baseline.py 3d7631fc6903e509 ran Apache-2.0 (permissive)
Weakly Supervised Semantic Parsing with Execution-based Spurious Program Filtering 2 Nov 2023 klee972/exec-filter/wikitable/weaksp_em19/wikitable/module/lattice.py c9cc0b6ea0723393 ran Apache-2.0 (permissive)
RegaVAE: A Retrieval-Augmented Gaussian Mixture Variational Auto-Encoder for Language Modeling 16 Oct 2023 trustedllm/regavae/Step1/train_utils.py 5efe6eb2209f6591 ran · our draft was wrong no licence file found · pointer only
TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series 2 Oct 2023 ServiceNow/TACTiS/tactis/model/flow.py 3545580aca8bb732 ran Apache-2.0 (permissive)
Exchanging-based Multimodal Fusion with Transformer 5 Sep 2023 recklessronan/muse/code/models.py a42f23f7210ea856 ran · honoured contract fingerprinted no licence file found · pointer only
Language Model Pre-Training with Sparse Latent Typing 23 Oct 2022 renll/sparselt/evaluations/supervised-ie/model.py bd9ad74746bdeace ran · our draft was wrong Apache-2.0 (permissive)
Fengshenbang 1.0: Being the Foundation of Chinese Cognitive Intelligence 7 Sep 2022 idea-ccnl/fengshenbang-lm/fengshen/models/DAVAE/DAVAEModel.py 5efe6eb2209f6591 ran · our draft was wrong Apache-2.0 (permissive)
Fuse It More Deeply! A Variational Transformer with Layer-Wise Latent Variable Inference for Text Generation 13 Jul 2022 OpenVLG/DELLA/train_utils.py 5efe6eb2209f6591 ran · our draft was wrong MIT (permissive)
TAGPRIME: A Unified Framework for Relational Structure Extraction 25 May 2022 PlusLabNLP/TagPrime/src/model.py bd9ad74746bdeace ran · our draft was wrong no licence file found · pointer only
Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks 28 Jan 2022 SCccc21/Knowledge-Enriched-DMI/attack.py 265774c3878176e5 unverified MIT (permissive)
Regularizing Variational Autoencoder with Diversity and Uncertainty Awareness 24 Oct 2021 smilesdzgk/du-vae/modules/vae.py 5efe6eb2209f6591 ran · our draft was wrong MIT (permissive)
ProtoMIL: Multiple Instance Learning with Prototypical Parts for Whole-Slide Image Classification 24 Aug 2021 apardyl/protomil/weight_loss.py d90a16e645700743 unverified MIT (permissive)
Rethinking Noisy Label Models: Labeler-Dependent Noise with Adversarial Awareness 28 May 2021 wohlert/semi-supervised-pytorch/semi-supervised/utils.py c96d37e6f13ff9af unverified MIT (permissive)
Video Corpus Moment Retrieval with Contrastive Learning 13 May 2021 IsaacChanghau/ReLoCLNet/method_tvr/contrastive.py 80b5572ac3d22dd3 unverified MIT (permissive)
Active Learning for Deep Object Detection via Probabilistic Modeling 30 Mar 2021 NVlabs/AL-MDN/layers/modules/multibox_loss_gmm.py 99c65fd4e843a6a0 ran · our draft was wrong fingerprinted licence not identified · pointer only
Contrastive Learning with Hard Negative Samples 9 Oct 2020 joshr17/HCL/graph/cortex_DIM/functions/gan_losses.py c03feba6bc4986f6 unverified MIT (permissive)
Knowledge-Enriched Distributional Model Inversion Attacks 8 Oct 2020 scccc21/knowledge-enriched-dmi/k+1_gan.py ed2c8f941b766ebb ran · our draft was wrong fingerprinted MIT (permissive)
Discontinuous Constituent Parsing as Sequence Labeling 1 Oct 2020 aghie/disco2labels/NCRF/model/crf.py 8e960fbb64668568 ran · our draft was wrong fingerprinted MIT (permissive)
Fast and Accurate Neural CRF Constituency Parsing 9 Aug 2020 jiesutd/NCRFpp/model/crf.py 8e960fbb64668568 ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information 22 Jun 2020 Linear95/CLUB/mi_estimators.py a1572564f4e423a2 ran · our draft was wrong fingerprinted no licence file found · pointer only
MAVEN: A Massive General Domain Event Detection Dataset 28 Apr 2020 THU-KEG/MAVEN-dataset/baselines/BERT+CRF/BERT-CRF-MAVEN/crf.py 8e960fbb64668568 ran · our draft was wrong fingerprinted MIT (permissive)
A Batch Normalized Inference Network Keeps the KL Vanishing Away 27 Apr 2020 valdersoul/bn-vae/modules/utils.py 5efe6eb2209f6591 ran · our draft was wrong MIT (permissive)
State-only Imitation with Transition Dynamics Mismatch 27 Feb 2020 tgangwani/RL-Indirect-imitation/i2l/networks/discriminator_model.py 5e0544169ee07211 ran · our draft was wrong no licence file found · pointer only
Parsing as Pretraining 5 Feb 2020 aghie/parsing-as-pretraining/NCRFpp/model/crf.py 8e960fbb64668568 ran · our draft was wrong fingerprinted MIT (permissive)
Hierarchical Contextualized Representation for Named Entity Recognition 6 Nov 2019 cslydia/Hire-NER/model/crf.py 8e960fbb64668568 ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
Distantly Supervised Named Entity Recognition using Positive-Unlabeled Learning 4 Jun 2019 v-mipeng/LexiconNER/sub_model.py 390527929922fd01 unverified Apache-2.0 (permissive)
Riemannian Normalizing Flow on Variational Wasserstein Autoencoder for Text Modeling 4 Apr 2019 kingofspace0wzz/wae-rnf-lm/model.py 7b95c648cb0fb5f2 unverified MIT (permissive)
Are Few-Shot Learning Benchmarks too Simple ? Solving them without Task Supervision at Test-Time 22 Feb 2019 gabrielhuang/centroid-networks/protonets/models/wasserstein.py 62fa5972227f4654 unverified MIT (permissive)
Wasserstein Barycenter Model Ensembling 13 Feb 2019 IBM/wasserstein-barycenters/barycenter.py 961877103f86fea9 unverified Apache-2.0 (permissive)
Particle Flow Bayes' Rule 2 Feb 2019 xinshi-chen/MetaParticleFlow/pfbayes/common/torch_utils.py 4c56e632880df4e3 unverified MIT (permissive)
Lagging Inference Networks and Posterior Collapse in Variational Autoencoders 16 Jan 2019 jxhe/vae-lagging-encoder/modules/utils.py 5efe6eb2209f6591 ran · our draft was wrong MIT (permissive)
Self-Supervised GANs via Auxiliary Rotation Loss 27 Nov 2018 vandit15/Self-Supervised-Gans-Pytorch/ops.py 6a0d455dcdcf2ec5 unverified MIT (permissive)
Self-Supervised GANs via Auxiliary Rotation Loss 27 Nov 2018 zhangqianhui/Self-Supervised-GANs/ops.py dffe333c7a3624a0 unverified Apache-2.0 (permissive)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding 11 Oct 2018 sberbank-ai/ner-bert/modules/layers/ncrf.py 8e960fbb64668568 ran · our draft was wrong fingerprinted MIT (permissive)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding 11 Oct 2018 sberbank-ai/ner-bert/modules/layers/crf.py 913ba2502c2a2780 unverified MIT (permissive)
Diverse feature visualizations reveal invariances in early layers of deep neural networks 27 Jul 2018 sacadena/diverse_feature_vis/pixel-cnn/pixel_cnn_pp/nn.py ba937f5383eb9016 unverified MIT (permissive)
ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech 19 Jul 2018 tiberiu44/TTS-Cube/cube/networks/loss.py a42f23f7210ea856 ran · honoured contract fingerprinted Apache-2.0 (permissive)
NCRF++: An Open-source Neural Sequence Labeling Toolkit 14 Jun 2018 jiesutd/PyTorchSeqLabel/model/crf.py 8e960fbb64668568 ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
Generative Modeling by Inclusive Neural Random Fields with Applications in Image Generation and Anomaly Detection 1 Jun 2018 thu-spmi/Inclusive-NRF/pytorch_generation/CIFAR_NRF_supervised.py 79526833a41be6f5 ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
Smooth Loss Functions for Deep Top-k Classification 21 Feb 2018 oval-group/smooth-topk/topk/polynomial/sp.py 17dff13c779067fd unverified MIT (permissive)
Towards Deeper Understanding of Variational Autoencoding Models 28 Feb 2017 ShengjiaZhao/Generalized-PixelVAE/pixel_cnn_pp/nn.py ad066f5de5f84073 unverified MIT (permissive)
Neural Architectures for Named Entity Recognition 4 Mar 2016 ZubinGou/NER-BiLSTM-CRF-PyTorch/src/model.py d4329236872658c9 ran · honoured contract fingerprinted MIT (permissive)
Neural Architectures for Named Entity Recognition 4 Mar 2016 yyHaker/NamedEntityRecognition/src/LSTM-CNNs-CRF/model.py ca4d0de367bcc625 ran · our draft was wrong fingerprinted no licence file found · pointer only
End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF 4 Mar 2016 identical code first harvested elsewhere d4329236872658c9 ran · honoured contract fingerprinted licence of this copy not recorded
Named Entity Recognition with Bidirectional LSTM-CNNs 26 Nov 2015 identical code first harvested elsewhere d4329236872658c9 ran · honoured contract fingerprinted licence of this copy not recorded
Bidirectional LSTM-CRF Models for Sequence Tagging 9 Aug 2015 jidasheng/bi-lstm-crf/bi_lstm_crf/model/crf.py 270d6bd48a51f2ae unverified MIT (permissive)
Transition-Based Dependency Parsing with Stack Long Short-Term Memory 29 May 2015 mstrise/dep2label/model/crf.py 8e960fbb64668568 ran · our draft was wrong fingerprinted MIT (permissive)
arXiv:2024.naacl-long.343 king-yyf/CMeKG_tools/model_cws/crf.py 390527929922fd01 unverified MIT (permissive)
arXiv:2024.naacl-long.343 king-yyf/CMeKG_tools/model_ner/crf.py 8c72bb90ead60151 unverified MIT (permissive)
arXiv:2024.naacl-long.241 jiadongzh/iacos/modelx/rnnx.py 05c860970db7fdc1 unverified Apache-2.0 (permissive)
arXiv:2024.findings-acl.760 ej0cl6/TextEE/TextEE/models/AMRIE/E2Emodel.py bd9ad74746bdeace ran · our draft was wrong Apache-2.0 (permissive)
arXiv:2023.emnlp-demo.11 jiesutd/YATO/model/crf.py 8e960fbb64668568 ran · our draft was wrong fingerprinted Apache-2.0 (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