Browse State-of-the-Art › Few-Shot Image Classification

Few-Shot Image Classification

220 papers with code · 89 benchmarks · 24 datasets archive 2025-07-28

Computer Vision

Few-Shot Image Classification is a computer vision task that involves training machine learning models to classify images into predefined categories using only a few labeled examples of each category (typically < 6 examples). The goal is to enable models to recognize and classify new images with minimal supervision and limited data, without having to train on large datasets. (typically < 6 examples)

( Image credit: Learning Embedding Adaptation for Few-Shot Learning )

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

89 leaderboard tables shown for this task, 89 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 89 until expanded.

Syntology 1 newer paper was judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): Mini-Imagenet 5-way (1-shot) (1 judged, 0 placed), Mini-Imagenet 5-way (5-shot) (1 judged, 0 placed), CIFAR-FS 5-way (5-shot) (1 judged, 0 placed), CIFAR-FS 5-way (1-shot) (1 judged, 0 placed), CUB 200 5-way 1-shot (1 judged, 0 placed), CUB 200 5-way 5-shot (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
Mini-Imagenet 5-way (1-shot) (105 rows) SgVA-CLIP SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language... code — Compare
Mini-Imagenet 5-way (5-shot) (95 rows) SgVA-CLIP SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language... code — Compare
Tiered ImageNet 5-way (5-shot) (51 rows) CAML [Laion-2b] Context-Aware Meta-Learning code Syntology official (archive's flag): 5 ran · 5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified Compare
Tiered ImageNet 5-way (1-shot) (49 rows) CAML [Laion-2b] Context-Aware Meta-Learning code Syntology official (archive's flag): 5 ran · 5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified Compare
CIFAR-FS 5-way (5-shot) (39 rows) CAML [Laion-2b] Context-Aware Meta-Learning code Syntology official (archive's flag): 5 ran · 5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified Compare
CIFAR-FS 5-way (1-shot) (38 rows) PT+MAP+SF+SOT (transductive) The Self-Optimal-Transport Feature Transform code — Compare
CUB 200 5-way 1-shot (36 rows) PT+MAP+SF+SOT (transductive) The Self-Optimal-Transport Feature Transform code — Compare
CUB 200 5-way 5-shot (32 rows) CAML [Laion-2b] Context-Aware Meta-Learning code Syntology official (archive's flag): 5 ran · 5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified Compare
FC100 5-way (1-shot) (22 rows) BAVARDAGE Adaptive Dimension Reduction and Variational Inference for... — — Compare
FC100 5-way (5-shot) (22 rows) BAVARDAGE Adaptive Dimension Reduction and Variational Inference for... — — Compare
Meta-Dataset (22 rows) SMAT (DINO-VIT-Base-16-224) Unleashing the Power of Meta-tuning for Few-shot Generalization... code Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified Compare
OMNIGLOT - 1-Shot, 20-way (20 rows) GCR Few-Shot Learning with Global Class Representations code Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified Compare
OMNIGLOT - 5-Shot, 20-way (19 rows) MC2+ Meta-Curvature code — Compare
OMNIGLOT - 1-Shot, 5-way (17 rows) MC2+ Meta-Curvature code — Compare
Mini-ImageNet - 1-Shot Learning (16 rows) PT+MAP Leveraging the Feature Distribution in Transfer-based Few-Shot Learning code Syntology official (archive's flag): 3 ran · 22 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 9 where Syntology's instrument failed) · 4 unverified Compare
OMNIGLOT - 5-Shot, 5-way (16 rows) DCN6-E Decoder Choice Network for Meta-Learning code — Compare
Mini-Imagenet 10-way (1-shot) (14 rows) Transductive CNAPS + FETI Enhancing Few-Shot Image Classification with Unlabelled Examples code Syntology official (archive's flag): 6 ran · 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified Compare
Mini-Imagenet 10-way (5-shot) (14 rows) Transductive CNAPS + FETI Enhancing Few-Shot Image Classification with Unlabelled Examples code Syntology official (archive's flag): 6 ran · 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified Compare
Meta-Dataset Rank (13 rows) URT A Universal Representation Transformer Layer for Few-Shot Image... code — Compare
Tiered ImageNet 10-way (1-shot) (13 rows) Transductive CNAPS + FETI Enhancing Few-Shot Image Classification with Unlabelled Examples code Syntology official (archive's flag): 6 ran · 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified Compare
Tiered ImageNet 10-way (5-shot) (13 rows) Transductive CNAPS + FETI Enhancing Few-Shot Image Classification with Unlabelled Examples code Syntology official (archive's flag): 6 ran · 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified Compare
Dirichlet Mini-Imagenet (5-way, 1-shot) (12 rows) BAVARDAGE Adaptive Dimension Reduction and Variational Inference for... — — Compare
Dirichlet Mini-Imagenet (5-way, 5-shot) (12 rows) BAVARDAGE Adaptive Dimension Reduction and Variational Inference for... — — Compare
Mini-ImageNet-CUB 5-way (1-shot) (12 rows) TRIDENT Transductive Decoupled Variational Inference for Few-Shot Classification code Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified Compare
Bongard-HOI (9 rows) Human (Amateur) Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for... code — Compare
Dirichlet Tiered-Imagenet (5-way, 1-shot) (9 rows) BAVARDAGE Adaptive Dimension Reduction and Variational Inference for... — — Compare
Dirichlet Tiered-Imagenet (5-way, 5-shot) (9 rows) α-TIM Realistic Evaluation of Transductive Few-Shot Learning code Syntology official (archive's flag): 6 ran · 6 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified Compare
Dirichlet CUB-200 (5-way, 1-shot) (8 rows) BAVARDAGE Adaptive Dimension Reduction and Variational Inference for... — — Compare
Dirichlet CUB-200 (5-way, 5-shot) (8 rows) BAVARDAGE Adaptive Dimension Reduction and Variational Inference for... — — Compare
ImageNet - 1-shot (8 rows) ViT-MoE-15B (Every-2) Scaling Vision with Sparse Mixture of Experts code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
ImageNet - 5-shot (8 rows) ViT-MoE-15B (Every-2) Scaling Vision with Sparse Mixture of Experts code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
ImageNet-FS (2-shot, novel) (8 rows) KGTN-ens (ResNet-50, h+g, max) KGTN-ens: Few-Shot Image Classification with Knowledge Graph Ensembles code — Compare
ImageNet-FS (5-shot, all) (8 rows) KGTN-ens (ResNet-50, h+g, max) KGTN-ens: Few-Shot Image Classification with Knowledge Graph Ensembles code — Compare
Mini-ImageNet-CUB 5-way (5-shot) (8 rows) TRIDENT Transductive Decoupled Variational Inference for Few-Shot Classification code Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified Compare
ImageNet - 10-shot (7 rows) MAWS (ViT-6.5B) The effectiveness of MAE pre-pretraining for billion-scale pretraining code — Compare
ImageNet-FS (1-shot, novel) (7 rows) KGTN-ens (ResNet-50, h+g, max) KGTN-ens: Few-Shot Image Classification with Knowledge Graph Ensembles code — Compare
Mini-Imagenet 20-way (1-shot) (6 rows) TIM-GD Transductive Information Maximization For Few-Shot Learning code Syntology official (archive's flag): 6 ran · 9 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified Compare
Mini-Imagenet 20-way (5-shot) (6 rows) TIM-GD Transductive Information Maximization For Few-Shot Learning code Syntology official (archive's flag): 6 ran · 9 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified Compare
Stanford Dogs 5-way (5-shot) (6 rows) MML(KL) Multi-level Metric Learning for Few-shot Image Recognition — — Compare
Stanford Cars 5-way (1-shot) (6 rows) MATANet Multi-scale Adaptive Task Attention Network for Few-Shot Learning — — Compare
Stanford Cars 5-way (5-shot) (6 rows) MATANet Multi-scale Adaptive Task Attention Network for Few-Shot Learning — — Compare
CUB-200-2011 - 0-Shot (5 rows) Word CNN-RNN (DS-SJE Embedding) Learning Deep Representations of Fine-grained Visual Descriptions code — Compare
ImageNet - 0-Shot (5 rows) DebiasPL (ResNet50) Debiased Learning from Naturally Imbalanced Pseudo-Labels code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified Compare
Mini-Imagenet 5-way (10-shot) (5 rows) PT+MAP Leveraging the Feature Distribution in Transfer-based Few-Shot Learning code Syntology official (archive's flag): 3 ran · 22 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 9 where Syntology's instrument failed) · 4 unverified Compare
CUB 200 50-way (0-shot) (4 rows) Prototypical Networks Prototypical Networks for Few-shot Learning code Syntology official (archive's flag): 1 ran · 50 ran (of which 14 constructed an object rather than computing a result; 29 with no instrument failure: 5 honoured, 0 violated, 24 with no contract checked; 21 where Syntology's instrument failed) · 14 unverified Compare
Caltech-256 5-way (1-shot) (3 rows) UL-Hopfield (ULH) Unsupervised Learning using Pretrained CNN and Associative Memory Bank — — Compare
CUB-200 - 0-Shot Learning (3 rows) TAFE-Net TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified Compare
ImageNet-FS (5-shot, novel) (3 rows) KGTN-ens (ResNet-50, h+g, mean) KGTN-ens: Few-Shot Image Classification with Knowledge Graph Ensembles code — Compare
ORBIT Clutter Video Evaluation (3 rows) ProtoNetsVideo Improving ProtoNet for Few-Shot Video Object Recognition: Winner... code — Compare
Stanford Dogs 5-way (1-shot) (3 rows) MML(KL) Multi-level Metric Learning for Few-shot Image Recognition — — Compare
CIFAR100 5-way (1-shot) (2 rows) UL-Hopfield (ULH) Unsupervised Learning using Pretrained CNN and Associative Memory Bank — — Compare
ImageNet (1-shot) (2 rows) TRAML Boosting Few-Shot Learning With Adaptive Margin Loss — — Compare
ImageNet-FS (10-shot, novel) (2 rows) KGTN-ens (ResNet-50, h+g, max) KGTN-ens: Few-Shot Image Classification with Knowledge Graph Ensembles code — Compare
ImageNet-FS (1-shot, all) (2 rows) KGTN-ens (ResNet-50, h+g, max) KGTN-ens: Few-Shot Image Classification with Knowledge Graph Ensembles code — Compare
ImageNet-FS (2-shot, all) (2 rows) KGTN-ens (ResNet-50, h+g, max) KGTN-ens: Few-Shot Image Classification with Knowledge Graph Ensembles code — Compare
ImageNet-FS (10-shot, all) (2 rows) KGTN (ResNet-50) Knowledge Graph Transfer Network for Few-Shot Recognition code — Compare
Mini-ImageNet to CUB - 5 shot learning (2 rows) TIM-GD Transductive Information Maximization For Few-Shot Learning code Syntology official (archive's flag): 6 ran · 9 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified Compare
OMNIGLOT-EMNIST 5-way (1-shot) (2 rows) HyperShot HyperShot: Few-Shot Learning by Kernel HyperNetworks code — Compare
OMNIGLOT-EMNIST 5-way (5-shot) (2 rows) HyperShot HyperShot: Few-Shot Learning by Kernel HyperNetworks code — Compare
ORBIT Clean Video Evaluation (2 rows) SimpleCNAPs + LITE Memory Efficient Meta-Learning with Large Images code Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified Compare
SUN - 0-Shot (2 rows) Synthesised Classifier Synthesized Classifiers for Zero-Shot Learning code Syntology 0 ran · 3 unverified Compare
aPY - 0-Shot (1 row) TAFE-Net TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified Compare
AWA - 0-Shot (1 row) Synthesised Classifier Synthesized Classifiers for Zero-Shot Learning code Syntology 0 ran · 3 unverified Compare
AWA1 - 0-Shot (1 row) TAFE-Net TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified Compare
AWA2 - 0-Shot (1 row) TAFE-Net TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified Compare
Caltech-256 5-way (5-shot) (1 row) MergedNet-Concat MergedNET: A simple approach for one-shot learning in siamese... code — Compare
Caltech101 (1 row) PRE PRE: Vision-Language Prompt Learning with Reparameterization Encoder code — Compare
CIFAR-FS - 1-Shot Learning (1 row) pseudo-shots Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks code — Compare
CIFAR-FS - 5-Shot Learning (1 row) pseudo-shots Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks code — Compare
CUB-200-2011 5-way (1-shot) (1 row) MATANet Multi-scale Adaptive Task Attention Network for Few-Shot Learning — — Compare
CUB-200-2011 5-way (5-shot) (1 row) MATANet Multi-scale Adaptive Task Attention Network for Few-Shot Learning — — Compare
CUB 200 5-way (1 row) EASY 3xResNet12 (transductive) EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art... code — Compare
FC100 5-way (10-shot) (1 row) MTL Meta-Transfer Learning for Few-Shot Learning code — Compare
Fewshot-CIFAR100 - 1-Shot Learning (1 row) pseudo-shots Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks code — Compare
Fewshot-CIFAR100 - 5-Shot Learning (1 row) pseudo-shots Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks code — Compare
Flowers-102 - 0-Shot (1 row) Word CNN-RNN (DS-SJE Embedding) Learning Deep Representations of Fine-grained Visual Descriptions code — Compare
iNaturalist (227-way multi-shot) (1 row) LaplacianShot Laplacian Regularized Few-Shot Learning code Syntology 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified Compare
iNaturalist 2018 - 1-shot (1 row) MAWS (ViT-2B) The effectiveness of MAE pre-pretraining for billion-scale pretraining code — Compare
iNaturalist 2018 - 5-shot (1 row) MAWS (ViT-2B) The effectiveness of MAE pre-pretraining for billion-scale pretraining code — Compare
iNaturalist 2018 - 10-shot (1 row) MAWS (ViT-2B) The effectiveness of MAE pre-pretraining for billion-scale pretraining code — Compare
mini-ImageNet - 100-Way (1 row) GCR Few-Shot Learning with Global Class Representations code Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified Compare
miniImagenet → CUB (5-way 1-shot) (1 row) LaplacianShot Laplacian Regularized Few-Shot Learning code Syntology 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified Compare
miniImagenet → CUB (5-way 5-shot) (1 row) LaplacianShot Laplacian Regularized Few-Shot Learning code Syntology 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified Compare
OMNIGLOT - 1-Shot, 423 way (1 row) APL Adaptive Posterior Learning: few-shot learning with a... code — Compare
OMNIGLOT - 1-Shot, 1000 way (1 row) APL Adaptive Posterior Learning: few-shot learning with a... code — Compare
OMNIGLOT - 5-Shot, 423 way (1 row) APL Adaptive Posterior Learning: few-shot learning with a... code — Compare
OMNIGLOT - 5-Shot, 1000 way (1 row) APL Adaptive Posterior Learning: few-shot learning with a... code — Compare
Oxford 102 Flower (1 row) RS-FSL Rich Semantics Improve Few-shot Learning — — Compare
UT Zappos50K (1 row) MScon Multi-Similarity Contrastive Learning — — Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

24 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

3 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 353 · with a code link: 220 · where Syntology ran a sample: 80 (67 with a run with no instrument failure, 13 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (80 of 353 tagged: 67 with a run with no instrument failure, 13 where every run was a failure of Syntology's instrument)

Page 1 of 4: papers 1 to 100 of 353, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 53 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

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