Code that ran · page 7

Papers with a repository link where Syntology ran at least one harvested code sample, whether or not every run was a failure of Syntology's instrument (each stream's ledger splits them). On a card, when the archive marks a repository official for the paper, the Syntology 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). Each page shows two streams, newest first within each, counted separately: papers newer than the archive snapshot come from Syntology's graph Syntology; the rest are archive rows archive 2025-07-28. The two are never added together.

Newer than the archive snapshot Syntology

Cards 91–105 of 6,651 graph papers newer than 2025-07-28 with a Syntology-ran sample; this feed shows the newest 150, newest arXiv id first. Dates and the abstract sentence are from arXiv's metadata (CC0) for 6,651 of 6,651. Each of the 6,651 has a sample that ran: 5,550 with a run with no instrument failure, 1,101 where every run was a failure of Syntology's instrument.

The Shape of Time: Video-Token Contrast for Temporal Understanding in VideoLMs

ANDgate99/VT-Contrast3 Sep 2026added by Syntology

Seeing frames in order does not mean representing time.

Syntology
5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
licence: 6 of 6 pointer-only

Hardware-Aware FP4 FlashAttention-4

MrHuff/fp4-fa43 Sep 2026added by Syntology

Blackwell's 4-bit floating-point (FP4) tensor cores do not automatically make attention faster because softmax conversion and on-chip dependencies dominate once its matrix products shrink.

Syntology
18 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 6 honoured, 0 violated, 2 with no contract checked; 10 where Syntology's instrument failed) · 4 unverified
“instrument failed”: failures of Syntology's instrument, not of the code

DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training

IBM/draco3 Sep 2026added by Syntology

Reinforcement Learning from Verifiable Rewards works well when a task has a programmatic checker, but most long-horizon agent domains have none.

Syntology
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) · 5 unverified
“instrument failed”: failures of Syntology's instrument, not of the code

RARF: Region-Aware Rectified Flows for 3D Brain MRI Inpainting

TomasGuija/rarf3 Sep 2026added by Syntology

Medical image inpainting has the potential to improve automated brain MRI analysis by reconstructing healthy tissue within pathological regions.

Syntology
7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified
“instrument failed”: failures of Syntology's instrument, not of the code

Differentiable Interval Bottlenecks for Interpretable Anomaly Detection in Numerical Data

DiffInt/diffint3 Sep 2026added by Syntology

Reconstruction-based anomaly detectors are accurate but opaque: a deep autoencoder flags a sample without telling a practitioner which feature ranges made it anomalous.

Syntology
5 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; 1 where Syntology's instrument failed) · 1 unverified
“instrument failed”: failures of Syntology's instrument, not of the code

Urban Boundaries, Social Barriers: A Benchmark and Vision-Centric Framework for Mapping Gated Communities and Equity Implications

MinweiZhao/GBA-GCs3 Sep 2026added by Syntology

Communities are fundamental spatial units that shape urban form and social life.

Syntology
2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
licence: 2 of 2 pointer-only

OBER+: Continuity-Aware Reporting and Traceable Continuous Improvement in Outcome-Based Education

Elakkiya16/OBER_Plus3 Sep 2026added by Syntology

Institutions practising outcome-based education compute learning outcome attainment routinely, while reviews of curriculum analytics report an absence of evidence on how that computation informs decisions.

Syntology
12 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; 9 where Syntology's instrument failed) · 0 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
licence: 12 of 12 pointer-only

ENEAS: Embedding-guided Neural Ensemble for Adaptive Segmentation

speridlabs/eneas3 Sep 2026added by Syntology

We present ENEAS, a unified, text-promptable method for instance tracking and semantic discovery.

Syntology
8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
licence: 1 of 11 pointer-only

SimSkill: A Lifelong Learning AI Agent for Autonomous Mastery of Traffic Simulation

qiliuchn/SimSkill-V13 Sep 2026added by Syntology

As large language models (LLMs) become increasingly capable, the long-term value of AI systems depends not only on solving individual requests, but also on transforming experience and accumulated knowledge into durable…

Syntology
5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified
“instrument failed”: failures of Syntology's instrument, not of the code

Fill My Mirror: Geometry-Constrained Mirror Inpainting

OfekBasson/Fill-My-Mirror3 Sep 2026added by Syntology

Mirrors are common in real-world images, yet producing geometrically consistent reflections with generative models remains challenging.

Syntology
4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
licence: 1 of 6 pointer-only

Artificial Intelligence for Energy Optimization in Data Centers

Kimalice/AI-for-Energy-Optimization-in-Data-Centers-Closing-the-Optimizer-Load-Loop3 Sep 2026added by Syntology

Data centers are increasingly optimized by artificial intelligence and, at the same time, increasingly loaded by it.

Syntology
7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
licence: 7 of 7 pointer-only

Federated Causal Discovery via Regression-Directed Cumulants

ptorrijos99/FedLiNGAM3 Sep 2026added by Syntology

In this paper we study linear non-Gaussian acyclic models (LiNGAM) when used in federated environments.

Syntology
9 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; 5 where Syntology's instrument failed) · 7 unverified
“instrument failed”: failures of Syntology's instrument, not of the code

Semantic-Aware Subgraph State Space Model for WSI Classification in Histopathology

HLSvois/SASG-SSM3 Sep 2026added by Syntology

Histopathological subtyping relies on the recognition of characteristic histological patterns.

Syntology
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
“instrument failed”: failures of Syntology's instrument, not of the code
every run of this paper's code is a failure of Syntology's instrument, not of the code
licence: 1 of 1 pointer-only

Understanding Autonomous Driving Datasets by Describing Differences between Image Subsets in Natural Language

KIT-MRT/AD-Diff3 Sep 2026added by Syntology

Understanding the composition of large-scale autonomous driving datasets is essential for safety, robustness, and reliable operation across domains.

Syntology
7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified
“instrument failed”: failures of Syntology's instrument, not of the code

EraseSAE: Surgical Concept Erasure in Text-to-Video Diffusion Models via Sparse Autoencoders

HiDream-ai/EraseSAE3 Sep 2026added by Syntology

Recent advances in text-to-video (T2V) diffusion models have demonstrated remarkable generative capabilities, yet their reliance on loosely curated training data raises pressing safety and copyright concerns.

Syntology
23 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 1 violated, 18 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
licence: 24 of 24 pointer-only

From the archive archive 2025-07-28 — filtered to papers Syntology ran Syntology

Cards 91–105 of 38,710 archive papers with a code link, filtered to those where Syntology ran at least one sample (the archive chip labels the rows, the Syntology chip labels the filter; the count is the archive rows that pass it); this feed shows the newest 150, archive date first (newest archive date 2025-07-17). Within a month, dated rows come first, then the 1,274 undated rows placed by the month in their arXiv id. 8 archive papers with neither a date nor an arXiv id cannot be placed and are not listed. Each of the 38,710 has a sample that ran: 31,633 with a run with no instrument failure, 7,077 where every run was a failure of Syntology's instrument.

FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language

huggingface/fineweb-2 official26 Jun 2025archive 2025-07-28

Pre-training state-of-the-art large language models (LLMs) requires vast amounts of clean and diverse text data.

Syntology
official (archive's flag): 2 ran
2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified
“instrument failed”: failures of Syntology's instrument, not of the code

Vector Contrastive Learning For Pixel-Wise Pretraining In Medical Vision

yutinghe-list/cover officialpytorch25 Jun 2025archive 2025-07-28

Contrastive learning (CL) has become a cornerstone of self-supervised pretraining (SSP) in foundation models, however, extending CL to pixel-wise representation, crucial for medical vision, remains an open problem.

Syntology
official (archive's flag): 8 ran
8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
licence: 9 of 9 pointer-only

The Ideation-Execution Gap: Execution Outcomes of LLM-Generated versus Human Research Ideas

NoviScl/AI-Researcher official25 Jun 2025archive 2025-07-28

Large Language Models (LLMs) have shown promise in accelerating the scientific research pipeline.

Syntology
official (archive's flag): 4 ran
4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified
“instrument failed”: failures of Syntology's instrument, not of the code

Stochastic Parameter Decomposition

goodfire-ai/spd officialjax25 Jun 2025archive 2025-07-28

A key step in reverse engineering neural networks is to decompose them into simpler parts that can be studied in relative isolation.

Syntology
official (archive's flag): 4 ran
4 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; 3 where Syntology's instrument failed) · 4 unverified
“instrument failed”: failures of Syntology's instrument, not of the code

OTSurv: A Novel Multiple Instance Learning Framework for Survival Prediction with Heterogeneity-aware Optimal Transport

y-research-sbu/otsurv officialpytorch25 Jun 2025archive 2025-07-28

Survival prediction using whole slide images (WSIs) can be formulated as a multiple instance learning (MIL) problem.

Syntology
official (archive's flag): 8 ran
8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
licence: 10 of 10 pointer-only

Towards Community-Driven Agents for Machine Learning Engineering

comind-ml/comind official25 Jun 2025archive 2025-07-28

Large language model-based machine learning (ML) agents have shown great promise in automating ML research.

Syntology
official (archive's flag): 2 ran
2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified
“instrument failed”: failures of Syntology's instrument, not of the code

DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation

apple/ml-diffucoder officialpytorch25 Jun 2025archive 2025-07-28

Diffusion large language models (dLLMs) are compelling alternatives to autoregressive (AR) models because their denoising models operate over the entire sequence.

Syntology
official (archive's flag): 5 ran
5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
licence: 7 of 7 pointer-only

PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models

soufiane001/plop officialpytorch25 Jun 2025archive 2025-07-28

Low-Rank Adaptation (LoRA) is a widely used finetuning method for large models.

Syntology
official (archive's flag): 15 ran
15 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 3 honoured, 1 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 6 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
licence: 21 of 21 pointer-only

Reinforcement Learning Increases Wind Farm Power Production by Enabling Closed-Loop Collaborative Control

admole/wind-rl officialpytorch25 Jun 2025archive 2025-07-28

Traditional wind farm control operates each turbine independently to maximize individual power output.

Syntology
official (archive's flag): 4 ran
4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified
“instrument failed”: failures of Syntology's instrument, not of the code

Pay Less Attention to Deceptive Artifacts: Robust Detection of Compressed Deepfakes on Online Social Networks

manyilee/plada officialpytorch25 Jun 2025archive 2025-07-28

With the rapid advancement of deep learning, particularly through generative adversarial networks (GANs) and diffusion models (DMs), AI-generated images, or ``deepfakes", have become nearly indistinguishable from real…

Syntology
official (archive's flag): 13 ran
13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 3 honoured, 1 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
licence: 18 of 18 pointer-only

OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling

gair-nlp/octothinker officialpytorch25 Jun 2025archive 2025-07-28

Different base language model families, such as Llama and Qwen, exhibit divergent behaviors during post-training with reinforcement learning (RL), especially on reasoning-intensive tasks.

Syntology
official (archive's flag): 16 ran
16 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
licence: 4 of 17 pointer-only

TAPS: Tool-Augmented Personalisation via Structured Tagging

grill-lab/taps official25 Jun 2025archive 2025-07-28

Recent advancements in tool-augmented large language models have enabled them to interact with external tools, enhancing their ability to perform complex user tasks.

Syntology
official (archive's flag): 8 ran
8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified
“instrument failed”: failures of Syntology's instrument, not of the code

Q-resafe: Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models

thecommonirin/qresafe officialpytorch25 Jun 2025archive 2025-07-28

Quantized large language models (LLMs) have gained increasing attention and significance for enabling deployment in resource-constrained environments.

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
“instrument failed”: failures of Syntology's instrument, not of the code
every run of this paper's code is a failure of Syntology's instrument, not of the code
licence: 2 of 2 pointer-only

Language Modeling by Language Models

allenai/genesys officialjax25 Jun 2025archive 2025-07-28

Can we leverage LLMs to model the process of discovering novel language model (LM) architectures?

Syntology
official (archive's flag): 5 ran
5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified
“instrument failed”: failures of Syntology's instrument, not of the code

High-Resolution Live Fuel Moisture Content (LFMC) Maps for Wildfire Risk from Multimodal Earth Observation Data

allenai/lfmc official25 Jun 2025archive 2025-07-28

Wildfires are increasing in intensity and severity at an alarming rate.

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
“instrument failed”: failures of Syntology's instrument, not of the code
every run of this paper's code is a failure of Syntology's instrument, not of the code

The feed is static: 10 pages of up to 15 cards per stream, rebuilt with the site. Older papers are reachable from task, dataset and method pages and from search. No repository stars are tracked and nothing here is ranked by popularity. Machine-readable twin: JSON.