Papers with Code told you where the code is. We ran it. In this build, Syntology harvested 294,260 distinct code samples from the repositories of 51,887 papers: 211,169 ran (of which 22,388 constructed an object rather than computing a result; 147,384 with no instrument failure: 15,745 honoured, 5,703 violated, 125,936 with no contract checked; 63,785 where Syntology's instrument failed) · 83,091 unverified. Each sample is one function or class, executed on a synthesized input; the 63,785 where Syntology's instrument failed (a contract draft that was wrong, or a contract check that could not run) are failures of Syntology's instrument, not of the code, and the 83,091 unverified were harvested and not run. A sample that ran is not a sample shown to be correct, and a paper with a sample that ran is not a reproduced paper.
Code with Papers is a free community app by Syntology, built on the archived Papers with Code data (last public snapshot 2025-07-28): its papers, benchmarks, datasets and methods, plus one thing the archive never held: for the papers whose code Syntology harvested, each code sample is marked with whether it ran, and what happened when it did. No account is needed.
Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.
218,852papers with code archive 2025-07-28
11,026benchmarks archive 2025-07-28
12,168datasets archive 2025-07-28
2,289methods archive 2025-07-28
48,557 of 51,887papers with harvested code have a sample that ran: 40,099 with at least one run that had no instrument failure, 8,458 where every run is a failure of Syntology's instrument, not of the code 294,260 samples: 211,169 ran (of which 22,388 constructed an object rather than computing a result; 147,384 with no instrument failure: 15,745 honoured, 5,703 violated, 125,936 with no contract checked; 63,785 where Syntology's instrument failed) · 83,091 unverified Syntology
132results placed on 95 archive leaderboards from newer papers 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read) · see the 95 leaderboards Syntology
Archive figures are counted from the snapshot at build time; a benchmark is a leaderboard table with at least one row, as on Browse State-of-the-Art (544 archive tables have no rows and are not counted). The Syntology figure counts papers in Syntology's graph with at least one harvested sample, with or without an archive code link, and how many of them have a sample that ran; 3,330 have harvested code and nothing that ran. “Ran” means executed on a synthesized fixture, not that the paper's results reproduce. “With no instrument failure” counts the samples whose record is about the code: honoured or violated the contract Syntology drafted, or ran with no contract checked; “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. The totals include 2,441 papers that have no page here (why). The placed-results figure counts entries from newer papers' own tables: a model pointed at the cell, the number was read from it and checked against the leaderboard's metric, dataset, split and scale, and an independent check accepted it; they are listed below each leaderboard's archive rows, never ranked among them (how, and how it was measured). Syntology has checked 8,886 of the 18,637 papers on this site that are newer than the archive (for 3,717 of them no archive leaderboard matched the paper's tables, so there was nothing further to check); 733 were read and have nothing to place (arXiv has no HTML version of the paper, or that version has no tables), 41 could not be read (the extractor's reply could not be parsed), and results from the other 8,977 appear after they are checked. What “ran” means · What is not shown.
Which papers have a page. An archive paper has one when the archive gives it a code link, a leaderboard row, or an introduced dataset or method, or when Syntology's graph links it to code; archive papers with only an abstract have none. A paper newer than the snapshot has a page only when Syntology's graph links it to a code repository, or when one of its results was placed on an archive leaderboard, so a widely discussed recent paper is missing until that link exists. Every archive paper left out is counted on what is not shown. A newer paper that Syntology's graph does not link to code is not held by the site and is not counted. Papers in Syntology's layer with harvested samples and no page here: 2,441. Of these, 1,954 carry an id in the export that is not an arXiv id (731 ACL Anthology ids, 489 CVF open access ids, 439 AAAI ids, 117 IJCAI ids, 96 OpenReview ids, 82 bare-number ids), and 487 have an arXiv id from before the snapshot that the archive catalogue does not hold. Their 18,061 sample links, and the 2,343 of these papers with a sample that ran, are counted in the site's sample and paper totals (the ledger).
How current this is. Archive snapshot 2025-07-28. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. Nothing on the site changes between builds.
From Syntology
This app shows one part of what Syntology builds: the harvested code and whether it ran, next to the archive. The rest is on Syntology's own services.
Syntology's graph of AI and machine-learning research: papers, authors, citations, methods and code, with every relation tagged with where it came from. Ask it a question in plain English and the sources come back under the answer.
Papers and the citations between them, drawn as one navigable map. A link of the form app.syntology.ai/?focus=<arXiv id> opens the map on one paper when the Atlas holds it.
The same harvested code with its run record, for agents and scripts: get_harvested_code_for_paper lists every function and class harvested from a paper and whether each one ran; get_code fetches one stored sample. A trial token needs no account and no card.
Code that ran
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 1–15 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.
Offline reinforcement learning aims to learn a policy solely from fixed datasets, which often contain multimodal action distributions.
Syntology 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 2 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified “instrument failed”: failures of Syntology's instrument, not of the code licence: 11 of 11 pointer-only
Automatic speech recognition (ASR) systems, trained on paired speech-text data, have been improved by leveraging language models (LMs) trained on text-only data.
Syntology 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 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
Brain signal analysis is essential for both neuroscience research and clinical diagnostics, yet current approaches face critical limitations.
Syntology 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified “instrument failed”: failures of Syntology's instrument, not of the code licence: 1 of 5 pointer-only
EEG foundation models such as BIOT, LaBraM, and EEGMamba have achieved remarkable performance in neural signal decoding, but their black-box nature limits clinical trust and neuroscientific validation.
Syntology 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified “instrument failed”: failures of Syntology's instrument, not of the code licence: 9 of 9 pointer-only
Keyed watermark detection tests dependence between observed tokens and pseudorandom variables reconstructed from a secret key.
Syntology 17 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 4 honoured, 1 violated, 6 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified “instrument failed”: failures of Syntology's instrument, not of the code
Part-level control is essential for modern 3D asset creation, where objects are frequently edited, reused, animated, or fabricated through their individual components.
Syntology 11 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 9 where Syntology's instrument failed) · 2 unverified “instrument failed”: failures of Syntology's instrument, not of the code licence: 13 of 13 pointer-only
As deep learning models become fundamental to modern healthcare, the "Right to be Forgotten" mandated by privacy regulations like GDPR and HIPAA necessitates effective machine unlearning (MU) to remove sensitive patient…
Syntology 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified “instrument failed”: failures of Syntology's instrument, not of the code licence: 11 of 11 pointer-only
Bayesian optimisation (BO) typically relies on a single global Gaussian process (GP) model as its surrogate model.
Syntology 6 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; 2 where Syntology's instrument failed) · 0 unverified “instrument failed”: failures of Syntology's instrument, not of the code licence: 6 of 6 pointer-only
We describe our submission to the MedReason 2026 challenge, covering multiple-choice (MCQ) and open-ended (OE) medical visual question answering (VQA) under fully offline, containerized inference.
Syntology 8 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; 5 where Syntology's instrument failed) · 1 unverified “instrument failed”: failures of Syntology's instrument, not of the code
BraTS-GoAT evaluates tumor segmentation across heterogeneous populations.
Syntology 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) · 1 unverified “instrument failed”: failures of Syntology's instrument, not of the code
Deep learning models have become the standard tool for document rectification and illumination correction, yet their performance is fundamentally bound by their training data.
Syntology 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified “instrument failed”: failures of Syntology's instrument, not of the code
End-to-end Supervised Graph Prediction (SGP) requires a permutation-invariant loss to compare predicted and target graphs with arbitrary node orderings.
Syntology 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
Vessel segmentation in X-ray coronary angiography (XCA) is a fundamental step for quantitative coronary analysis and subsequent assessment of coronary artery disease.
Syntology 18 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 4 honoured, 0 violated, 5 with no contract checked; 9 where Syntology's instrument failed) · 4 unverified “instrument failed”: failures of Syntology's instrument, not of the code
Kolmogorov-Arnold Networks (KANs) with spline activations have recently shown promise for interpretable function approximation.
Syntology 3 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; 2 where Syntology's instrument failed) · 1 unverified “instrument failed”: failures of Syntology's instrument, not of the code licence: 4 of 4 pointer-only
We propose a pre-fine-tuning probing method for Parameter-Efficient Fine-Tuning (PEFT) layer selection, aiming to obtain more stable and higher gains with fewer trainable parameters when adapting large vision--language…
Syntology 4 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; 3 where Syntology's instrument failed) · 0 unverified “instrument failed”: failures of Syntology's instrument, not of the code
From the archive archive 2025-07-28— filtered to papers Syntology ranSyntology
Cards 1–15 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.
Language models (LMs) are challenging to adapt to new data distributions by simple finetuning.
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 licence: 1 of 1 pointer-only
Syntology official (archive's flag): 6 ran 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified “instrument failed”: failures of Syntology's instrument, not of the code licence: 8 of 8 pointer-only
Multimodal large language models (MLLMs) have revolutionized cross-modal understanding but continue to struggle with hallucinations - fabricated content contradicting visual inputs.
Syntology official (archive's flag): 7 ran 7 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; 7 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
Syntology official (archive's flag): 13 ran 13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified “instrument failed”: failures of Syntology's instrument, not of the code licence: 13 of 13 pointer-only
Large Language Model (LLM) agents have shown great potential for solving real-world problems and promise to be a solution for tasks automation in industry.
Syntology official (archive's flag): 6 ran 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 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
Syntology official (archive's flag): 8 ran 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified “instrument failed”: failures of Syntology's instrument, not of the code licence: 8 of 8 pointer-only
Achieving equity in healthcare accessibility requires lightweight yet high-performance solutions for medical image segmentation, particularly in resource-limited settings.
Syntology official (archive's flag): 6 ran 6 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; 3 where Syntology's instrument failed) · 1 unverified “instrument failed”: failures of Syntology's instrument, not of the code licence: 1 of 7 pointer-only
Syntology official (archive's flag): 9 ran 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified “instrument failed”: failures of Syntology's instrument, not of the code
The ubiquitous independence assumption among symbolic concepts in neurosymbolic (NeSy) predictors is a convenient simplification: NeSy predictors use it to speed up probabilistic reasoning.
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 licence: 1 of 1 pointer-only
Syntology official (archive's flag): 9 ran 9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified “instrument failed”: failures of Syntology's instrument, not of the code
Large language models (LLMs) based on Transformer Decoders have become the preferred choice for conversational generative AI.
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 licence: 1 of 1 pointer-only
Diffusion-based large language models (dLLMs) have recently emerged as a powerful alternative to autoregressive LLMs, offering faster inference and greater interactivity via parallel decoding and bidirectional modeling.
Syntology official (archive's flag): 16 ran 16 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; 13 where Syntology's instrument failed) · 1 unverified “instrument failed”: failures of Syntology's instrument, not of the code licence: 15 of 17 pointer-only
Medical language-guided segmentation, integrating textual clinical reports as auxiliary guidance to enhance image segmentation, has demonstrated significant improvements over unimodal approaches.
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: 0 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
We propose AdaMuon, an adaptive learning-rate framework built upon the recently validated Muon optimizer, which has demonstrated substantial efficiency gains over AdamW in large-scale model training.
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
Cross-view localization, the task of estimating a camera's 3-degrees-of-freedom (3-DoF) pose by aligning ground-level images with satellite images, is crucial for large-scale outdoor applications like autonomous…
Syntology official (archive's flag): 7 ran 7 ran (of which 2 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) · 2 unverified “instrument failed”: failures of Syntology's instrument, not of the code licence: 9 of 9 pointer-only
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.