Papers › Learning Transferable Visual Models From Natural Language Supervision
Learning Transferable Visual Models From Natural Language Supervision
26 Feb 2021arXiv:2103.00020archive 2025-07-28
Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, Ilya Sutskever
State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories. This restricted form of supervision limits their generality and usability since additional labeled data is needed to specify any other visual concept. Learning directly from raw text about images is a promising alternative which leverages a much broader source of supervision. We demonstrate that the simple pre-training task of predicting which caption goes with which image is an efficient and scalable way to learn SOTA image representations from scratch on a dataset of 400 million (image, text) pairs collected from the internet. After pre-training, natural language is used to reference learned visual concepts (or describe new ones) enabling zero-shot transfer of the model to downstream tasks. We study the performance of this approach by benchmarking on over 30 different existing computer vision datasets, spanning tasks such as OCR, action recognition in videos, geo-localization, and many types of fine-grained object classification. The model transfers non-trivially to most tasks and is often competitive with a fully supervised baseline without the need for any dataset specific training. For instance, we match the accuracy of the original ResNet-50 on ImageNet zero-shot without needing to use any of the 1.28 million training examples it was trained on. We release our code and pre-trained model weights at https://github.com/OpenAI/CLIP.
In SyntologyView this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.
get_code(code_sha256="…") with a sample's code_sha256 from the list below
get_citation_path(paper_1="2103.00020", paper_2="…") with another paper's arXiv id or title
get_concepts_for_paper(arxiv_id="2103.00020")
Code
No sample from the archive's official repository (openai/CLIP) is linked to this paper; the 18 samples below come from 9 community repositories, and 2 more are identical to code Syntology harvested from another paper's repository. Syntology harvested code from openai/CLIP for another paper.
openai/CLIP: Syntology's graph links these samples to SwordBench: Evaluating Orthogonality of Steering Image Representations (arXiv:2605.16372; that paper's own run record: 14 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; 13 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method.
Syntology20 code samples: 18 from 9 repositories linked to this paper, 2 identical to code harvested from another paper's repository. Across all 20: 16 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 14 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 10 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: community (archive-listed): 18 samples from 9 repositories, 14 ran (2 with no instrument failure; 12 where Syntology's instrument failed); 2 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
No sample is linked to this paper from 35 of its repositories that Syntology harvested for other papers:
Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 7 of the 16 samples that ran have no recorded date.
82 repositories listed; official and paper-mentioned ones first.
openai/CLIPofficialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SwordBench: Evaluating Orthogonality of Steering Image Representations (arXiv:2605.16372; that paper's own run record: 14 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; 13 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method.report
FreddeFrallan/Multilingual-CLIPmentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Towards Zero-shot Cross-lingual Image Retrieval and Tagging (arXiv:2109.07622; that paper's own run record: 6 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; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method.report
Gahyeonkim09/AAPLmentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Conditional Prompt Learning for Vision-Language Models (arXiv:2203.05557; that paper's own run record: 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) · 2 unverified); nothing checks that they implement this paper's method.report
IMvision12/keras-vision-modelsmentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Swin Transformer: Hierarchical Vision Transformer using Shifted Windows (arXiv:2103.14030; that paper's own run record: 123 ran (of which 45 constructed an object rather than computing a result; 79 with no instrument failure: 6 honoured, 3 violated, 70 with no contract checked; 44 where Syntology's instrument failed) · 84 unverified); nothing checks that they implement this paper's method.report
NYU-DICE-Lab/open_clipmentioned on GitHubpytorchSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverifiedreport
SforAiDl/CountCLIPmentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Teaching CLIP to Count to Ten (arXiv:2302.12066; that paper's own run record: 0 ran · 1 unverified); nothing checks that they implement this paper's method.report
YvanG/VQGAN-CLIPmentioned on GitHubpytorchSyntology: 3 samples, 3 ran (2 instrument-failed) · 0 unverifiedreport
apple/ml-mobileclipmentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Sigmoid Loss for Language Image Pre-Training (arXiv:2303.15343; that paper's own run record: 14 ran (of which 3 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 15 unverified) and MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training (arXiv:2311.17049; that paper's own run record: 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); nothing checks that they implement this paper's method.report
azshue/TPTmentioned on GitHubpytorchSyntology: 3 samples, 2 ran (2 instrument-failed) · 1 unverifiedreport
baskargroup/Arboretummentioned on GitHubpytorchNOASSERTIONSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to BioTrove: A Large Curated Image Dataset Enabling AI for Biodiversity (arXiv:2406.17720; that paper's own run record: 5 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; 5 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method.report
borisdayma/clip-jaxmentioned on GitHubjaxApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Vision Transformers Need Registers (arXiv:2309.16588; that paper's own run record: 15 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 1 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method.report
brown-palm/ObjectPromptmentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Object-centric Video Representation for Long-term Action Anticipation (arXiv:2311.00180; that paper's own run record: 2 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; 0 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method.report
buyeah1109/KENmentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DINOv2: Learning Robust Visual Features without Supervision (arXiv:2304.07193; that paper's own run record: 39 ran (of which 13 constructed an object rather than computing a result; 32 with no instrument failure: 2 honoured, 0 violated, 30 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified) and An Interpretable Evaluation of Entropy-based Novelty of Generative Models (arXiv:2402.17287; that paper's own run record: 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); nothing checks that they implement this paper's method.report
buyeah1109/fincmentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Unsupervised Learning of Visual Features by Contrasting Cluster Assignments (arXiv:2006.09882; that paper's own run record: 13 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method.report
ericyinyzy/vlattackmentioned on GitHubtfBSD-3-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models (arXiv:2310.04655; that paper's own run record: 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) · 4 unverified); nothing checks that they implement this paper's method.report
facebookresearch/clip-rocketmentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Unsupervised Learning of Visual Features by Contrasting Cluster Assignments (arXiv:2006.09882; that paper's own run record: 13 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified), Exploring Simple Siamese Representation Learning (arXiv:2011.10566; that paper's own run record: 34 ran (of which 20 constructed an object rather than computing a result; 25 with no instrument failure: 0 honoured, 0 violated, 25 with no contract checked; 9 where Syntology's instrument failed) · 5 unverified) and Barlow Twins: Self-Supervised Learning via Redundancy Reduction (arXiv:2103.03230; that paper's own run record: 21 ran (of which 6 constructed an object rather than computing a result; 15 with no instrument failure: 2 honoured, 1 violated, 12 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method.report
facebookresearch/visslmentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles (arXiv:1603.09246; that paper's own run record: 10 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified), Unsupervised Representation Learning by Predicting Image Rotations (arXiv:1803.07728; that paper's own run record: 16 ran (of which 7 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified), BEiT: BERT Pre-Training of Image Transformers (arXiv:2106.08254; that paper's own run record: 6 ran (of which 2 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) · 5 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method.report
filipbasara0/simple-clipmentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverifiedreport
giantseaweed/decreementioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning (arXiv:2108.00352; that paper's own run record: 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) · 3 unverified); nothing checks that they implement this paper's method.report
iejMac/ScriptWritermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified); nothing checks that they implement this paper's method.report
klemens-floege/oneprotmentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ImageBind: One Embedding Space To Bind Them All (arXiv:2305.05665; that paper's own run record: 24 ran (of which 14 constructed an object rather than computing a result; 21 with no instrument failure: 1 honoured, 1 violated, 19 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method.report
linjieli222/hero_video_feature_extractormentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training (arXiv:2005.00200; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method.report
lunaproject22/rpamentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to The Abduction of Sherlock Holmes: A Dataset for Visual Abductive Reasoning (arXiv:2202.04800; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method.report
mainaksingha01/odg-clipmentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverifiedreport
mertyg/post-hoc-cbmmentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Post-hoc Concept Bottleneck Models (arXiv:2205.15480; that paper's own run record: 1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result); nothing checks that they implement this paper's method.report
michi-3000/eyeclipmentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverifiedreport
ml-jku/cloobmentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP (arXiv:2110.11316; that paper's own run record: 7 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; 6 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method.report
mlbio-epfl/turtlementioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Let Go of Your Labels with Unsupervised Transfer (arXiv:2406.07236; that paper's own run record: 3 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; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method.report
mlfoundations/open_clipmentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Sigmoid Loss for Language Image Pre-Training (arXiv:2303.15343; that paper's own run record: 14 ran (of which 3 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 15 unverified), DisCo-CLIP: A Distributed Contrastive Loss for Memory Efficient CLIP Training (arXiv:2304.08480; that paper's own run record: 1 ran (of which 1 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) · 2 unverified; the one sample that ran constructed an object rather than computing a result) and Fine-tuning CLIP Text Encoders with Two-step Paraphrasing (arXiv:2402.15120; that paper's own run record: 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) · 0 unverified); nothing checks that they implement this paper's method.report
muzairkhattak/multimodal-prompt-learningmentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MaPLe: Multi-modal Prompt Learning (arXiv:2210.03117; that paper's own run record: 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) · 2 unverified); nothing checks that they implement this paper's method.report
ramanakshay/clipmentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Sigmoid Loss for Language Image Pre-Training (arXiv:2303.15343; that paper's own run record: 14 ran (of which 3 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 15 unverified); nothing checks that they implement this paper's method.report
salesforce/pb-ovdmentioned on GitHubpytorchBSD-3-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Open Vocabulary Object Detection with Pseudo Bounding-Box Labels (arXiv:2111.09452; that paper's own run record: 6 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; 6 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method.report
sincerass/mvlptmentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Multitask Vision-Language Prompt Tuning (arXiv:2211.11720; that paper's own run record: 3 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; 3 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method.report
sithu31296/simple-object-trackingmentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Emerging Properties in Self-Supervised Vision Transformers (arXiv:2104.14294; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method.report
OML-Team/open-metric-learningpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (arXiv:2010.11929; that paper's own run record: 307 ran (of which 165 constructed an object rather than computing a result; 286 with no instrument failure: 8 honoured, 2 violated, 276 with no contract checked; 21 where Syntology's instrument failed) · 112 unverified); nothing checks that they implement this paper's method.report
PaddlePaddle/PASSLpaddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DINOv2: Learning Robust Visual Features without Supervision (arXiv:2304.07193; that paper's own run record: 39 ran (of which 13 constructed an object rather than computing a result; 32 with no instrument failure: 2 honoured, 0 violated, 30 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method.report
alibaba/EasyNLPjaxApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning Knowledge-Enhanced Contextual Language Representations for Domain Natural... (arXiv:2311.06761; that paper's own run record: 9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method.report
pwc-1/Paper-8mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MathOdyssey: Benchmarking Mathematical Problem-Solving Skills in Large Language Models... (arXiv:2406.18321; that paper's own run record: 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) · 0 unverified); nothing checks that they implement this paper's method.report
shkarupa-alex/tfcliptfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Demystifying CLIP Data (arXiv:2309.16671; that paper's own run record: 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) · 2 unverified); nothing checks that they implement this paper's method.report
towhee-io/towheepytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Perceiver: General Perception with Iterative Attention (arXiv:2103.03206; that paper's own run record: 41 ran (of which 20 constructed an object rather than computing a result; 30 with no instrument failure: 0 honoured, 2 violated, 28 with no contract checked; 11 where Syntology's instrument failed) · 14 unverified), LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval (arXiv:2103.08784; that paper's own run record: 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) and 9 more (every one in this page's JSON twin); nothing checks that they implement this paper's method.report
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
Code Syntology ran Syntology
20 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 14 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
1ran · honoured contract
1ran · violated contract
10ran · our draft was wrong
4ran; the contract check could not run
4unverified
Licence: 16 of the 20 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from 9 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 8 samples whose link to this paper records no repository are listed under one of this paper's own repositories, because identical code was harvested from it for another paper. 2 samples are listed last, in a group without a repository. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.
Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.
Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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 label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.
A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.
NYU-DICE-Lab/open_clipcommunity (archive-listed)2 samples, 1 ran (1 instrument-failed) · 1 unverified
trace_modelin 12 paperssrc/open_clip/model.pyran · our draft was wronglicence not identified · pointer only · 8e95157106d1df8c · reportfixture: signature model:callable/0/?, batch_size:int/0/int, device:device/0/? · returned TopLevelTracedModule · level recorded 2026-09-22
YvanG/VQGAN-CLIPcommunity (archive-listed)3 samples, 3 ran (2 instrument-failed) · 0 unverified
lanczosCLIP_VQGAN.pyran · our draft was wrongfingerprintedno licence file found · pointer only · 1c4b58a58ab65b12 · reportfixture: signature x:Tensor/1/float, a:float/0/float · returned Tensor · level recorded 2026-09-22
rampin 5 papersCLIP_VQGAN.pyran · honoured contractfingerprintedno licence file found · pointer only · 8c580a6820115461 · reportfixture: signature ratio:float/0/float, width:int/0/int · returned Tensor · level recorded 2026-09-22
sincin 9 papersCLIP_VQGAN.pyran · our draft was wrongfingerprintedno licence file found · pointer only · 86a64cd8e1771cc5 · reportfixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
azshue/TPTcommunity (archive-listed)3 samples, 2 ran (2 instrument-failed) · 1 unverified
avg_entropyin 6 paperstpt_classification.pyidentical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its ownran · our draft was wrongfingerprintedlicence of this copy not recorded · 441ae80dd4f616f3 · reportfixture: signature outputs:Tensor/2/float · returned Tensor · level recorded, date not recorded
select_confident_samplesin 10 paperstpt_classification.pyidentical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its ownran · our draft was wrongfingerprintedlicence of this copy not recorded · 3ce4d11e58de02ad · reportfixture: signature logits:Tensor/2/float, top:float/0/float · returned tuple · level recorded, date not recorded
test_time_tuningin 5 paperstpt_classification.pyidentical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its ownunverifiedlicence of this copy not recorded · 631c70c26c0fcedf · report
has_ddp_wrapperin 6 paperseval/ImageNet_probing/dinov2/eval/linear_proteus.pyidentical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its ownunverifiedlicence of this copy not recorded · 1cd2728a84872357 · report
eify/open_clipcommunity (archive-listed)3 samples, 3 ran (2 instrument-failed) · 0 unverified
convert_to_custom_text_state_dictin 59 paperssrc/open_clip/model.pyidentical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its ownran · violated contractlicence of this copy not recorded · f19962ebb134b3d7 · reportfixture: signature state_dict:dict/0/? · returned dict · level recorded, date not recorded
get_cast_dtypein 67 paperssrc/open_clip/model.pyidentical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its ownran · our draft was wronglicence of this copy not recorded · dcd422d66b0581d8 · reportfixture: signature precision:str/0/str · returned dtype · level recorded, date not recorded
get_input_dtypein 30 paperssrc/open_clip/model.pyidentical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its ownran · our draft was wronglicence of this copy not recorded · b476c8cfbf0f1f47 · reportfixture: signature precision:str/0/str · returned dtype · level recorded, date not recorded
filipbasara0/simple-clipcommunity (archive-listed)2 samples, 2 ran (2 instrument-failed) · 0 unverified
siglip_losssimple_clip/clip.pyran · our draft was wrongfingerprintedMIT (permissive) · 67c4ef5004396e02 · reportfixture: signature logits:Tensor/2/float · returned Tensor · level recorded 2026-09-22
mainaksingha01/odg-clipcommunity (archive-listed)1 sample, 1 ran (1 instrument-failed) · 0 unverified
domain_text_losspacs.pyran; the contract check could not run (RAISES) · metamorphic tier: invariantfingerprintedMIT (permissive) · 7f39fa83f26c97c7 · reportfixture: signature diff_textfeatures:Tensor/2/float, domain:list/1/int · returned Tensor · level recorded 2026-09-22
michi-3000/eyeclipcommunity (archive-listed)1 sample, 1 ran (1 instrument-failed) · 0 unverified
misc_measureszero_shot.pyran; the contract check could not run (RAISES) · metamorphic tier: invariantfingerprintedno licence file found · pointer only · 1b17b45e4d751423 · reportfixture: signature confusion_matrix:ndarray/3/float · returned tuple · level recorded 2026-09-22
Repository not located2 samples, 2 ran (2 instrument-failed) · 0 unverified 2 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
mean_per_classin 6 papersrepository not locatedran; the contract check could not run (RAISES) · metamorphic tier: invariantfingerprintedlicence of this copy not recorded · f0eb8193f86d363b · reportfixture: signature outputs:Tensor/2/float, targets:ndarray/1/int · returned float64 · level recorded, date not recorded
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.