Home › Code › build_model_from_openai_state_dict

build_model_from_openai_state_dict

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

build_model_from_openai_state_dict appears in the code Syntology harvested for 42 papers, as 30 distinct code bodies found in 45 places (a place is one code body under one paper). At least one of them ran in 0 of the papers; 0 of the code bodies carry a behaviour fingerprint.

What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named build_model_from_openai_state_dict do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

Syntology ran 0 of the 30 distinct code bodies named build_model_from_openai_state_dict; 30 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
0ran · our draft was wrong
0ran · fixture could not drive it
0ran
30unverified
0fingerprinted

Licence is a property of each copy, so it is counted per place: 20 of the 45 places are pointer only (Syntology does not serve that copy's text). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.

“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page.

Papers

42 papers shown of 42, newest first; 45 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive, and the graph's for 2 papers added by Syntology; 2 papers have no page here and are shown by arXiv id only. Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's code_sha256, Syntology's identity for that exact code: an agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

PaperDateFileStatus SyntologyLicence
Bridging Vision Foundation Model Priors with CLIP for Spatial-aware Few-shot Anomaly Detection in Medical Images added by Syntology 2026-09 (from id) JuzhengMiao/Spatial-FAD/CLIP/model.py 09c0abc70500a134 unverified MIT (permissive)
Dial HEALTHDIAL for Advice: A Multilingual and Multi-Parallel Spoken Dialogue Dataset for Knowledge-Grounded Information Seeking added by Syntology 2026-05 (from id) LAION-AI/CLAP/src/laion_clap/clap_module/model.py 50d4bb09e01d4068 unverified CC0-1.0 (permissive)
Streamline Without Sacrifice -- Squeeze out Computation Redundancy in LMM 21 May 2025 penghao-wu/proxyv/llava/model/multimodal_encoder/dev_eva_clip/eva_clip/model.py a8e9981d9caacade unverified Apache-2.0 (permissive)
CAFe: Unifying Representation and Generation with Contrastive-Autoregressive Finetuning 25 Mar 2025 identical code first harvested elsewhere 275eb8fe6104bf3a unverified licence of this copy not recorded
Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step 23 Jan 2025 identical code first harvested elsewhere 275eb8fe6104bf3a unverified licence of this copy not recorded
UniMed-CLIP: Towards a Unified Image-Text Pretraining Paradigm for Diverse Medical Imaging Modalities 13 Dec 2024 mbzuai-oryx/unimed-clip/src/open_clip/model.py 4bdb7789fe2f485e unverified licence not identified · pointer only
Hidden in the Noise: Two-Stage Robust Watermarking for Images 5 Dec 2024 Kasraarabi/Hidden-in-the-Noise/open_clip/model.py 57f1602ed20a9c21 unverified no licence file found · pointer only
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models 22 Nov 2024 identical code first harvested elsewhere 275eb8fe6104bf3a unverified licence of this copy not recorded
ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimization 6 Nov 2024 Hannah1102/ROBIN/open_clip/model.py 57f1602ed20a9c21 unverified no licence file found · pointer only
SePPO: Semi-Policy Preference Optimization for Diffusion Alignment 7 Oct 2024 dwanzhang-ai/seppo/utils/open_clip/model.py 53fc85e1b2889c0f unverified no licence file found · pointer only
PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detection 1 Oct 2024 zqhang/accurate-winclip-pytorch/src/open_clip/model.py b7bca1358293c8ab unverified MIT (permissive)
AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection 22 Jul 2024 caoyunkang/adaclip/method/clip_model.py 5d5046aaa43f74c7 unverified MIT (permissive)
VideoEval: Comprehensive Benchmark Suite for Low-Cost Evaluation of Video Foundation Model 9 Jul 2024 leexinhao/VideoEval/VidTAB_Zeroshot/eva_clip/model.py b34d6c17c6e09a04 unverified no licence file found · pointer only
Modeling Caption Diversity in Contrastive Vision-Language Pretraining 30 Apr 2024 facebookresearch/llip/llip/open_clip/model.py 546ba17b219740cb unverified licence not identified · pointer only
PuLID: Pure and Lightning ID Customization via Contrastive Alignment 24 Apr 2024 ToTheBeginning/PuLID/eva_clip/model.py e3f7350246f3e4bb unverified Apache-2.0 (permissive)
PuLID: Pure and Lightning ID Customization via Contrastive Alignment 24 Apr 2024 zsxkib/PuLID/eva_clip/model.py b34d6c17c6e09a04 unverified Apache-2.0 (permissive)
RingID: Rethinking Tree-Ring Watermarking for Enhanced Multi-Key Identification 22 Apr 2024 showlab/ringid/open_clip/model.py 57f1602ed20a9c21 unverified no licence file found · pointer only
FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localization 21 Apr 2024 casia-iva-lab/filo/models/vv_open_clip/model.py 566817905973a0e8 unverified Apache-2.0 (permissive)
PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection 8 Apr 2024 funz-0/promptad/PromptAD/CLIPAD/model.py c92f832f94b5a1c1 unverified Unlicense (permissive)
Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models 7 Apr 2024 bsmhmmlf/Gaussian-Shading/open_clip/model.py 57f1602ed20a9c21 unverified MIT (permissive)
Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Images 19 Mar 2024 mediabrain-sjtu/mvfa-ad/CLIP/model.py 09c0abc70500a134 unverified MIT (permissive)
InstructTA: Instruction-Tuned Targeted Attack for Large Vision-Language Models 4 Dec 2023 xunguangwang/instructta/EVA-CLIP/rei/eva_clip/model.py b34d6c17c6e09a04 unverified no licence file found · pointer only
BioCLIP: A Vision Foundation Model for the Tree of Life 30 Nov 2023 imageomics/bioclip/src/open_clip/model.py 57f1602ed20a9c21 unverified licence not identified · pointer only
Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and Captions 28 Nov 2023 show-han/zeroshot_rec/VLA_finetune/open_clip/model.py e209d001d7c966cf unverified Apache-2.0 (permissive)
Diffusion Model Alignment Using Direct Preference Optimization 21 Nov 2023 SalesforceAIResearch/DiffusionDPO/utils/open_clip/model.py 53fc85e1b2889c0f unverified Apache-2.0 recorded; this copy not marked cleared · pointer only
AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection 29 Oct 2023 zqhang/WinCLIP-pytorch/src/open_clip/model.py e332828701fffe70 unverified MIT (permissive)
AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection 29 Oct 2023 zqhang/WinCLIP-pytorch/src/open_clip/model_revise.py e0b318791c717866 unverified MIT (permissive)
Improved Baselines with Visual Instruction Tuning 5 Oct 2023 dinhvietcuong1996/icme25-inova/llava/model/multimodal_encoder/dev_eva_clip/eva_clip/model.py 275eb8fe6104bf3a unverified Apache-2.0 (permissive)
Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks 29 Sep 2023 Hhhhhhao/Noisy-Model-Learning/open_clip/open_clip/model.py 8b4b0d1ac0c85692 unverified no licence file found · pointer only
Bootstrap Fine-Grained Vision-Language Alignment for Unified Zero-Shot Anomaly Localization 30 Aug 2023 hq-deng/AnoVL/open_clip/model.py 566817905973a0e8 unverified MIT (permissive)
CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say No 23 Aug 2023 xmed-lab/clipn/src/open_clip/model.py 630cd10269e63c8c unverified MIT (permissive)
AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining 10 Aug 2023 haoheliu/AudioLDM2/audioldm2/clap/open_clip/model.py fde7529206b8c46f unverified licence not identified · pointer only
CLIP-KD: An Empirical Study of CLIP Model Distillation 24 Jul 2023 winycg/clip-kd/src/open_clip/model.py 1ae9f5eab925c792 unverified no licence file found · pointer only
Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models 29 Jun 2023 luosiallen/Diff-Foley/training/open_cavp_main/src/open_clip/model.py e4c056f11a6a6acf unverified Apache-2.0 (permissive)
APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot AD 27 May 2023 bychelsea/vand-april-gan/open_clip/model.py 096be08051b5c0d0 unverified MIT (permissive)
Unicom: Universal and Compact Representation Learning for Image Retrieval 12 Apr 2023 identical code first harvested elsewhere 275eb8fe6104bf3a unverified licence of this copy not recorded
WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation 26 Mar 2023 zqhang/Accurate-WinCLIP-pytorch/src/open_clip/model.py e332828701fffe70 unverified MIT (permissive)
WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation 26 Mar 2023 caoyunkang/WinClip/WinCLIP/CLIPAD/model.py c94ec43ef54519ef unverified MIT (permissive)
LiT Tuned Models for Efficient Species Detection 12 Feb 2023 identical code first harvested elsewhere 903b104e9c495329 unverified licence of this copy not recorded
Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery 7 Feb 2023 YuxinWenRick/hard-prompts-made-easy/open_clip/model.py 10a858bd32dad1e6 unverified MIT (permissive)
Learning Customized Visual Models with Retrieval-Augmented Knowledge 17 Jan 2023 microsoft/react/react_customization/src/open_clip/model.py 26a799d4c5d477a1 unverified MIT (permissive)
Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP 9 Oct 2022 facebookresearch/ov-seg/open_clip_training/src/open_clip/model.py b9b4b4cc71fba508 unverified licence not identified · pointer only
Learning Transferable Visual Models From Natural Language Supervision 26 Feb 2021 NYU-DICE-Lab/open_clip/src/open_clip/model.py 903b104e9c495329 unverified licence not identified · pointer only
arXiv:Ma_ReMP-AD_Retrieval-enhanced_Multi-modal_Prompt_Fusion_for_Few-Shot_Industrial_Visual_Anomaly_ICCV_2025_paper cshcma/ReMP-AD/open_clip/model.py 8b968a2166183191 unverified MIT (permissive)
arXiv:Hertz_Style_Aligned_Image_Generation_via_Shared_Attention_CVPR_2024_paper aim-uofa/StyleDrop-PyTorch/open_clip/model.py b42328328b7afbf8 unverified MIT (permissive)

This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the harvest. "Pointer only" means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections