Sicheng Zhu, Furong Huang, Bang An, Michael-Andrei Panaitescu-Liess, Chaithanya Mummadi
4 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 8 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.
"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2308.01313.json · badge: /api/ran/2308.01313.svg
Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.
| Repository | Role | Ran |
|---|---|---|
| umd-huang-lab/perceptionCLIP | canonical (classifier label) classifier basis not recorded on the link |
3 ran · 3 no recorded run |
| umd-huang-lab/perceptionclip | community Papers with Code archive |
1 ran · 5 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| basic_clean | Ran ran; our contract draft was wrong, not the code |
umd-huang-lab/perceptionCLIP/clip/tokenizer.py pointer only (licence: MIT); the stored copy get_code serves, from ltpwy/MSCI, is pointer only (licence: NONE) · get_code("98f385d847636a3e") How it ranThe body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ltpwy/MSCI, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| get_pairs | Ran ran; our contract draft was wrong, not the code |
umd-huang-lab/perceptionCLIP/clip/tokenizer.py code served (permissive licence) · get_code("d919ae32e5e4e616") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned set. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| maybe_dictionarize | Ran ran; our contract draft was wrong, not the code |
umd-huang-lab/perceptionclip/src/zero_shot_inference/perceptionclip_two_step.py code served (permissive licence) · get_code("b1e9e0d3d7d7e615") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| whitespace_clean | Ran ran; our contract draft was wrong, not the code |
umd-huang-lab/perceptionCLIP/clip/tokenizer.py pointer only (licence: MIT); the stored copy get_code serves, from ltpwy/MSCI, is pointer only (licence: NONE) · get_code("9542161e9640b858") How it ranThe body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ltpwy/MSCI, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| FeatureDataset | Not yet run unverified (harvested, no recorded run) |
umd-huang-lab/perceptionclip/src/zero_shot_inference/perceptionclip_two_step.py code served (permissive licence) · get_code("b2ca442256677f59") How it ranno invocation recorded. |
| build_model | Not yet run unverified (harvested, no recorded run) |
umd-huang-lab/perceptionCLIP/clip/model.py pointer only (licence: MIT); the stored copy get_code serves, from HesamAsad/TRACER, is pointer only (licence: NONE) · get_code("b64f67bec6a093b9") How it ranThe body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from HesamAsad/TRACER, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded. |
| classify | Not yet run unverified (harvested, no recorded run) |
umd-huang-lab/perceptionclip/src/zero_shot_inference/perceptionclip_two_step.py code served (permissive licence) · get_code("707f6200db45227e") How it ranno invocation recorded. |
| gather_features | Not yet run unverified (harvested, no recorded run) |
umd-huang-lab/perceptionCLIP/clip/loss.py pointer only (licence: MIT); the stored copy get_code serves, from lxa9867/imagefolder, is pointer only (licence: NOASSERTION) · get_code("ddcbd45e940484ee") How it ranThe body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from lxa9867/imagefolder, and GitHub could not classify the licence of that repository (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded. |
| get_dataloader | Not yet run unverified (harvested, no recorded run) |
umd-huang-lab/perceptionclip/src/zero_shot_inference/perceptionclip_two_step.py code served (permissive licence) · get_code("d72e4be63bb4c2b4") How it ranno invocation recorded. |
| get_features | Not yet run unverified (harvested, no recorded run) |
umd-huang-lab/perceptionclip/src/zero_shot_inference/perceptionclip_two_step.py code served (permissive licence) · get_code("69f5c5edbc89d5b8") How it ranno invocation recorded. |
| get_features | Not yet run unverified (harvested, no recorded run) |
umd-huang-lab/perceptionCLIP/src/datasets/common.py pointer only (licence: MIT); the stored copy get_code serves, from ganglii/devsafety, is pointer only (licence: NONE) · get_code("7727c964cfcd56e6") How it ranThe body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ganglii/devsafety, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded. |
| get_features_helper | Not yet run unverified (harvested, no recorded run) |
umd-huang-lab/perceptionclip/src/zero_shot_inference/perceptionclip_two_step.py code served (permissive licence) · get_code("74edffa1dfc39e58") How it ranno invocation recorded. |
Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 8 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 5 the same month, 8 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).
Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.
| Function | Also present in | Earliest-dated | Others named |
|---|---|---|---|
| get_pairs | 258 other papers 66 dated earlier, 6 the same month, 178 later, 7 same year, order not determinable, 1 undated · 4 only as an assembly brick |
1802.06474 (2018-02) A Closed-form Solution to Photorealistic Image Stylization |
1803.01128 (2018-03) Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples 1809.00125 (2018-09) Simple Fusion: Return of the Language Model and 255 more not named here |
| whitespace_clean | 231 other papers 50 dated earlier, 6 the same month, 169 later, 5 same year, order not determinable, 1 undated · 4 only as an assembly brick |
1901.07441 (2019-01) PadChest: A large chest x-ray image dataset with multi-label annotated reports |
2107.06383 (2021-07) How Much Can CLIP Benefit Vision-and-Language Tasks? 2108.10904 (2021-08) SimVLM: Simple Visual Language Model Pretraining with Weak Supervision and 228 more not named here |
| basic_clean | 218 other papers 50 dated earlier, 6 the same month, 156 later, 5 same year, order not determinable, 1 undated · 4 only as an assembly brick |
1901.07441 (2019-01) PadChest: A large chest x-ray image dataset with multi-label annotated reports |
2107.06383 (2021-07) How Much Can CLIP Benefit Vision-and-Language Tasks? 2108.10904 (2021-08) SimVLM: Simple Visual Language Model Pretraining with Weak Supervision and 215 more not named here |
| gather_features | 57 other papers 9 dated earlier, 2 the same month, 46 later · 1 only as an assembly brick |
2206.01670 (2022-06) Egocentric Video-Language Pretraining |
2212.00638 (2022-12) Finetune like you pretrain: Improved finetuning of zero-shot vision models 2301.07094 (2023-01) Learning Customized Visual Models with Retrieval-Augmented Knowledge and 54 more not named here |
| maybe_dictionarize brick of this paper's assembly: helper |
13 other papers 1 the same month, 12 later · 1 only as an assembly brick |
2308.12213 (2023-08) CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say No |
2311.01723 (2023-11) Towards Calibrated Robust Fine-Tuning of Vision-Language Models 2312.02546 (2023-12) Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning and 10 more not named here |
| build_model | 8 other papers 3 dated earlier, 5 later |
2208.05592 (2022-08) Patching open-vocabulary models by interpolating weights |
2212.00638 (2022-12) Finetune like you pretrain: Improved finetuning of zero-shot vision models 2302.13602 (2023-02) The Role of Pre-training Data in Transfer Learning and 5 more not named here |
| get_features_helper brick of this paper's assembly: helper |
4 other papers 4 later |
2311.01723 (2023-11) Towards Calibrated Robust Fine-Tuning of Vision-Language Models |
2312.02546 (2023-12) Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning 2410.03955 (2024-10) A Retention-Centric Framework for Continual Learning with Guaranteed Model Developmental Safety and 1 more not named here |
| get_features brick of this paper's assembly: helper |
3 other papers 3 later |
2312.02546 (2023-12) Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning |
2410.03955 (2024-10) A Retention-Centric Framework for Continual Learning with Guaranteed Model Developmental Safety 2411.19757 (2024-11) Dual Risk Minimization: Towards Next-Level Robustness in Fine-tuning Zero-Shot Models |
Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Vision-language models like CLIP are widely used in zero-shot image classification due to their ability to understand various visual concepts and natural language descriptions. However, how to fully leverage CLIP's unprecedented human-like understanding capabilities to achieve better performance is still an open question. This paper draws inspiration from the human visual perception process: when classifying an object, humans first infer contextual attributes (e.g., background and orientation) which help separate the foreground object from the background, and then classify the object based on this information. Inspired by it, we observe that providing CLIP with contextual attributes improves zero-shot image classification and mitigates reliance on spurious features. We also observe that CLIP itself can reasonably infer the attributes from an image. With these observations, we propose a training-free, two-step zero-shot classification method PerceptionCLIP. Given an image, it first infers contextual attributes (e.g., background) and then performs object classification conditioning on them. Our experiments show that PerceptionCLIP achieves better generalization, group robustness, and interpretability. Our code is available at https://github.com/umd-huang-lab/perceptionCLIP.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2308.01313")
get_code_for_paper("2308.01313")
have("2308.01313")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2308.01313.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2308.01313)
Connect an agent — have() is free.