10 of 14 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; 2 honoured the contract we drafted, 2 violated it and 1 has no contract verdict; 5 failures of our instrument; 4 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/2106.09681.json · badge: /api/ran/2106.09681.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 |
|---|---|---|
| facebookresearch/xcit | canonical (classifier label) classifier basis: census |
2 ran · 1 no recorded run |
| adrienangeli/dino | community (classifier label) classifier basis not recorded on the link |
8 ran · 3 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| bool_flag | Ran ran, violated the contract we drafted |
adrienangeli/dino/utils.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from sthalles/MaSSL, is pointer only (licence: NONE) · get_code("c19231378e41dc5a") How it ranThe body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from sthalles/MaSSL, 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. |
| build_transform | Ran ran on a synthesized input |
facebookresearch/xcit/datasets.py pointer only (licence: Apache-2.0) · get_code("e7791ea55637b67a") How it ranThe body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, facebookresearch/xcit, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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. |
| clip_gradients | Ran ran, honoured the contract we drafted |
adrienangeli/dino/utils.py code served (permissive licence) · get_code("2b5489053b222e00") 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 list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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.
|
| config_imname | Ran ran; our contract draft was wrong, not the code |
adrienangeli/dino/eval_image_retrieval.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from mahmoodlab/HIPT, is pointer only (licence: NOASSERTION) · get_code("49cf1f4ce52e9613") How it ranThe body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from mahmoodlab/HIPT, 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. A run is recorded. |
| config_qimname | Ran ran; our contract draft was wrong, not the code |
adrienangeli/dino/eval_image_retrieval.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from mahmoodlab/HIPT, is pointer only (licence: NOASSERTION) · get_code("91c5ae2396603107") How it ranThe body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from mahmoodlab/HIPT, 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. A run is recorded. |
| conv3x3 | Ran ran; our contract draft was wrong, not the code |
facebookresearch/xcit/xcit.py pointer only (licence: Apache-2.0) · get_code("429abe9dc8793925") How it ranThe body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, facebookresearch/xcit, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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. |
| cosine_scheduler | Ran ran, honoured the contract we drafted |
adrienangeli/dino/utils.py code served (permissive licence) · get_code("361a6b24f11fc50a") 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 ndarray, ndim 1, dtype family float, shape (500,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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.
|
| is_image_file | Ran ran, violated the contract we drafted |
adrienangeli/dino/eval_copy_detection.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from mahmoodlab/HIPT, is pointer only (licence: NOASSERTION) · get_code("dfebfd56865b6379") How it ranThe body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from mahmoodlab/HIPT, 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. A run is recorded. |
| norm_mask | Ran ran; our contract draft was wrong, not the code |
adrienangeli/dino/eval_video_segmentation.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from mahmoodlab/HIPT, is pointer only (licence: NOASSERTION) · get_code("e015f2c93c762aff") How it ranThe body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from mahmoodlab/HIPT, 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. A run is recorded. |
| score_ap_from_ranks_1 | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
adrienangeli/dino/eval_copy_detection.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from mahmoodlab/HIPT, is pointer only (licence: NOASSERTION) · get_code("5f21619ff716c1ce") How it ranThe body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from mahmoodlab/HIPT, 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. A run is recorded. |
| build_dataset | Not yet run unverified (harvested, no recorded run) |
facebookresearch/xcit/datasets.py pointer only (licence: Apache-2.0) · get_code("18119fb5f5299851") How it ranThe body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, facebookresearch/xcit, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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. |
| knn_classifier | Not yet run unverified (harvested, no recorded run) |
adrienangeli/dino/eval_knn.py code served (permissive licence) · get_code("6ecb6791e6a9ebfb") How it ranno invocation recorded. |
| label_propagation | Not yet run unverified (harvested, no recorded run) |
adrienangeli/dino/eval_video_segmentation.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from mahmoodlab/HIPT, is pointer only (licence: NOASSERTION) · get_code("3093e0466654d790") How it ranThe body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from mahmoodlab/HIPT, 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. |
| restrict_neighborhood | Not yet run unverified (harvested, no recorded run) |
adrienangeli/dino/eval_video_segmentation.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from mahmoodlab/HIPT, is pointer only (licence: NOASSERTION) · get_code("efc78e753491eeab") How it ranThe body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from mahmoodlab/HIPT, 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. |
Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 14 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 14 later) and 0 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 |
|---|---|---|---|
| cosine_scheduler | 37 other papers 2 dated earlier, 35 later |
2005.10242 (2020-05) Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere |
2103.15375 (2021-03) AlignMixup: Improving Representations By Interpolating Aligned Features 2109.13228 (2021-09) PASS: An ImageNet replacement for self-supervised pretraining without humans and 34 more not named here |
| bool_flag | 31 other papers 31 later |
2109.13228 (2021-09) PASS: An ImageNet replacement for self-supervised pretraining without humans |
2111.12958 (2021-11) Self-Distilled Self-Supervised Representation Learning 136810551 (2022 (year only)) UniMiSS: Universal Medical Self-Supervised Learning via Breaking Dimensionality Barrier and 28 more not named here |
| clip_gradients | 28 other papers 28 later |
2109.13228 (2021-09) PASS: An ImageNet replacement for self-supervised pretraining without humans |
2111.12958 (2021-11) Self-Distilled Self-Supervised Representation Learning 136810551 (2022 (year only)) UniMiSS: Universal Medical Self-Supervised Learning via Breaking Dimensionality Barrier and 25 more not named here |
| config_imname | 4 other papers 1 dated earlier, 3 later |
1711.02512 (2017-11) Fine-tuning CNN Image Retrieval with No Human Annotation |
2109.13228 (2021-09) PASS: An ImageNet replacement for self-supervised pretraining without humans 2308.04008 (2023-08) Coarse-to-Fine: Learning Compact Discriminative Representation for Single-Stage Image Retrieval and 1 more not named here |
| config_qimname | 4 other papers 1 dated earlier, 3 later |
1711.02512 (2017-11) Fine-tuning CNN Image Retrieval with No Human Annotation |
2109.13228 (2021-09) PASS: An ImageNet replacement for self-supervised pretraining without humans 2308.04008 (2023-08) Coarse-to-Fine: Learning Compact Discriminative Representation for Single-Stage Image Retrieval and 1 more not named here |
| knn_classifier | 4 other papers 1 dated earlier, 3 later |
2104.14294 (2021-04) Emerging Properties in Self-Supervised Vision Transformers |
2109.13228 (2021-09) PASS: An ImageNet replacement for self-supervised pretraining without humans 2410.05057 (2024-10) SELECT: A Large-Scale Benchmark of Data Curation Strategies for Image Classification and 1 more not named here |
| conv3x3 | 3 other papers 3 later |
2206.08898 (2022-06) SimA: Simple Softmax-free Attention for Vision Transformers |
2210.05958 (2022-10) Bridging the Gap Between Vision Transformers and Convolutional Neural Networks on Small Datasets 2410.02675 (2024-10) FAN: Fourier Analysis Networks |
| norm_mask | 3 other papers 3 later |
2109.13228 (2021-09) PASS: An ImageNet replacement for self-supervised pretraining without humans |
2306.03881 (2023-06) Emergent Correspondence from Image Diffusion 2602.01951 (2026-02) Enabling Progressive Whole-slide Image Analysis with Multi-scale Pyramidal Network |
| restrict_neighborhood | 3 other papers 3 later |
2109.13228 (2021-09) PASS: An ImageNet replacement for self-supervised pretraining without humans |
2306.03881 (2023-06) Emergent Correspondence from Image Diffusion 2602.01951 (2026-02) Enabling Progressive Whole-slide Image Analysis with Multi-scale Pyramidal Network |
| score_ap_from_ranks_1 | 3 other papers 3 later |
2109.13228 (2021-09) PASS: An ImageNet replacement for self-supervised pretraining without humans |
2202.10261 (2022-02) A Self-Supervised Descriptor for Image Copy Detection 2602.01951 (2026-02) Enabling Progressive Whole-slide Image Analysis with Multi-scale Pyramidal Network |
| is_image_file | 2 other papers 2 later |
2109.13228 (2021-09) PASS: An ImageNet replacement for self-supervised pretraining without humans |
2602.01951 (2026-02) Enabling Progressive Whole-slide Image Analysis with Multi-scale Pyramidal Network |
| label_propagation | 2 other papers 2 later |
2109.13228 (2021-09) PASS: An ImageNet replacement for self-supervised pretraining without humans |
2602.01951 (2026-02) Enabling Progressive Whole-slide Image Analysis with Multi-scale Pyramidal Network |
| build_dataset | 1 other paper 1 later |
2206.08898 (2022-06) SimA: Simple Softmax-free Attention for Vision Transformers |
|
| build_transform | 1 other paper 1 later |
2206.08898 (2022-06) SimA: Simple Softmax-free Attention for Vision Transformers |
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.
Following their success in natural language processing, transformers have recently shown much promise for computer vision. The self-attention operation underlying transformers yields global interactions between all tokens ,i.e. words or image patches, and enables flexible modelling of image data beyond the local interactions of convolutions. This flexibility, however, comes with a quadratic complexity in time and memory, hindering application to long sequences and high-resolution images. We propose a "transposed" version of self-attention that operates across feature channels rather than tokens, where the interactions are based on the cross-covariance matrix between keys and queries. The resulting cross-covariance attention (XCA) has linear complexity in the number of tokens, and allows efficient processing of high-resolution images. Our cross-covariance image transformer (XCiT) is built upon XCA. It combines the accuracy of conventional transformers with the scalability of convolutional architectures. We validate the effectiveness and generality of XCiT by reporting excellent results on multiple vision benchmarks, including image classification and self-supervised feature learning on ImageNet-1k, object detection and instance segmentation on COCO, and semantic segmentation on ADE20k.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2106.09681")
get_code_for_paper("2106.09681")
have("2106.09681")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2106.09681.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2106.09681)
Connect an agent — have() is free.