Qing Zhang, Chengjiang Long, Yongwei Nie, Guiqing Li, Zhian Liu
10 of 11 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 8 have no contract verdict; 2 failures of our instrument; 1 no recorded run), measured 2026-11-22; 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/2108.06852.json · badge: /api/ran/2108.06852.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 |
|---|---|---|
| LiUzHiAn/hf2vad | canonical (classifier label) classifier basis: census |
10 ran · 1 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| aggregate_kl_loss | Ran ran on a synthesized input |
LiUzHiAn/hf2vad/losses/loss.py code served (permissive licence) · get_code("38d8b97b928f93a2") 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 Tensor, ndim 0, dtype family float, shape () 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.
|
| delCoverBboxes | Ran ran on a synthesized input |
LiUzHiAn/hf2vad/pre_process/extract_bboxes.py code served (permissive licence) · get_code("a653b45bfcbe2b95") 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 ndarray, ndim 2, dtype family float, shape (2, 4) 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.
|
| getFgBboxes | Ran ran on a synthesized input |
LiUzHiAn/hf2vad/pre_process/extract_bboxes.py code served (permissive licence) · get_code("b3698ab6fca12450") 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 ndarray, ndim 2, dtype family int, shape (3, 4) 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.
|
| get_inputs | Ran ran on a synthesized input |
LiUzHiAn/hf2vad/datasets/dataset.py code served (permissive licence) · get_code("8d81b09e9f81cc4b") 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 ndarray, ndim 2, dtype family float, shape (4, 3) 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.
|
| img_batch_tensor2numpy | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
LiUzHiAn/hf2vad/datasets/dataset.py code served (permissive licence) · get_code("c33c92a32cd64fd4") 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 Tensor, ndim 4, dtype family float, shape (2, 3, 4, 5) 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.
|
| img_tensor2numpy | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
LiUzHiAn/hf2vad/datasets/dataset.py code served (permissive licence) · get_code("b6912e844379ed70") 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 Tensor, ndim 3, dtype family float, shape (3, 4, 5) 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.
|
| latent_kl | Ran ran on a synthesized input |
LiUzHiAn/hf2vad/losses/loss.py code served (permissive licence) · get_code("46f0670b0df56146") 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 Tensor, ndim 0, dtype family float, shape () 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.
|
| loader | Ran ran on a synthesized input |
LiUzHiAn/hf2vad/utils/model_utils.py code served (permissive licence) · get_code("bc27df2e0a58fe31") 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 tuple, 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.
|
| mem_loader | Ran ran on a synthesized input |
LiUzHiAn/hf2vad/utils/model_utils.py code served (permissive licence) · get_code("79bed0a0515af148") 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 Tensor, ndim 2, dtype family float, shape (2, 4) 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.
|
| only_model_loader | Ran ran on a synthesized input |
LiUzHiAn/hf2vad/utils/model_utils.py code served (permissive licence) · get_code("75bb71577a8469ba") 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.
|
| hard_shrink_relu | Not yet run unverified (harvested, no recorded run) |
LiUzHiAn/hf2vad/models/ml_memAE_sc.py code served (permissive licence) · get_code("22ed0e6535db75a1") How it ranno invocation recorded. |
Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 3 later) and 8 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 |
|---|---|---|---|
| hard_shrink_relu | 1 other paper 1 later |
2111.13495 (2021-11) SQUID: Deep Feature In-Painting for Unsupervised Anomaly Detection |
|
| img_batch_tensor2numpy | 1 other paper 1 later |
2403.06495 (2024-03) Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Prompts |
|
| img_tensor2numpy | 1 other paper 1 later |
2403.06495 (2024-03) Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Prompts |
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.
In this paper, we propose HF 2 -VAD, a Hybrid framework that integrates Flow reconstruction and Frame prediction seamlessly to handle Video Anomaly Detection. Firstly, we design the network of ML-MemAE-SC (Multi-Level Memory modules in an Autoencoder with Skip Connections) to memorize normal patterns for optical flow reconstruction so that abnormal events can be sensitively identified with larger flow reconstruction errors. More importantly, conditioned on the reconstructed flows, we then employ a Conditional Variational Autoencoder (CVAE), which captures the high correlation between video frame and optical flow, to predict the next frame given several previous frames. By CVAE, the quality of flow reconstruction essentially influences that of frame prediction. Therefore, poorly reconstructed optical flows of abnormal events further deteriorate the quality of the final predicted future frame, making the anomalies more detectable. Experimental results demonstrate the effectiveness of the proposed method. Code is available at https://github.com/LiUzHiAn/hf2vad.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2108.06852")
get_code_for_paper("2108.06852")
have("2108.06852")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2108.06852.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2108.06852)
Connect an agent — have() is free.