Dan Jurafsky, Alex Tamkin, Noah Goodman
None of the 5 samples (functions and classes) lifted from this paper's linked repositories has a recorded run on a synthesized input (5 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/2011.04823.json · badge: /api/ran/2011.04823.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 |
|---|---|---|
| zh217/torch-dct | named in the paper Papers with Code archive |
0 ran · 5 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| LinearDCT | Not yet run unverified (harvested, no recorded run) |
zh217/torch-dct/torch_dct/_dct.py code served (permissive licence) · get_code("8ee2bb43bd28f6ac") How it ranno invocation recorded. |
| dct | Not yet run unverified (harvested, no recorded run) |
zh217/torch-dct/torch_dct/_dct.py code served (permissive licence) · get_code("39394813950ed362") How it ranno invocation recorded. |
| dct1 | Not yet run unverified (harvested, no recorded run) |
zh217/torch-dct/torch_dct/_dct.py code served (permissive licence) · get_code("f3f999af44b26296") How it ranno invocation recorded. |
| idct | Not yet run unverified (harvested, no recorded run) |
zh217/torch-dct/torch_dct/_dct.py code served (permissive licence) · get_code("fdb926eceb3af796") How it ranno invocation recorded. |
| idct1 | Not yet run unverified (harvested, no recorded run) |
zh217/torch-dct/torch_dct/_dct.py code served (permissive licence) · get_code("2f88f7130eaa3ed7") How it ranno invocation recorded. |
Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 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 |
|---|---|---|---|
| idct1 brick of this paper's assembly: helper |
10 other papers 10 later |
2105.08997 (2021-05) When Deep Classifiers Agree: Analyzing Correlations between Learning Order and Image Statistics |
2209.11888 (2022-09) JPEG Artifact Correction using Denoising Diffusion Restoration Models 2306.12685 (2023-06) Rethinking the Backward Propagation for Adversarial Transferability and 7 more not named here |
| LinearDCT brick of this paper's assembly: entry |
1 other paper 1 later |
2209.11888 (2022-09) JPEG Artifact Correction using Denoising Diffusion Restoration 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.
Language exhibits structure at different scales, ranging from subwords to words, sentences, paragraphs, and documents. To what extent do deep models capture information at these scales, and can we force them to better capture structure across this hierarchy? We approach this question by focusing on individual neurons, analyzing the behavior of their activations at different timescales. We show that signal processing provides a natural framework for separating structure across scales, enabling us to 1) disentangle scale-specific information in existing embeddings and 2) train models to learn more about particular scales. Concretely, we apply spectral filters to the activations of a neuron across an input, producing filtered embeddings that perform well on part of speech tagging (word-level), dialog speech acts classification (utterance-level), or topic classification (document-level), while performing poorly on the other tasks. We also present a prism layer for training models, which uses spectral filters to constrain different neurons to model structure at different scales. Our proposed BERT + Prism model can better predict masked tokens using long-range context and produces multiscale representations that perform better at utterance-and document-level tasks. Our methods are general and readily applicable to other domains besides language, such as images, audio, and video.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2011.04823")
get_code_for_paper("2011.04823")
have("2011.04823")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2011.04823.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2011.04823)
Connect an agent — have() is free.