Tabish Rashid, Katja Hofmann, Tim Pearce, Anssi Kanervisto, Sam Devlin, Ida Momennejad, Raluca Georgescu, Mingfei Sun, Dave Bignell, Sergio Macua, Shan Tan
5 of 5 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 4 have no contract verdict; 1 failure of our instrument; 0 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/2301.10677.json · badge: /api/ran/2301.10677.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 |
|---|---|---|
| microsoft/imitating-human-behaviour-w-diffusion | canonical (classifier label) classifier basis not recorded on the link |
5 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| ddpm_schedules | Ran ran on a synthesized input |
microsoft/imitating-human-behaviour-w-diffusion/code/models.py code served (permissive licence) · get_code("9a16e3abe84897af") 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.
|
| get_random_offset | Ran ran on a synthesized input |
microsoft/imitating-human-behaviour-w-diffusion/code/make_dataset.py code served (permissive licence) · get_code("5d9e485a37d3737f") 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 int; 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.
|
| matrix_diag | Ran ran; our contract draft was wrong, not the code |
microsoft/imitating-human-behaviour-w-diffusion/code/models.py pointer only (licence: MIT); the stored copy get_code serves, from ZhuYun97/RoSA, is pointer only (licence: NONE) · get_code("f29345568db89515") 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 ZhuYun97/RoSA, 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. |
| rotate_image | Ran ran on a synthesized input |
microsoft/imitating-human-behaviour-w-diffusion/code/make_dataset.py code served (permissive licence) · get_code("c7c461dd154a4b37") 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 3, dtype family int, shape (4, 6, 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.
|
| scale_image | Ran ran on a synthesized input |
microsoft/imitating-human-behaviour-w-diffusion/code/make_dataset.py code served (permissive licence) · get_code("bf2dfa276aafa115") 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 3, dtype family int, shape (2, 3, 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.
|
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, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 4 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 |
|---|---|---|---|
| matrix_diag | 2 other papers 2 dated earlier |
2106.03375 (2021-06) Commutative Lie Group VAE for Disentanglement Learning |
2204.13846 (2022-04) RoSA: A Robust Self-Aligned Framework for Node-Node Graph Contrastive Learning |
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.
Diffusion models have emerged as powerful generative models in the text-toimage domain. This paper studies their application as observation-to-action models for imitating human behaviour in sequential environments. Human behaviour is stochastic and multimodal, with structured correlations between action dimensions. Meanwhile, standard modelling choices in behaviour cloning are limited in their expressiveness and may introduce bias into the cloned policy. We begin by pointing out the limitations of these choices. We then propose that diffusion models are an excellent fit for imitating human behaviour, since they learn an expressive distribution over the joint action space. We introduce several innovations to make diffusion models suitable for sequential environments; designing suitable architectures, investigating the role of guidance, and developing reliable sampling strategies. Experimentally, diffusion models closely match human demonstrations in a simulated robotic control task and a modern 3D gaming environment.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2301.10677")
get_code_for_paper("2301.10677")
have("2301.10677")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2301.10677.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2301.10677)
Connect an agent — have() is free.