3 of 10 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 3 have no contract verdict; 0 failures of our instrument; 7 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/2210.05668.json · badge: /api/ran/2210.05668.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 |
|---|---|---|
| yang-li-2000/understanding-embodied-reference-with-touch-line-transformer | canonical (classifier label) classifier basis not recorded on the link |
3 ran · 7 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| ArmEquation | Ran ran on a synthesized input |
yang-li-2000/understanding-embodied-reference-with-touch-line-transformer/models/mdetr.py code served (permissive licence) · get_code("8981e75acb0c4ff6") 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 2, 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.
|
| box_cxcywh_to_vertices | Ran ran on a synthesized input |
yang-li-2000/understanding-embodied-reference-with-touch-line-transformer/models/mdetr.py code served (permissive licence) · get_code("0ecebfab6929ce3c") 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 3, 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.
|
| string_to_bool | Ran ran on a synthesized input |
yang-li-2000/understanding-embodied-reference-with-touch-line-transformer/main_ref.py code served (permissive licence) · get_code("2f6ccc9112e1fb36") 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 bool, 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.
|
| build_transformer | Not yet run unverified (harvested, no recorded run) |
yang-li-2000/understanding-embodied-reference-with-touch-line-transformer/models/transformer.py code served (permissive licence) · get_code("1e7c78d96968a055") How it ranno invocation recorded. |
| build_transformer | Not yet run unverified (harvested, no recorded run) |
yang-li-2000/understanding-embodied-reference-with-touch-line-transformer/models/transformer_ori.py code served (permissive licence) · get_code("b0beffbe8deaa71a") How it ranno invocation recorded. |
| get_init_file | Not yet run unverified (harvested, no recorded run) |
yang-li-2000/understanding-embodied-reference-with-touch-line-transformer/run_with_submitit_gqa_eval.py code served (permissive licence) · get_code("d71abefc7fbfd28f") How it ranno invocation recorded. |
| get_init_file | Not yet run unverified (harvested, no recorded run) |
yang-li-2000/understanding-embodied-reference-with-touch-line-transformer/run_with_submitit.py code served (permissive licence) · get_code("21c87739b7777475") How it ranno invocation recorded. |
| get_pose_loss | Not yet run unverified (harvested, no recorded run) |
yang-li-2000/understanding-embodied-reference-with-touch-line-transformer/models/mdetr.py code served (permissive licence) · get_code("d2a29b502b98e1b7") How it ranno invocation recorded. |
| get_shared_folder | Not yet run unverified (harvested, no recorded run) |
yang-li-2000/understanding-embodied-reference-with-touch-line-transformer/run_with_submitit_gqa_eval.py code served (permissive licence) · get_code("84691ff17ae1504d") How it ranno invocation recorded. |
| get_shared_folder | Not yet run unverified (harvested, no recorded run) |
yang-li-2000/understanding-embodied-reference-with-touch-line-transformer/run_with_submitit.py code served (permissive licence) · get_code("f8c4f1b9ea37610b") How it ranno invocation recorded. |
Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 2 later) and 7 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_init_file | 4 other papers 2 dated earlier, 2 later |
2104.12763 (2021-04) MDETR -Modulated Detection for End-to-End Multi-Modal Understanding |
2112.08654 (2021-12) Learning to Prompt for Continual Learning 2404.14721 (2024-04) Dynamically Anchored Prompting for Task-Imbalanced Continual Learning and 1 more not named here |
| get_shared_folder | 2 other papers 1 dated earlier, 1 later |
2104.12763 (2021-04) MDETR -Modulated Detection for End-to-End Multi-Modal Understanding |
2505.11726 (2025-05) Disambiguating Reference in Visually Grounded Dialogues through Joint Modeling of Textual and Multimodal Semantic Structures |
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.
We study embodied reference understanding, the task of locating referents using embodied gestural signals and language references. Human studies have revealed that objects referred to or pointed to do not lie on the elbow-wrist line, a common misconception; instead, they lie on the so-called virtual touch line. However, existing human pose representations fail to incorporate the virtual touch line. To tackle this problem, we devise the touch-line transformer: It takes as input tokenized visual and textual features and simultaneously predicts the referent's bounding box and a touch-line vector. Leveraging this touch-line prior, we further devise a geometric consistency loss that encourages the co-linearity between referents and touch lines. Using the touch-line as gestural information improves model performances significantly. Experiments on the YouRefIt dataset show our method achieves a +25.0% accuracy improvement under the 0.75 IoU criterion, closing 63.6% of the gap between model and human performances. Furthermore, we computationally verify prior human studies by showing that computational models more accurately locate referents when using the virtual touch line than when using the elbow-wrist line.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2210.05668")
get_code_for_paper("2210.05668")
have("2210.05668")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2210.05668.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2210.05668)
Connect an agent — have() is free.