11 of 15 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, 0 violated it and 8 have no contract verdict; 1 failure of our instrument; 4 no recorded run), measured 2026-11-21; 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/2004.04730.json · badge: /api/ran/2004.04730.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 |
|---|---|---|
| STONE-SAMA/x3d_mindspore | community (classifier label) classifier basis not recorded on the link |
5 ran · 2 no recorded run |
| Chianugoogidi/X3D-tf | community (classifier label) classifier basis not recorded on the link |
4 ran · 1 no recorded run |
| kkahatapitiya/X3D-Multigrid | extension (classifier label) classifier basis: classifier_2025 |
2 ran · 1 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| check_is_number | Ran ran on a synthesized input |
STONE-SAMA/x3d_mindspore/src/utils/check_param.py code served (permissive licence) · get_code("293dab24489b41d1") 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 int, ndim 0, dtype family int, 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.
|
| conv1x1x1 | Ran ran; our contract draft was wrong, not the code |
kkahatapitiya/X3D-Multigrid/x3d.py code served (permissive licence) · get_code("0a3fae1570b6c8c7") 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 Conv3d. 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_inplanes | Ran ran, honoured the contract we drafted |
kkahatapitiya/X3D-Multigrid/x3d.py code served (permissive licence) · get_code("acfa08610335818d") 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 list, ndim 2, 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.
|
| linear_warmup_learning_rate | Ran ran, honoured the contract we drafted |
STONE-SAMA/x3d_mindspore/src/schedule/lr_schedule.py code served (permissive licence) · get_code("d6a99ec714147ac1") 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 float, 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.
|
| normalize | Ran ran on a synthesized input |
Chianugoogidi/X3D-tf/utils.py code served (permissive licence) · get_code("0aca91fe0fed88cb") 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 EagerTensor, ndim 5, dtype family float, shape (2, 3, 4, 5, 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.
|
| recur_list2tuple | Ran ran on a synthesized input |
STONE-SAMA/x3d_mindspore/src/utils/config.py code served (permissive licence) · get_code("64bc6885f46ca205") 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.
|
| round_repeats | Ran ran on a synthesized input |
Chianugoogidi/X3D-tf/utils.py code served (permissive licence) · get_code("4ed34e164b9d3a9f") 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 int, ndim 0, dtype family int, 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.
|
| round_width | Ran ran on a synthesized input |
Chianugoogidi/X3D-tf/utils.py code served (permissive licence) · get_code("b033c87e17ebe6b9") 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 int, ndim 0, dtype family int, 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.
|
| to_tf_example | Ran ran on a synthesized input |
Chianugoogidi/X3D-tf/datasets/create_tfrecords.py code served (permissive licence) · get_code("f040ea8252820867") 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 SequenceExample. 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.
|
| warmup_cosine_annealing_lr_v1 | Ran ran on a synthesized input |
STONE-SAMA/x3d_mindspore/src/schedule/lr_schedule.py code served (permissive licence) · get_code("1a80346f67ccb9cf") 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 1, dtype family float, shape (1000,) 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.
|
| warmup_step_lr | Ran ran on a synthesized input |
STONE-SAMA/x3d_mindspore/src/schedule/lr_schedule.py code served (permissive licence) · get_code("e90ba252e203e0e9") 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 1, dtype family float, shape (10000,) 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.
|
| check_number | Not yet run unverified (harvested, no recorded run) |
STONE-SAMA/x3d_mindspore/src/utils/check_param.py code served (permissive licence) · get_code("8ce6bc3f1fabc927") How it ranno invocation recorded. |
| check_number_range | Not yet run unverified (harvested, no recorded run) |
STONE-SAMA/x3d_mindspore/src/utils/check_param.py code served (permissive licence) · get_code("e5f77ac329bf7def") How it ranno invocation recorded. |
| conv3x3x3 | Not yet run unverified (harvested, no recorded run) |
kkahatapitiya/X3D-Multigrid/x3d.py code served (permissive licence) · get_code("624693b57e7dcd4a") How it ranno invocation recorded. |
| write_tfrecord | Not yet run unverified (harvested, no recorded run) |
Chianugoogidi/X3D-tf/datasets/create_tfrecords.py code served (permissive licence) · get_code("7be94293e72825f2") How it ranno invocation recorded. |
Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 10 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 0 the same month, 8 later) and 5 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 |
|---|---|---|---|
| linear_warmup_learning_rate | 7 other papers 4 dated earlier, 3 later |
1506.01497 (2015-06) Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks |
1606.04797 (2016-06) V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation 1606.06650 (2016-06) 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation and 4 more not named here |
| check_is_number | 2 other papers 1 dated earlier, 1 later |
1905.11946 (2019-05) EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks |
2106.13230 (2021-06) Video Swin Transformer |
| check_number | 2 other papers 1 dated earlier, 1 later |
1905.11946 (2019-05) EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks |
2106.13230 (2021-06) Video Swin Transformer |
| check_number_range | 2 other papers 1 dated earlier, 1 later |
1905.11946 (2019-05) EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks |
2106.13230 (2021-06) Video Swin Transformer |
| get_inplanes | 2 other papers 1 dated earlier, 1 later |
1912.00998 (2019-12) A Multigrid Method for Efficiently Training Video Models |
2111.13675 (2021-11) Weakly-guided Self-supervised Pretraining for Temporal Activity Detection |
| conv1x1x1 | 1 other paper 1 dated earlier |
1912.00998 (2019-12) A Multigrid Method for Efficiently Training Video Models |
|
| conv3x3x3 | 1 other paper 1 dated earlier |
1912.00998 (2019-12) A Multigrid Method for Efficiently Training Video Models |
|
| recur_list2tuple | 1 other paper 1 later |
2106.13230 (2021-06) Video Swin Transformer |
|
| warmup_cosine_annealing_lr_v1 | 1 other paper 1 later |
2106.13230 (2021-06) Video Swin Transformer |
|
| warmup_step_lr | 1 other paper 1 later |
2106.13230 (2021-06) Video Swin Transformer |
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 2026-11-21.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
This paper presents X3D, a family of efficient video networks that progressively expand a tiny 2D image classification architecture along multiple network axes, in space, time, width and depth. Inspired by feature selection methods in machine learning, a simple stepwise network expansion approach is employed that expands a single axis in each step, such that good accuracy to complexity trade-off is achieved. To expand X3D to a specific target complexity, we perform progressive forward expansion followed by backward contraction. X3D achieves state-of-the-art performance while requiring 4.8x and 5.5x fewer multiply-adds and parameters for similar accuracy as previous work. Our most surprising finding is that networks with high spatiotemporal resolution can perform well, while being extremely light in terms of network width and parameters. We report competitive accuracy at unprecedented efficiency on video classification and detection benchmarks. Code will be available at: https://github.com/facebookresearch/SlowFast
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2004.04730")
get_code_for_paper("2004.04730")
have("2004.04730")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2004.04730.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2004.04730)
Connect an agent — have() is free.