Garima, Frederick Liu, Satyen Kale, Mukund Sundararajan
7 of 13 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 6 have no contract verdict; 1 failure of our instrument; 6 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/2002.08484.json · badge: /api/ran/2002.08484.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 |
|---|---|---|
| frederick0329/TracIn | canonical (classifier label) classifier basis: census |
6 ran · 2 no recorded run |
| rollovd/TracIn-PyTorch | community Papers with Code archive |
1 ran · 4 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| calculate_train_grads_per_checkpoint | Ran ran; our contract draft was wrong, not the code |
rollovd/TracIn-PyTorch/src/tracin.py pointer only (licence: NONE) · get_code("6def3c9b3d79c36d") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, rollovd/TracIn-PyTorch 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. |
| configure_cluster | Ran ran on a synthesized input |
frederick0329/TracIn/imagenet/resnet50/distribution_utils.py code served (permissive licence) · get_code("a3908ed79b55f793") 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.
|
| conv_block | Ran ran on a synthesized input |
frederick0329/TracIn/imagenet/resnet50/resnet.py code served (permissive licence) · get_code("6418d1ea781bab93") 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 4, 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.
|
| get_distribution_strategy | Ran ran on a synthesized input |
frederick0329/TracIn/imagenet/resnet50/distribution_utils.py code served (permissive licence) · get_code("db9d71dd2270776a") 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 MirroredStrategy. 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.
|
| mean_image_subtraction | Ran ran on a synthesized input |
frederick0329/TracIn/imagenet/resnet50/preprocessing.py code served (permissive licence) · get_code("e8512af53323cac3") 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 3, dtype family float, shape (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.
|
| normalize_images | Ran ran on a synthesized input |
frederick0329/TracIn/imagenet/resnet50/preprocessing.py code served (permissive licence) · get_code("1ae302f00326beec") 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 4, dtype family float, shape (2, 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.
|
| standardize_image | Ran ran on a synthesized input |
frederick0329/TracIn/imagenet/resnet50/preprocessing.py code served (permissive licence) · get_code("252a762d9fe4f7a2") 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 3, dtype family float, shape (4, 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.
|
| identity_block | Not yet run unverified (harvested, no recorded run) |
frederick0329/TracIn/imagenet/resnet50/resnet.py code served (permissive licence) · get_code("bc5c578afb5bb8b6") How it ranno invocation recorded. |
| load_checkpoint | Not yet run unverified (harvested, no recorded run) |
rollovd/TracIn-PyTorch/src/tracin.py pointer only (licence: NONE) · get_code("425a8b4fb346cc50") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, rollovd/TracIn-PyTorch 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. No invocation recorded. |
| precompute_models_with_weights | Not yet run unverified (harvested, no recorded run) |
rollovd/TracIn-PyTorch/src/tracin.py pointer only (licence: NONE) · get_code("cd0404df91f2edcf") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, rollovd/TracIn-PyTorch 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. No invocation recorded. |
| precompute_test_gradients | Not yet run unverified (harvested, no recorded run) |
rollovd/TracIn-PyTorch/src/tracin.py pointer only (licence: NONE) · get_code("ba995f8393ec29e3") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, rollovd/TracIn-PyTorch 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. No invocation recorded. |
| resnet50 | Not yet run unverified (harvested, no recorded run) |
frederick0329/TracIn/imagenet/resnet50/resnet.py code served (permissive licence) · get_code("4c1214758a0f6151") How it ranno invocation recorded. |
| vectorized_calculate_tracin_score | Not yet run unverified (harvested, no recorded run) |
rollovd/TracIn-PyTorch/src/tracin.py pointer only (licence: NONE) · get_code("bd5f57e1f5a91dc3") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, rollovd/TracIn-PyTorch 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. No invocation recorded. |
Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 13 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.
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.
We introduce a method called TracIn that computes the influence of a training example on a prediction made by the model. The idea is to trace how the loss on the test point changes during the training process whenever the training example of interest was utilized. We provide a scalable implementation of TracIn via: (a) a first-order gradient approximation to the exact computation, (b) saved checkpoints of standard training procedures, and (c) cherry-picking layers of a deep neural network. In contrast with previously proposed methods, TracIn is simple to implement; all it needs is the ability to work with gradients, checkpoints, and loss functions. The method is general. It applies to any machine learning model trained using stochastic gradient descent or a variant of it, agnostic of architecture, domain and task. We expect the method to be widely useful within processes that study and improve training data. Code is available at [1].
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2002.08484")
get_code_for_paper("2002.08484")
have("2002.08484")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2002.08484.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2002.08484)
Connect an agent — have() is free.