14 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; 0 honoured the contract we drafted, 1 violated it and 11 have no contract verdict; 2 failures of our instrument; 1 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/2006.09286.json · badge: /api/ran/2006.09286.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 |
|---|---|---|
| satwik77/Transformer-Computation-Analysis | canonical (classifier label) classifier basis: census |
14 ran · 1 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| attention | Ran ran; our contract draft was wrong, not the code |
satwik77/Transformer-Computation-Analysis/Transformer/src/components/self_attention.py pointer only (licence: MIT); the stored copy get_code serves, from ruotianluo/Transformer_Captioning, is pointer only (licence: NONE) · get_code("20bb0ff4a2d77a03") 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 ruotianluo/Transformer_Captioning, 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. |
| cal_score | Ran ran on a synthesized input |
satwik77/Transformer-Computation-Analysis/Transformer/src/utils/evaluate.py code served (permissive licence) · get_code("34e826973176fc38") 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.
|
| cal_score_AP | Ran ran on a synthesized input |
satwik77/Transformer-Computation-Analysis/Transformer/src/utils/evaluate.py code served (permissive licence) · get_code("74e35c9e284520a1") 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.
|
| clones | Ran ran; our contract draft was wrong, not the code |
satwik77/Transformer-Computation-Analysis/Transformer/src/components/utils.py code served (permissive licence) · get_code("a3722169bbc81569") 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 ModuleList. 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.
|
| compute_bleu | Ran ran on a synthesized input |
satwik77/Transformer-Computation-Analysis/Transformer/src/utils/bleu.py code served (permissive licence) · get_code("ae3b0a421287c5c9") 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. 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_logger | Ran ran on a synthesized input |
satwik77/Transformer-Computation-Analysis/Transformer/src/utils/logger.py code served (permissive licence) · get_code("ebe3d1e68daeb780") 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 Logger. 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_std_opt | Ran ran on a synthesized input |
satwik77/Transformer-Computation-Analysis/Transformer/src/utils/helper.py code served (permissive licence) · get_code("c930b9e88eed3346") 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 NoamOpt. 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.
|
| greedy_decode | Ran ran on a synthesized input |
satwik77/Transformer-Computation-Analysis/Transformer/src/components/utils.py code served (permissive licence) · get_code("5f0fe04ab8eb68da") 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 Tensor, ndim 2, dtype family int, shape (2, 7) 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.
|
| run_epoch | Ran ran on a synthesized input |
satwik77/Transformer-Computation-Analysis/Transformer/src/model.py code served (permissive licence) · get_code("c179d23a93633b29") 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 Tensor, 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.
|
| sent_to_idx | Ran ran on a synthesized input |
satwik77/Transformer-Computation-Analysis/Transformer/src/utils/sentence_processing.py code served (permissive licence) · get_code("543b4d33c65c0c61") 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 list, 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.
|
| sent_to_tensor | Ran ran on a synthesized input |
satwik77/Transformer-Computation-Analysis/Transformer/src/utils/sentence_processing.py code served (permissive licence) · get_code("0a8dfa17ef60febe") 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 Tensor, ndim 2, dtype family int, shape (3, 1) 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.
|
| sents_to_idx | Ran ran on a synthesized input |
satwik77/Transformer-Computation-Analysis/Transformer/src/utils/sentence_processing.py code served (permissive licence) · get_code("6a992d9f1625b3ae") 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 list. 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.
|
| stack_to_string | Ran ran on a synthesized input |
satwik77/Transformer-Computation-Analysis/Transformer/src/utils/evaluate.py code served (permissive licence) · get_code("6d3d89720d9d4bd7") 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 str. 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.
|
| subsequent_mask | Ran ran, violated the contract we drafted |
satwik77/Transformer-Computation-Analysis/Transformer/src/components/utils.py pointer only (licence: MIT); the stored copy get_code serves, from cuhksz-nlp/R2Gen, is pointer only (licence: NONE) · get_code("66fbf162663d4cff") 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 cuhksz-nlp/R2Gen, 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. |
| make_model | Not yet run unverified (harvested, no recorded run) |
satwik77/Transformer-Computation-Analysis/Transformer/src/model.py code served (permissive licence) · get_code("a4731b662e3d1cd8") 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, 4 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 3 the same month, 4 later) and 11 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 |
|---|---|---|---|
| clones | 79 other papers 20 dated earlier, 3 the same month, 56 later · 11 only as an assembly brick |
1411.4555 (2014-11) Show and Tell: A Neural Image Caption Generator |
1612.00563 (2016-12) Self-critical Sequence Training for Image Captioning 1706.03762 (2017-06) Attention Is All You Need and 76 more not named here |
| attention | 27 other papers 9 dated earlier, 1 the same month, 16 later, 1 same year, order not determinable |
1411.4555 (2014-11) Show and Tell: A Neural Image Caption Generator |
1609.08144 (2016-09) Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation 1612.00563 (2016-12) Self-critical Sequence Training for Image Captioning and 24 more not named here |
| subsequent_mask | 21 other papers 7 dated earlier, 1 the same month, 13 later |
1411.4555 (2014-11) Show and Tell: A Neural Image Caption Generator |
1612.00563 (2016-12) Self-critical Sequence Training for Image Captioning 1707.07998 (2017-07) Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering and 18 more not named here |
| compute_bleu | 1 other paper 1 later |
2022.findings-naacl.160 (2022 (year only)) Learning Structural Information for Syntax-Controlled Paraphrase Generation |
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.
Transformers are being used extensively across several sequence modeling tasks. Significant research effort has been devoted to experimentally probe the inner workings of Transformers. However, our conceptual and theoretical understanding of their power and inherent limitations is still nascent. In particular, the roles of various components in Transformers such as positional encodings, attention heads, residual connections, and feedforward networks, are not clear. In this paper, we take a step towards answering these questions. We analyze the computational power as captured by Turing-completeness. We first provide an alternate and simpler proof to show that vanilla Transformers are Turing-complete and then we prove that Transformers with only positional masking and without any positional encoding are also Turing-complete. We further analyze the necessity of each component for the Turing-completeness of the network; interestingly, we find that a particular type of residual connection is necessary. We demonstrate the practical implications of our results via experiments on machine translation and synthetic tasks.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2006.09286")
get_code_for_paper("2006.09286")
have("2006.09286")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2006.09286.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2006.09286)
Connect an agent — have() is free.