10 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; 4 honoured the contract we drafted, 0 violated it and 5 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/1910.02562.json · badge: /api/ran/1910.02562.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 |
|---|---|---|
| jiangxiluning/MASTER-TF | canonical (classifier label) classifier basis: census |
9 ran · 0 no recorded run |
| S-HuaBomb/MASTER-paddle | community (classifier label) classifier basis not recorded on the link |
1 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| calculate_gain | Ran ran, honoured the contract we drafted |
S-HuaBomb/MASTER-paddle/model/initializers.py code served (permissive licence) · get_code("5c1510caf3cf76cb") 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 |
jiangxiluning/MASTER-TF/src/model/transformer.py pointer only (licence: MIT); the stored copy get_code serves, from nicoladainese96/RelationalDeepRL, is pointer only (licence: NONE) · get_code("2271c8526c9dce4e") 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 nicoladainese96/RelationalDeepRL, 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. |
| conv33 | Ran ran on a synthesized input |
jiangxiluning/MASTER-TF/src/model/backbone.py code served (permissive licence) · get_code("39161ed30377ac7c") 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 Conv2D. 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.
|
| create_padding_mask | Ran ran on a synthesized input |
jiangxiluning/MASTER-TF/src/model/transformer_tf.py code served (permissive licence) · get_code("436719c2595f1c54") 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, 1, 1, 4) 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.
|
| get_angles | Ran ran, honoured the contract we drafted |
jiangxiluning/MASTER-TF/src/model/transformer.py pointer only (licence: MIT); the stored copy get_code serves, from chihchenghsieh/eventlogdice, is pointer only (licence: NONE) · get_code("7816c6d65ab55d8f") 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 chihchenghsieh/eventlogdice, 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. |
| get_vocabulary | Ran ran on a synthesized input |
jiangxiluning/MASTER-TF/src/dataset/utils.py code served (permissive licence) · get_code("a7852c913c2d2af2") 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.
|
| positional_encoding | Ran ran, honoured the contract we drafted |
jiangxiluning/MASTER-TF/src/model/transformer_tf.py code served (permissive licence) · get_code("29af386f64351dae") 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 (1, 8, 16) 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.
|
| positional_encoding | Ran ran, honoured the contract we drafted |
jiangxiluning/MASTER-TF/src/model/transformer.py code served (permissive licence) · get_code("70fe09020aeba7f4") 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 EagerTensor, ndim 3, dtype family float, shape (1, 8, 16) 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.
|
| resize_width | Ran ran on a synthesized input |
jiangxiluning/MASTER-TF/src/dataset/utils.py code served (permissive licence) · get_code("bf79ed7abc99e5ee") 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.
|
| rotate_img | Ran ran on a synthesized input |
jiangxiluning/MASTER-TF/src/dataset/utils.py code served (permissive licence) · get_code("e72bcd44ddf201b9") 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 (128, 128, 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 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, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 2 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 |
|---|---|---|---|
| get_angles | 14 other papers 5 dated earlier, 9 later · 2 only as an assembly brick |
1704.04368 (2017-04) Get To The Point: Summarization with Pointer-Generator Networks |
1706.03762 (2017-06) Attention Is All You Need 1810.04805 (2018-10) BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding and 11 more not named here |
| positional_encoding | 5 other papers 3 dated earlier, 2 later · 1 only as an assembly brick |
1704.04368 (2017-04) Get To The Point: Summarization with Pointer-Generator Networks |
1706.03762 (2017-06) Attention Is All You Need 1810.04805 (2018-10) BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding and 2 more not named here |
| calculate_gain | 1 other paper 1 dated earlier |
1612.04402 (2016-12) Finding Tiny Faces |
|
| clones | 1 other paper 1 dated earlier |
1806.01830 (2018-06) Relational Deep Reinforcement Learning |
|
| create_padding_mask | 1 other paper 1 dated earlier |
1905.09904 (2019-05) CDSA: Cross-Dimensional Self-Attention for Multivariate, Geo-tagged Time Series Imputation |
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.
Attention-based scene text recognizers have gained huge success, which leverages a more compact intermediate representation to learn 1d- or 2d- attention by a RNN-based encoder-decoder architecture. However, such methods suffer from attention-drift problem because high similarity among encoded features leads to attention confusion under the RNN-based local attention mechanism. Moreover, RNN-based methods have low efficiency due to poor parallelization. To overcome these problems, we propose the MASTER, a self-attention based scene text recognizer that (1) not only encodes the input-output attention but also learns self-attention which encodes feature-feature and target-target relationships inside the encoder and decoder and (2) learns a more powerful and robust intermediate representation to spatial distortion, and (3) owns a great training efficiency because of high training parallelization and a high-speed inference because of an efficient memory-cache mechanism. Extensive experiments on various benchmarks demonstrate the superior performance of our MASTER on both regular and irregular scene text. Pytorch code can be found at https://github.com/wenwenyu/MASTER-pytorch, and Tensorflow code can be found at https://github.com/jiangxiluning/MASTER-TF.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1910.02562")
get_code_for_paper("1910.02562")
have("1910.02562")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/1910.02562.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/1910.02562)
Connect an agent — have() is free.