Ruslan Salakhutdinov, Yiming Yang, Quoc Le, Zihang Dai, Zhilin Yang, Jaime Carbonell
15 of 24 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 7 failures of our instrument; 9 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/1906.08237.json · badge: /api/ran/1906.08237.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 |
|---|---|---|
| samwisegamjeee/pytorch-transformers | community (classifier label) classifier basis not recorded on the link |
11 ran · 6 no recorded run |
| chesterdu/contrastive_summary | community Papers with Code archive |
2 ran · 0 no recorded run |
| zihangdai/xlnet | marked official in Papers with Code Papers with Code archive |
1 ran · 1 no recorded run |
| fanchenyou/transformer-study | community Papers with Code archive |
1 ran · 0 no recorded run |
| zaradana/Fast_BERT | community Papers with Code archive |
0 ran · 1 no recorded run |
| utterworks/fast-bert | community Papers with Code archive |
0 ran · 1 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| swish | Ran ran; our contract draft was wrong, not the code |
samwisegamjeee/pytorch-transformers/pytorch_transformers/modeling_bert.py code served (permissive licence) · get_code("0f786c407fb1ee4c") How it ranRan in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-04T22:33:52Z). 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.
|
| SupConLoss | Ran ran on a synthesized input |
chesterdu/contrastive_summary/src/model.py pointer only (licence: NONE) · get_code("624bba127433de69") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, chesterdu/contrastive_summary 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. |
| XLNet | Ran ran on a synthesized input · constructed an object; no result was computed |
fanchenyou/transformer-study/transformer_xlnet_4.py pointer only (licence: NONE) · get_code("30647553d552c86f") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, fanchenyou/transformer-study 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. |
| build_tf_to_pytorch_map | Ran ran; our contract draft was wrong, not the code |
samwisegamjeee/pytorch-transformers/pytorch_transformers/modeling_transfo_xl.py code served (permissive licence) · get_code("35ef111fc00c21b4") 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.
|
| build_tf_xlnet_to_pytorch_map | Ran ran on a synthesized input |
samwisegamjeee/pytorch-transformers/pytorch_transformers/modeling_xlnet.py code served (permissive licence) · get_code("c92ba449e48ecffe") 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.
|
| gelu | Ran ran; our contract draft was wrong, not the code |
samwisegamjeee/pytorch-transformers/pytorch_transformers/modeling_gpt2.py code served (permissive licence) · get_code("8d23fbe2b99b840b") 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 Tensor, ndim 2, dtype family float, shape (2, 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.
|
| gelu | Ran ran, honoured the contract we drafted |
samwisegamjeee/pytorch-transformers/pytorch_transformers/modeling_bert.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from tanmay1618/text_to_sql_bert, is pointer only (licence: NONE) · get_code("fdc64f4c72036ae4") How it ranThe body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from tanmay1618/text_to_sql_bert, 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. |
| gelu | Ran ran on a synthesized input |
samwisegamjeee/pytorch-transformers/pytorch_transformers/modeling_xlnet.py code served (permissive licence) · get_code("b05b2bb38c0e4e72") 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 float, shape (2, 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.
|
| gelu | Ran ran; our contract draft was wrong, not the code |
samwisegamjeee/pytorch-transformers/pytorch_transformers/modeling_xlm.py code served (permissive licence) · get_code("b3c2618f6b7fb60c") 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 float, shape (2, 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_masks | Ran ran on a synthesized input |
samwisegamjeee/pytorch-transformers/pytorch_transformers/modeling_xlm.py code served (permissive licence) · get_code("f5d8d44f65a08b76") 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.
|
| prune_conv1d_layer | Ran ran; our contract draft was wrong, not the code |
samwisegamjeee/pytorch-transformers/pytorch_transformers/modeling_utils.py code served (permissive licence) · get_code("7183a17dd79327a8") 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 Conv1D. 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.
|
| prune_linear_layer | Ran ran; our contract draft was wrong, not the code |
samwisegamjeee/pytorch-transformers/pytorch_transformers/modeling_utils.py code served (permissive licence) · get_code("d30d6c3098df2c42") 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 Linear. 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.
|
| relative_positional_encoding | Ran ran, honoured the contract we drafted |
zihangdai/xlnet/modeling.py code served (permissive licence) · get_code("4276ef7411886c72") 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 (10, 4, 8) 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.
|
| sample_logits | Ran ran; our contract draft was wrong, not the code |
samwisegamjeee/pytorch-transformers/pytorch_transformers/modeling_transfo_xl_utilities.py code served (permissive licence) · get_code("93228a3eb5c4d179") 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 3, dtype family float, shape (2, 3, 6) 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.
|
| scl_model_Xlnet | Ran ran on a synthesized input · constructed an object; no result was computed |
chesterdu/contrastive_summary/src/model.py pointer only (licence: NONE) · get_code("1370bb66bcbac8f1") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, chesterdu/contrastive_summary 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. |
| XLNetForMultiLabelSequenceClassification | Not yet run unverified (harvested, no recorded run) |
zaradana/Fast_BERT/0_fast_bert/modeling.py code served (permissive licence) · get_code("ea4abb20faaddb4d") How it ranno invocation recorded. |
| XLNetForMultiLabelSequenceClassification | Not yet run unverified (harvested, no recorded run) |
utterworks/fast-bert/fast_bert/modeling.py code served (permissive licence) · get_code("de032896e6064f69") How it ranno invocation recorded. |
| load_tf_weights_in_bert | Not yet run unverified (harvested, no recorded run) |
samwisegamjeee/pytorch-transformers/pytorch_transformers/modeling_bert.py code served (permissive licence) · get_code("03a94dbb436249a3") How it ranno invocation recorded. |
| load_tf_weights_in_gpt2 | Not yet run unverified (harvested, no recorded run) |
samwisegamjeee/pytorch-transformers/pytorch_transformers/modeling_gpt2.py code served (permissive licence) · get_code("07bb0220eb5b609f") How it ranno invocation recorded. |
| load_tf_weights_in_openai_gpt | Not yet run unverified (harvested, no recorded run) |
samwisegamjeee/pytorch-transformers/pytorch_transformers/modeling_openai.py code served (permissive licence) · get_code("42ee168c3ae12e60") How it ranno invocation recorded. |
| load_tf_weights_in_transfo_xl | Not yet run unverified (harvested, no recorded run) |
samwisegamjeee/pytorch-transformers/pytorch_transformers/modeling_transfo_xl.py code served (permissive licence) · get_code("23d246e59ef9447b") How it ranno invocation recorded. |
| load_tf_weights_in_xlnet | Not yet run unverified (harvested, no recorded run) |
samwisegamjeee/pytorch-transformers/pytorch_transformers/modeling_xlnet.py code served (permissive licence) · get_code("4a94662ff3b5c5cf") How it ranno invocation recorded. |
| prune_layer | Not yet run unverified (harvested, no recorded run) |
samwisegamjeee/pytorch-transformers/pytorch_transformers/modeling_utils.py code served (permissive licence) · get_code("e31093ffc8275cff") How it ranno invocation recorded. |
| transformer_xl | Not yet run unverified (harvested, no recorded run) |
zihangdai/xlnet/modeling.py code served (permissive licence) · get_code("346015e252bc02c1") How it ranno invocation recorded. |
Of 24 samples lifted from this paper's linked repositories, 24 carry a function identity and 0 do not. Of the 23 distinct functions with an identity, 18 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 4 the same month, 17 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 |
|---|---|---|---|
| swish | 206 other papers 9 dated earlier, 2 the same month, 195 later · 44 only as an assembly brick |
1408.5882 (2014-08) Convolutional Neural Networks for Sentence Classification |
1805.12114 (2018-05) Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models 1809.01357 (2018-09) Zero Shot Learning for Code Education: Rubric Sampling with Deep Learning Inference and 203 more not named here |
| gelu | 198 other papers 8 dated earlier, 4 the same month, 186 later · 32 only as an assembly brick |
1408.5882 (2014-08) Convolutional Neural Networks for Sentence Classification |
1810.04805 (2018-10) BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding 1901.10125 (2019-01) Glyce: Glyph-vectors for Chinese Character Representations and 195 more not named here |
| gelu | 51 other papers 3 dated earlier, 3 the same month, 45 later · 8 only as an assembly brick |
1706.03762 (2017-06) Attention Is All You Need |
1810.04805 (2018-10) BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding 1901.02860 (2019-01) Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context and 48 more not named here |
| prune_linear_layer | 29 other papers 1 dated earlier, 1 the same month, 27 later |
1810.04805 (2018-10) BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding |
1906.08230 (2019-06) Evaluating Protein Transfer Learning with TAPE 1909.05311 (2019-09) Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering and 26 more not named here |
| gelu | 17 other papers 1 dated earlier, 16 later |
1905.12790 (2019-05) A Generalized Framework of Sequence Generation with Application to Undirected Sequence Models |
1909.05311 (2019-09) Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering 1911.02116 (2019-11) Unsupervised Cross-lingual Representation Learning at Scale and 14 more not named here |
| prune_conv1d_layer | 16 other papers 16 later |
1909.05311 (2019-09) Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering |
1909.11942 (2019-09) ALBERT: A Lite BERT for Self-supervised Learning of Language Representations 1911.00720 (2019-11) ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations and 13 more not named here |
| sample_logits | 14 other papers 1 dated earlier, 13 later · 2 only as an assembly brick |
1901.02860 (2019-01) Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context |
1908.09355 (2019-08) Patient Knowledge Distillation for BERT Model Compression 1909.05311 (2019-09) Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering and 11 more not named here |
| build_tf_to_pytorch_map | 10 other papers 1 dated earlier, 9 later |
1901.02860 (2019-01) Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context |
1908.09355 (2019-08) Patient Knowledge Distillation for BERT Model Compression 1909.05311 (2019-09) Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering and 7 more not named here |
| load_tf_weights_in_openai_gpt | 8 other papers 8 later |
1909.05311 (2019-09) Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering |
2002.01808 (2020-02) K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters 2004.03829 (2020-04) Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learning and 5 more not named here |
| prune_layer | 7 other papers 7 later |
1909.11942 (2019-09) ALBERT: A Lite BERT for Self-supervised Learning of Language Representations |
2005.00558 (2020-05) POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-training 2007.02439 (2020-07) Pretrained Generalized Autoregressive Model with Adaptive Probabilistic Label Clusters for Extreme Multi-label Text Classification and 4 more not named here |
| load_tf_weights_in_transfo_xl | 6 other papers 6 later |
1909.05311 (2019-09) Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering |
2002.01808 (2020-02) K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters 2004.03829 (2020-04) Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learning and 3 more not named here |
| build_tf_xlnet_to_pytorch_map | 4 other papers 4 later |
1909.05311 (2019-09) Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering |
2007.02439 (2020-07) Pretrained Generalized Autoregressive Model with Adaptive Probabilistic Label Clusters for Extreme Multi-label Text Classification 2010.05607 (2020-10) The elephant in the interpretability room: Why use attention as explanation when we have saliency methods? and 1 more not named here |
| get_masks | 3 other papers 3 later |
1909.05311 (2019-09) Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering |
2005.00558 (2020-05) POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-training 2010.05607 (2020-10) The elephant in the interpretability room: Why use attention as explanation when we have saliency methods? |
| load_tf_weights_in_bert | 3 other papers 3 later |
1909.05311 (2019-09) Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering |
2005.00558 (2020-05) POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-training 2021.emnlp-main.721 (2021 (year only)) YASO: A Targeted Sentiment Analysis Evaluation Dataset for Open-Domain Reviews |
| load_tf_weights_in_xlnet | 3 other papers 3 later |
1909.05311 (2019-09) Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering |
2007.02439 (2020-07) Pretrained Generalized Autoregressive Model with Adaptive Probabilistic Label Clusters for Extreme Multi-label Text Classification 2010.05607 (2020-10) The elephant in the interpretability room: Why use attention as explanation when we have saliency methods? |
| gelu | 2 other papers 2 later |
1909.05311 (2019-09) Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering |
2007.02439 (2020-07) Pretrained Generalized Autoregressive Model with Adaptive Probabilistic Label Clusters for Extreme Multi-label Text Classification |
| load_tf_weights_in_gpt2 | 2 other papers 2 later |
1909.05311 (2019-09) Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering |
2005.00558 (2020-05) POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-training |
| transformer_xl brick of this paper's assembly: entry |
1 other paper 1 dated earlier |
1901.02860 (2019-01) Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context |
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.
With the capability of modeling bidirectional contexts, denoising autoencoding based pretraining like BERT achieves better performance than pretraining approaches based on autoregressive language modeling. However, relying on corrupting the input with masks, BERT neglects dependency between the masked positions and suffers from a pretrain-finetune discrepancy. In light of these pros and cons, we propose XLNet, a generalized autoregressive pretraining method that (1) enables learning bidirectional contexts by maximizing the expected likelihood over all permutations of the factorization order and (2) overcomes the limitations of BERT thanks to its autoregressive formulation. Furthermore, XLNet integrates ideas from Transformer-XL, the state-of-the-art autoregressive model, into pretraining. Empirically, under comparable experiment settings, XLNet outperforms BERT on 20 tasks, often by a large margin, including question answering, natural language inference, sentiment analysis, and document ranking. 1 . * Equal contribution. Order determined by swapping the one in [9]. 1 Pretrained models and code are available at https://github.com/zihangdai/xlnet 33rd Conference on Neural Information Processing Systems (NeurIPS 2019),
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1906.08237")
get_code_for_paper("1906.08237")
have("1906.08237")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/1906.08237.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/1906.08237)
Connect an agent — have() is free.