Yejin Choi, Noah Smith, Suchin Gururangan, Maarten Sap, Samuel Gehman
4 of 5 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 1 has no contract verdict; 3 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/2009.11462.json · badge: /api/ran/2009.11462.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 |
|---|---|---|
| allenai/real-toxicity-prompts | canonical (classifier label) classifier basis: census |
4 ran · 1 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| first | Ran ran on a synthesized input |
allenai/real-toxicity-prompts/utils/utils.py code served (permissive licence) · get_code("af7ceb2cad5d5b2c") 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_var | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
allenai/real-toxicity-prompts/generation/pplm_generation.py code served (permissive licence) · get_code("bbebd95a156061b0") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 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 code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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.
|
| top_k_filter | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
allenai/real-toxicity-prompts/generation/pplm_generation.py code served (permissive licence) · get_code("ac71b1f4007ef1dd") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (2, 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.
|
| unpack_scores | Ran ran; our contract draft was wrong, not the code |
allenai/real-toxicity-prompts/utils/perspective_api.py code served (permissive licence) · get_code("51f543f4f2fda251") 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 1, 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.
|
| adjust_length_to_model | Not yet run unverified (harvested, no recorded run) |
allenai/real-toxicity-prompts/generation/gpt2_generation.py code served (permissive licence) · get_code("5f768e9c3c410ca0") How it ranno invocation recorded. |
Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 3 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 3 later) and 2 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 |
|---|---|---|---|
| to_var | 4 other papers 1 dated earlier, 3 later |
1912.02164 (2019-12) Plug and Play Language Models: A Simple Approach to Controlled Text Generation |
2010.05906 (2020-10) Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning 2011.04000 (2020-11) Adapting a Language Model for Controlled Affective Text Generation and 1 more not named here |
| top_k_filter | 3 other papers 1 dated earlier, 2 later |
1912.02164 (2019-12) Plug and Play Language Models: A Simple Approach to Controlled Text Generation |
2011.04000 (2020-11) Adapting a Language Model for Controlled Affective Text Generation 2105.00164 (2021-05) Hidden Backdoors in Human-Centric Language Models |
| unpack_scores | 2 other papers 2 later |
2304.12397 (2023-04) On the Challenges of Using Black-Box APIs for Toxicity Evaluation in Research |
2310.07589 (2023-10) Goodtriever: Adaptive Toxicity Mitigation with Retrieval-augmented Models |
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.
Pretrained neural language models (LMs) are prone to generating racist, sexist, or otherwise toxic language which hinders their safe deployment. We investigate the extent to which pretrained LMs can be prompted to generate toxic language, and the effectiveness of controllable text generation algorithms at preventing such toxic degeneration. We create and release RE-ALTOXICITYPROMPTS, a dataset of 100K naturally occurring, sentence-level prompts derived from a large corpus of English web text, paired with toxicity scores from a widelyused toxicity classifier. Using REALTOXICI-TYPROMPTS, we find that pretrained LMs can degenerate into toxic text even from seemingly innocuous prompts. We empirically assess several controllable generation methods, and find that while data-or compute-intensive methods (e.g., adaptive pretraining on non-toxic data) are more effective at steering away from toxicity than simpler solutions (e.g., banning "bad" words), no current method is failsafe against neural toxic degeneration. To pinpoint the potential cause of such persistent toxic degeneration, we analyze two web text corpora used to pretrain several LMs (including GPT-2; Radford et al., 2019), and find a significant amount of offensive, factually unreliable, and otherwise toxic content. Our work provides a test bed for evaluating toxic generations by LMs and stresses the need for better data selection processes for pretraining.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2009.11462")
get_code_for_paper("2009.11462")
have("2009.11462")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2009.11462.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2009.11462)
Connect an agent — have() is free.