Home › Code › clean_string

clean_string

Syntologyentry name in harvested code

Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

clean_string appears in the code Syntology harvested for 21 papers, as 25 distinct code bodies found in 27 places (a place is one code body under one paper). Of the 21 papers, 21 with a sample that ran: 11 with a run with no instrument failure, 10 where every run was a failure of Syntology's instrument. 24 of the code bodies carry a behaviour fingerprint.

What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named clean_string do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; get_code(code_sha256="…") returns this sample's fingerprint on the shared battery, with the battery's shuffled null and lift; not shown on this site (how to connect). "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

The 25 distinct code bodies named clean_string: 24 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
10ran · our draft was wrong
0ran; the contract check could not run
14ran
1unverified
24fingerprinted

Licence is a property of each copy, so it is counted per place: 10 of the 27 places are pointer only (Syntology does not serve that copy's text); at 1 of them this paper's copy is under a permissive licence, but the stored copy of the same code that Syntology serves is not cleared for its text (hover the licence cell for why). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.

“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “the contract check could not run” (RAISES, DEP_MISSING or TIMEOUT; hover a row's label for which) are failures of Syntology's instrument, not of the code, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page; “with no instrument failure” is honoured, violated and ran with no contract checked. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Papers

21 papers shown of 21, newest first; 27 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive, and the graph's for 2 papers added by Syntology; 4 papers have no page here and are shown by their id only (arXiv: for an arXiv id; an id from another venue, such as ACL Anthology or AAAI, is named as that venue's id, never as an arXiv id). Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

PaperDateFileStatus SyntologyLicence
Big Tech-Funded AI Papers Have Higher Citation Impact, Greater Insularity, and Larger Recency Bias added by Syntology 2025-12 (from id) Peerzival/impact-big-tech-funding/src/services/fuzzy_matching_service.py fc21974dc5c48c50 ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
Pun Unintended: LLMs and the Illusion of Humor Understanding added by Syntology 2025-09 (from id) alezanga/punintended/dataset_generation/openai_generate_synthetic_data_script.py 3016ce5928efb28e ran · our draft was wrong fingerprinted no licence file found · pointer only
RustMap: Towards Project-Scale C-to-Rust Migration via Program Analysis and LLM 2025-03 (from id) cxm211/rustmap/scaffolding_py_tools/GlobDep_FnDep.py 4eb083afe9e6bd3a ran fingerprinted Apache-2.0 (permissive)
Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models 18 Nov 2024 gzcch/safety_snowball_agent/framework_for_mmsafety.py 095bcf8b8717e139 ran · our draft was wrong fingerprinted no licence file found · pointer only
Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models 18 Nov 2024 gzcch/safety_snowball_agent/framework_for_opensource_VLLMs.py 53ef7b3c226ba1bc ran · our draft was wrong fingerprinted no licence file found · pointer only
Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models 18 Nov 2024 gzcch/safety_snowball_agent/framework_on_GPT.py 05a067eeb8f96b68 ran · our draft was wrong fingerprinted no licence file found · pointer only
ELF-Gym: Evaluating Large Language Models Generated Features for Tabular Prediction 13 Oct 2024 Lilyzhangyanlin/ELF-Gym/task/task.py e646a1e4fb2a7ff1 ran · our draft was wrong fingerprinted no licence file found · pointer only
LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement 22 Mar 2024 squeezeailab/llm2llm/report_results.py 9d3687f5a5e31878 ran · our draft was wrong fingerprinted MIT (permissive)
Personalized LoRA for Human-Centered Text Understanding 10 Mar 2024 yoyo-yun/plora/dataset/utils.py aee09c284260f322 ran · our draft was wrong fingerprinted no licence file found · pointer only
CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusion 8 Mar 2024 thudm/cogview4/inference/gradio_web_demo.py 15543c2e826f861a ran fingerprinted Apache-2.0 (permissive)
RAM-EHR: Retrieval Augmentation Meets Clinical Predictions on Electronic Health Records 25 Feb 2024 ritaranx/RAM-EHR/query_drugbank.py 3e5d94b331e392fe ran · our draft was wrong fingerprinted MIT (permissive)
AI-generated text boundary detection with RoFT 14 Nov 2023 silversolver/ai_boundary_detection/perplexity.py 8e8cac04daff4e38 ran fingerprinted no licence file found · pointer only
Preventing Language Models From Hiding Their Reasoning 27 Oct 2023 redwoodresearch/text-steganography-benchmark/textsteg/attackers/instruction_attackers.py 39f566ebc9b12a49 ran fingerprinted no licence file found · pointer only
L2MAC: Large Language Model Automatic Computer for Extensive Code Generation 2 Oct 2023 samholt/l2mac/l2mac/utils/l2mac.py 0b71a825504a4b60 ran fingerprinted MIT (permissive)
BRIO: Bringing Order to Abstractive Summarization 31 Mar 2022 webis-de/summary-workbench/cli/plugins.py 6ab87da715f75e06 ran fingerprinted MIT (permissive)
From LSAT: The Progress and Challenges of Complex Reasoning 2 Aug 2021 zhongwanjun/AR-LSAT/LSTM/utils_multiple_choice.py 2ee6204e8f1548f9 ran fingerprinted MIT (permissive)
CVEfixes: Automated Collection of Vulnerabilities and Their Fixes from Open-Source Software 19 Jul 2021 secureIT-project/CVEfixes/Code/collect_commits.py bee7848557c8eb49 ran · our draft was wrong fingerprinted licence not identified · pointer only
DocBERT: BERT for Document Classification 17 Apr 2019 castorini/hedwig/datasets/ag_news.py 055cfc782a4a7f7a ran fingerprinted Apache-2.0 (permissive)
DocBERT: BERT for Document Classification 17 Apr 2019 castorini/hedwig/datasets/imdb_torchtext.py 4488684e7b9d2033 ran fingerprinted Apache-2.0 (permissive)
DocBERT: BERT for Document Classification 17 Apr 2019 dki-lab/covid19-classification/hedwig/datasets/litcovid.py 2c0a5cc710857b97 ran fingerprinted Apache-2.0 (permissive)
DocBERT: BERT for Document Classification 17 Apr 2019 dki-lab/covid19-classification/hedwig/datasets/reuters.py 17e08d7d57300508 ran fingerprinted Apache-2.0 (permissive)
DocBERT: BERT for Document Classification 17 Apr 2019 dki-lab/covid19-classification/hedwig/datasets/robust45.py 2036a64496afb96e unverified Apache-2.0 (permissive)
Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence 22 Mar 2019 recommeddit/labs/AnmolStuff/gsearch.py e27773680535fad6 ran fingerprinted MIT (permissive)
ACL Anthology id 2025.findings-acl.360 CarlWangChina/MuDiT-MuSiT/clap_finetuning_zh_en/gen_train_test_data.py e376eb20ead9c2fb ran fingerprinted MIT (permissive)
ACL Anthology id 2024.findings-acl.388 SqueezeAILab/LLM2LLM/report_results.py 9d3687f5a5e31878 ran · our draft was wrong fingerprinted MIT (permissive)
ACL Anthology id 2023.findings-acl.810 yoyo-yun/DG_RRR/dataset/utils.py aee09c284260f322 ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
ACL Anthology id 2023.emnlp-main.1005 YichenZW/Coh-MGT-Detection/preprocess/construct_graph.py 59a0c17b985fb226 ran fingerprinted MIT (permissive)

This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the harvest. "Pointer only" means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is under a permissive licence, but the stored copy of the same code that Syntology serves is not cleared for its text. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections