Home › Code › masked_var

masked_var

Syntologyentry name in harvested coderead from the graph 2026-09-24

masked_var appears in the code Syntology harvested for 12 papers, as 5 distinct code bodies found in 12 places (a place is one code body under one paper). At least one of them ran in 12 of the papers; 5 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 masked_var 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; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

Syntology ran 5 of the 5 distinct code bodies named masked_var; 0 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
1ran · our draft was wrong
2ran · fixture could not drive it
2ran
0unverified
5fingerprinted

Licence is a property of each copy, so it is counted per place: 1 of the 12 places is pointer only (Syntology does not serve that copy's text). 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 “fixture could not drive it” 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.

Papers

12 papers shown of 12, newest first; 12 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. 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, Syntology's identity for that exact code: an agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

PaperDateFileStatus SyntologyLicence
Towards Order Fairness: Mitigating LLMs Order Sensitivity through Dual Group Advantage Optimization added by Syntology 2026-05 (from id) Hyalinesky/DGAO/trl/core.py 67607956afbb2a83 ran fingerprinted Apache-2.0 (permissive)
Iterative Prompt Refinement for Safer Text-to-Image Generation added by Syntology 2025-09 (from id) ku-dmlab/IPR/trl/core.py 67607956afbb2a83 ran fingerprinted Apache-2.0 (permissive)
Steering LLM Thinking with Budget Guidance 16 Jun 2025 umass-embodied-agi/budgetguidance/3rdparty/trl/trl/core.py 67607956afbb2a83 ran fingerprinted MIT (permissive)
Lorentz Local Canonicalization: How to Make Any Network Lorentz-Equivariant 26 May 2025 heidelberg-hepml/lloca-experiments/experiments/baselines/pelican/perm_equiv_layers.py e78c5ecf916dd19c ran · our draft was wrong fingerprinted MIT (permissive)
Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen! 21 May 2025 thu-coai/backdoor-data-extraction/train/trl/core.py 67607956afbb2a83 ran fingerprinted MIT (permissive)
How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study 21 May 2025 thu-coai/lrm-safety-study/trl/trl/core.py 67607956afbb2a83 ran fingerprinted MIT (permissive)
DRA-GRPO: Exploring Diversity-Aware Reward Adjustment for R1-Zero-Like Training of Large Language Models 14 May 2025 xiwenc1/dra-grpo/src/open_r1/trl/core.py 67607956afbb2a83 ran fingerprinted MIT (permissive)
Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models 28 Apr 2025 minnesotanlp/mpo/trl/core.py 67607956afbb2a83 ran fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only
ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning 25 Mar 2025 agent-rl/research/src/verl/trainer/ppo/core_algos.py 252438cc046bfb61 ran · fixture could not drive it fingerprinted MIT (permissive)
From Demonstrations to Rewards: Alignment Without Explicit Human Preferences 15 Mar 2025 Hong-Lab-UMN-ECE/IRLAlignment/summarize_from_feedback_details/data_pairing.py 3a136e5f5a8047ac ran fingerprinted MIT (permissive)
Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback 13 Jun 2024 hamishivi/EasyLM/EasyLM/models/llama/llama_train_ppo.py c39dac404ff3f2b3 ran · fixture could not drive it fingerprinted Apache-2.0 (permissive)
The N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR Summarization 24 Mar 2024 vwxyzjn/summarize_from_feedback_details/summarize_from_feedback_details/ppo.py 3a136e5f5a8047ac 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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