Home › Code › extract_step

extract_step

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

extract_step appears in the code Syntology harvested for 22 papers, as 3 distinct code bodies found in 22 places (a place is one code body under one paper). At least one of them ran in 21 of the papers; 2 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 extract_step 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 2 of the 3 distinct code bodies named extract_step; 1 is unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

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

Licence is a property of each copy, so it is counted per place: 7 of the 22 places are 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

22 papers shown of 22, newest first; 22 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 8 papers added by Syntology; 2 papers have no page here and are shown by arXiv id only. 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
How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs added by Syntology 2026-06 (from id) Jiayi-Pan/TinyZero/verl/trainer/fsdp_sft_trainer.py 216e28c040173a61 ran · honoured contract fingerprinted Apache-2.0 (permissive)
SAW: Stage-Aware Dynamic Weighting for Multi-Objective Reinforcement Learning in Large Language Models added by Syntology 2026-06 (from id) Zhaolutuan/SAW/verl/trainer/fsdp_sft_trainer.py 216e28c040173a61 ran · honoured contract fingerprinted Apache-2.0 (permissive)
Beyond Static Pipelines: Learning Dynamic Workflows for Text-to-SQL added by Syntology 2026-02 (from id) Satissss/SquRL/verl/trainer/fsdp_sft_trainer.py 216e28c040173a61 ran · honoured contract fingerprinted Apache-2.0 (permissive)
VimRAG: Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory Graph added by Syntology 2026-02 (from id) Alibaba-NLP/VRAG/VRAG-RL/verl/trainer/fsdp_sft_trainer.py 216e28c040173a61 ran · honoured contract fingerprinted no licence file found · pointer only
Towards On-Policy SFT: Distribution Discriminant Theory and its Applications in LLM Training added by Syntology 12 Feb 2026 zhangmiaosen2000/Towards-On-Policy-SFT/IDFT/verl/trainer/fsdp_sft_trainer.py 216e28c040173a61 ran · honoured contract fingerprinted no licence file found · pointer only
Agent-Omit: Adaptive Context Omission for Efficient LLM Agents added by Syntology 2026-02 (from id) usail-hkust/Agent-Omit/AgentOmit-RL/verl/agent_trainer/fsdp_sft_trainer.py 216e28c040173a61 ran · honoured contract fingerprinted no licence file found · pointer only
GIFT: Reconciling Post-Training Objectives via Finite-Temperature Gibbs Initialization added by Syntology 2026-01 (from id) zzy1127/GIFT/verl/verl/trainer/fsdp_gift_trainer.py 216e28c040173a61 ran · honoured contract fingerprinted no licence file found · pointer only
UME-R1: Exploring Reasoning-Driven Generative Multimodal Embeddings added by Syntology 2025-11 (from id) XMUDeepLIT/UME-R1/src/eval/VLM2Vec/adhoc/gather_score_byckpt_aws.py 981eb19d513b4f7e unverified Apache-2.0 (permissive)
The Hallucination Dilemma: Factuality-Aware Reinforcement Learning for Large Reasoning Models 30 May 2025 identical code first harvested elsewhere 216e28c040173a61 ran · honoured contract fingerprinted licence of this copy not recorded
Behavior Injection: Preparing Language Models for Reinforcement Learning 25 May 2025 czp16/bridge-llm-reasoning/simple_verl/sverl/trainer/fsdp_sft_trainer.py 216e28c040173a61 ran · honoured contract fingerprinted MIT (permissive)
Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards 23 May 2025 identical code first harvested elsewhere 216e28c040173a61 ran · honoured contract fingerprinted licence of this copy not recorded
UFT: Unifying Supervised and Reinforcement Fine-Tuning 22 May 2025 liumy2010/uft/verl/trainer/fsdp_sft_trainer.py 216e28c040173a61 ran · honoured contract fingerprinted Apache-2.0 (permissive)
Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs 19 May 2025 zhyang2226/ar-lopti/verl/trainer/fsdp_sft_trainer.py 216e28c040173a61 ran · honoured contract fingerprinted Apache-2.0 (permissive)
DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization 18 May 2025 optimization-ai/disco/verl/verl/trainer/fsdp_sft_trainer.py 216e28c040173a61 ran · honoured contract fingerprinted MIT (permissive)
ZeroSearch: Incentivize the Search Capability of LLMs without Searching 7 May 2025 alibaba-nlp/zerosearch/verl/trainer/fsdp_sft_trainer.py 216e28c040173a61 ran · honoured contract fingerprinted Apache-2.0 (permissive)
Efficient Reinforcement Finetuning via Adaptive Curriculum Learning 7 Apr 2025 uscnlp-lime/verl/verl/trainer/fsdp_sft_trainer.py 216e28c040173a61 ran · honoured contract fingerprinted Apache-2.0 (permissive)
Do Theory of Mind Benchmarks Need Explicit Human-like Reasoning in Language Models? 2 Apr 2025 bigai-ai/ToM-RL/verl/trainer/fsdp_sft_trainer.py 216e28c040173a61 ran · honoured contract fingerprinted MIT (permissive)
Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning 20 Feb 2025 Unakar/Logic-RL/verl/trainer/fsdp_sft_trainer.py 216e28c040173a61 ran · honoured contract fingerprinted Apache-2.0 (permissive)
Flaming-hot Initiation with Regular Execution Sampling for Large Language Models 28 Oct 2024 yaof20/real/verl/trainer/fsdp_sft_trainer.py 216e28c040173a61 ran · honoured contract fingerprinted Apache-2.0 (permissive)
Efficient Autoregressive Audio Modeling via Next-Scale Prediction 16 Aug 2024 qiuk2/aar/train_AAR_mpi.py d09dbeb0d659afef ran · honoured contract fingerprinted no licence file found · pointer only
arXiv:openreview_QrC8OgQyOI viiika/Prism/Dream/Dream_Prism/src/trainer/fsdp_sft_trainer.py 216e28c040173a61 ran · honoured contract fingerprinted Apache-2.0 (permissive)
arXiv:2025.findings-emnlp.1015 fzp0424/MT-R1-Zero/verl/trainer/fsdp_sft_trainer.py 216e28c040173a61 ran · honoured contract fingerprinted Apache-2.0 (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