Home › Code › get_dynamic_pipeline_shards

get_dynamic_pipeline_shards

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

get_dynamic_pipeline_shards appears in the code Syntology harvested for 53 papers, as 1 distinct code body found in 53 places (a place is one code body under one paper). At least one of them ran in 53 of the papers; 1 of the code bodies carries 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 get_dynamic_pipeline_shards 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 1 of the 1 distinct code body named get_dynamic_pipeline_shards; 0 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

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

Licence is a property of each copy, so it is counted per place: 19 of the 53 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

53 papers shown of 53, newest first; 53 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 50 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
Learn from Whoever Is Right: Answer-Verified Multi-Teacher Distillation for Multi-Domain LLMs added by Syntology 2026-09 (from id) hexixiang/MT-SDPO/training/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted Apache-2.0 (permissive)
Explore More, Drift Less: Outcome-Only Reinforcement Learning Can Suffice for Long-Horizon Interactive Agents added by Syntology 2026-09 (from id) AlibabaResearch/SignalCoverageRL/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted Apache-2.0 (permissive)
On-policy Distillation with Verifiable Reward added by Syntology 2026-08 (from id) LeapLabTHU/OPDVR/verl/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted no licence file found · pointer only
FARCA: Fact-Aligned Reliability-Aware Credit Assignment for Reinforcement Learning with Factual Supervision added by Syntology 2026-08 (from id) verl-project/verl/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted Apache-2.0 (permissive)
Best Practice Critic Optimization BEST PRACTICE CRITIC OPTIMIZATION added by Syntology 2026-08 (from id) QPHutu/golden_critic/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted Apache-2.0 (permissive)
Beyond Teacher Likelihood: Group-Calibrated On-Policy Distillation for Long-Context Reasoning added by Syntology 2026-08 (from id) SolereZhang/GC-OPD/verl/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted Apache-2.0 (permissive)
TAIL-AWARE TOP-k ON-POLICY DISTILLATION added by Syntology 2026-08 (from id) HuipengHuang/TA-OPD/verl/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted no licence file found · pointer only
Self-Improving Large Language Models via Progressive Experience Evolution added by Syntology 2026-08 (from id) rrrsj/SPEE/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted Apache-2.0 (permissive)
From Trajectories to Prefixes: Reusing Teacher Trajectories via Replayed Prefixes and Online Continuation added by Syntology 2026-07 (from id) HappynessI/Prefix_GRPO/verl/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted Apache-2.0 (permissive)
ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples added by Syntology 2026-07 (from id) Hesse73/ARMOR/verl/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted no licence file found · pointer only
When Implausible Tokens Get Reinforced: Tail-Aware Credit Calibration for LLM Reinforcement Learning added by Syntology 2026-07 (from id) xiuyilou/TACO/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted no licence file found · pointer only
DENSER ̸ = BETTER: LIMITS OF ON-POLICY SELF-DISTILLATION FOR CONTINUAL POST-TRAINING added by Syntology 2026-07 (from id) Moenupa/SDPO-CL/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted Apache-2.0 (permissive)
VIMPO: Value-Implicit Policy Optimization for LLMs added by Syntology 2026-06 (from id) backprop07/VIMPO/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted Apache-2.0 (permissive)
EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts added by Syntology 2026-06 (from id) furiosa-ai/EfficientRollout/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted Apache-2.0 (permissive)
INFUSER: Influence-Guided Self-Evolution Improves Reasoning added by Syntology 2026-06 (from id) FFishy-git/INFUSER/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted MIT (permissive)
Self-Distilled Policy Gradient added by Syntology 2026-06 (from id) lauyikfung/SDPG/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted Apache-2.0 (permissive)
Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation added by Syntology 2026-06 (from id) YuYingLi0/FiRe-OPD/verl/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted no licence file found · pointer only
SPADER: Step-wise Peer Advantage with Diversity-Aware Exploration Rewards for Multi-Answer Question Answering added by Syntology 2026-06 (from id) KhanCold/spader/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted Apache-2.0 (permissive)
ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains added by Syntology 2026-05 (from id) ZiqiZhao1/ROSD/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted Apache-2.0 (permissive)
MERIT: Matching Expertise via Rubric-Informed Training for Reviewer Assignment added by Syntology 2026-05 (from id) Luli3220/MERIT/MERIT-Assessor/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted no licence file found · pointer only
Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning added by Syntology 2026-05 (from id) AlexFanw/LegalSearch-R1/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted Apache-2.0 (permissive)
Hide to Guide: Learning via Semantic Masking added by Syntology 2026-05 (from id) mit-han-lab/SMEPO/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted no licence file found · pointer only
Ranking-Aware Calibration for Reliable Multimodal Reinforcement Learning added by Syntology 2026-05 (from id) Stellaris167/RAC/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted Apache-2.0 (permissive)
Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation added by Syntology 2026-05 (from id) caiyuchen-ustc/EffOPD/EffOPD/verl/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted no licence file found · pointer only
Rethinking Importance Sampling in LLM Policy Optimization: A Cumulative Token Perspective added by Syntology 2026-05 (from id) horizon-llm/CTPO/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted Apache-2.0 (permissive)
When Less is Enough: Efficient Inference via Collaborative Reasoning added by Syntology 2026-05 (from id) fairytale9/llm_bottleneck/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted Apache-2.0 (permissive)
One Refiner to Unlock Them All: Inference-Time Reasoning Elicitation via Reinforcement Query Refinement added by Syntology 2026-04 (from id) newera-xiao/ReQueR/verl/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted Apache-2.0 (permissive)
Learning to Hint for Reinforcement Learning added by Syntology 2026-04 (from id) Andree-9/HiLL/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted no licence file found · pointer only
Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs? added by Syntology 2026-03 (from id) lasgroup/SDPO/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted Apache-2.0 (permissive)
TIPS: Turn-Level Information-Potential Reward Shaping for Search-Augmented LLMs added by Syntology 2026-03 (from id) ucsd-wang-lab-lm/tips/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted no licence file found · pointer only
Experience is the Best Teacher: Motivating Effective Exploration in Reinforcement Learning for LLMs added by Syntology 2026-03 (from id) sikelifei/HeRL/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted no licence file found · pointer only
Omanic: Towards Step-wise Evaluation of Multi-hop Reasoning in Large Language Models added by Syntology 2026-03 (from id) XiaojieGu/Omanic/verl/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted no licence file found · pointer only
On Information Self-Locking in Reinforcement Learning for Active Reasoning of LLM agents added by Syntology 2026-03 (from id) unimpor/T3/verl/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted no licence file found · pointer only
CLIPO: Contrastive Learning in Policy Optimization Generalizes RLVR added by Syntology 2026-03 (from id) Qwen-Applications/CLIPO/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted no licence file found · pointer only
Entropy-Aware On-Policy Distillation of Language Models added by Syntology 2026-03 (from id) WLS04/EOPD/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted Apache-2.0 (permissive)
MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning added by Syntology 2026-02 (from id) FlyTune/MASPO-RL/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted Apache-2.0 (permissive)
Online Causal Kalman Filtering for Stable and Effective Policy Optimization added by Syntology 2026-02 (from id) shuohe1995/verl-kpo/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted Apache-2.0 (permissive)
Uncovering Cross-Objective Interference in Multi-Objective Alignment added by Syntology 2026-02 (from id) yining610/ctwa/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted Apache-2.0 (permissive)
Stop Rewarding Hallucinated Steps: Faithfulness-Aware Step-Level Reinforcement Learning for Small Reasoning Models added by Syntology 2026-02 (from id) Easy195/FaithRL/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted no licence file found · pointer only
Rethinking the Trust Region in LLM Reinforcement Learning added by Syntology 2026-02 (from id) sail-sg/Stable-RL/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted Apache-2.0 (permissive)
PrAg-PO: Prompt Augmented Policy Optimization for Robust and Diverse Mathematical Reasoning added by Syntology 2026-02 (from id) wenquanlu/PrAg-PO/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted no licence file found · pointer only
Self-Hinting Language Models Enhance Reinforcement Learning added by Syntology 2026-02 (from id) BaohaoLiao/SAGE/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted Apache-2.0 (permissive)
CoBA-RL: Capability-Oriented Budget Allocation for Reinforcement Learning in LLMs added by Syntology 2026-02 (from id) Within-yao/CoBA-RL/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted no licence file found · pointer only
GRAPHDANCER: Training LLMs to Explore and Reason over Graphs via Two-Stage Curriculum Post-Training added by Syntology 2026-02 (from id) leopoldwhite/GraphDancer/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted no licence file found · pointer only
Agentic reinforcement learning empowers next-generation chemical language models for molecular design and synthesis added by Syntology 2026-01 (from id) HowardLi1984/ChemCraft/chemcraft_rl/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted no licence file found · pointer only
Enabling Stroke-Level Structural Analysis of Hieroglyphic Scripts without Language-Specific Priors added by Syntology 2026-01 (from id) THUNLP-MT/HieroSA/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted MIT (permissive)
Linear Dynamics in the RLVR Training of Large Language Models added by Syntology 2026-01 (from id) Miaow-Lab/RLVR-Linearity/verl/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted MIT (permissive)
Prioritized Replay for RL Post-training added by Syntology 2026-01 (from id) fatemi/verl/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted Apache-2.0 (permissive)
ExPO-HM: Learning to Explain-then-Detect for Hateful Meme Detection added by Syntology 2025-10 (from id) JingbiaoMei/ExPO-HM/verl/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted Apache-2.0 (permissive)
Self-Evolving Vision-Language Models for Image Quality Assessment via Voting and Ranking added by Syntology 2025-09 (from id) bytedance/EvoQuality/verl/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted Apache-2.0 (permissive)
Guided Stream of Search: Learning to Better Search with Language Models via Optimal Path Guidance 3 Oct 2024 snu-mllab/guided-rest/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted Apache-2.0 (permissive)
arXiv:openreview_v70fTOqer2 liziniu/KnapsackRL/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran fingerprinted Apache-2.0 (permissive)
arXiv:openreview_VZDlkXuIQc ShadeCloak/IP-GRM/verl/verl/model_merger/megatron_model_merger.py 94209884dcb2308e ran 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