Home › Code › format_reward

format_reward

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

format_reward appears in the code Syntology harvested for 35 papers, as 25 distinct code bodies found in 39 places (a place is one code body under one paper). At least one of them ran in 15 of the papers; 4 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 format_reward 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 11 of the 25 distinct code bodies named format_reward; 14 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

6ran · honoured contract
0ran · violated contract
0ran · our draft was wrong
0ran · fixture could not drive it
5ran
14unverified
4fingerprinted

Licence is a property of each copy, so it is counted per place: 18 of the 39 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

35 papers shown of 35, newest first; 39 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 19 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
SPEAR: Distilling Domain-Adaptive Reasoning Skeletons via Sequential Symbolic Alignment in Reinforcement Learning added by Syntology 2026-08 (from id) zhuochunli/SPEAR/reward.py 3f97780f21c0b793 unverified no licence file found · pointer only
MAVEN: A Macro-Societal Value Evaluation Framework of Multimodal Content with Compact Aligned Evaluators added by Syntology 2026-08 (from id) zzzzzzzzjj/MAVEN/src/train/reward_funcs.py cb8ca9226da3a936 ran Apache-2.0 (permissive)
PowerAtlas: Towards Electricity-Computing Co-Scheduling for Power Systems added by Syntology 2026-07 (from id) JAVA-Jiang/PowerAtlas/poweratlas/reward.py df8361c06df60d8e ran · honoured contract licence not identified · pointer only
Zero-source LLM Hallucination Detection with Human-like Criteria Probing added by Syntology 2026-06 (from id) TRISKEL10N/HCPD/src/open_r1/rewards.py ce353d566f3f2c9f ran Apache-2.0 (permissive)
VideoSEG-O3: A Multi-turn Reinforcement Learning Framework for Reasoning Video Object Segmentation added by Syntology 2026-06 (from id) Dmmm1997/VideoSEG-O3/projects/open_r1/rewards.py 09e6ed2ece2264f7 ran Apache-2.0 (permissive)
Evolutionary Task Discovery: Advancing Reasoning Frontiers via Skill Composition and Complexity Scaling added by Syntology 2026-05 (from id) liqinye/EvoTD/src/reward_function.py d67cad27811abe22 unverified MIT (permissive)
Strategy-Aware Optimization Modeling with Reasoning LLMs added by Syntology 2026-05 (from id) rachhhhing/SAGE/reward_func/batch_score.py c15d4169879b293c ran fingerprinted no licence file found · pointer only
Strategy-Aware Optimization Modeling with Reasoning LLMs added by Syntology 2026-05 (from id) rachhhhing/SAGE/reward_func/batch_score_no_tem.py ef9fa7347607c290 ran fingerprinted no licence file found · pointer only
OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization added by Syntology 2026-02 (from id) MIT-MI/human_behavior_atlas/training/rl/reward_function/human_behaviour.py fd2112df3f149ab0 unverified no licence file found · pointer only
OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization added by Syntology 2026-02 (from id) MIT-MI/human_behavior_atlas/training/rl/reward_function/human_behaviour_harpo.py b55511b458d41522 unverified no licence file found · pointer only
GOPO: Policy Optimization using Ranked Rewards added by Syntology 2026-02 (from id) friendshipkim/gopo/src/open_r1/rewards.py ce353d566f3f2c9f ran Apache-2.0 (permissive)
Alignment-Aware Model Adaptation via Feedback-Guided Optimization added by Syntology 2026-02 (from id) facebookresearch/TruthRL/training/open-r1/src/open_r1/rewards.py ce353d566f3f2c9f ran no licence file found · pointer only
2 RELATED WORK Reinforcement learning has emerged as a powerful paradigm for enhancing the reasoning abilities of LLMs added by Syntology 2026-01 (from id) zywang0104/Video-KTR/src/r1-v/src/open_r1/grpo.py 26720b6f9ee7eba4 unverified no licence file found · pointer only
RPO:Reinforcement Fine-Tuning with Partial Reasoning Optimization added by Syntology 2026-01 (from id) yhz5613813/RPO/src/open_r1/rewards.py 0a5c0b6fb53cd48c unverified MIT (permissive)
Weather-R1: Logically Consistent Reinforcement Fine-Tuning for Multimodal Reasoning in Meteorology added by Syntology 2026-01 (from id) Marcowky/Weather-R1/src/weather_r1/weather_r1_reward.py 12486ec2a6bdbe17 ran · honoured contract fingerprinted MPL-2.0 (copyleft) · pointer only
RelayLLM: Efficient Reasoning via Collaborative Decoding added by Syntology 2026-01 (from id) Chengsong-Huang/RelayLLM/RL_stage/data_filter.py e8ef1d6648c2b294 unverified no licence file found · pointer only
GRACE: Reinforcement Learning for Grounded Response and Abstention under Contextual Evidence added by Syntology 2026-01 (from id) YiboZhao624/Grace/src/custom_reward_v2.py ca32d84f17d98414 ran · honoured contract fingerprinted no licence file found · pointer only
Vision-Language Reasoning for Geolocalization: A Reinforcement Learning Approach added by Syntology 2026-01 (from id) aialt/geo-r/src/open-r1-multimodal/src/open_r1/grpo.py e89f2eec0a18d4c2 unverified Apache-2.0 (permissive)
You Need Reasoning to Learn Reasoning: The Limitations of Label-Free RL in Weak Base Models added by Syntology 2025-11 (from id) BorealisAI/CuMa/src/open_r1/rewards.py ce353d566f3f2c9f ran no licence file found · pointer only
EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT added by Syntology 2025-10 (from id) InternRobotics/EgoThinker/EgoThinker-RFT/src/open_r1/grpo.py 26720b6f9ee7eba4 unverified no licence file found · pointer only
EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT added by Syntology 2025-10 (from id) InternRobotics/EgoThinker/EgoThinker-RFT/src/open_r1/grpo_video.py 06eb76b246b185f7 unverified no licence file found · pointer only
Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and Filtering added by Syntology 2025-10 (from id) om-ai-lab/VLM-R1/src/open-r1-multimodal/src/open_r1/grpo.py e89f2eec0a18d4c2 unverified Apache-2.0 (permissive)
GTA1: GUI Test-time Scaling Agent 8 Jul 2025 yan98/gta1/src/grpo_grounding.py b6cc386477eb6792 ran · honoured contract no licence file found · pointer only
arXiv:2507.02834 2025-07 (from id) huggingface/open-r1/src/open_r1/rewards.py ce353d566f3f2c9f ran Apache-2.0 (permissive)
arXiv:2507.02834 2025-07 (from id) dhcode-cpp/X-R1/src/x_r1/benchmark.py 2627a2d9d4808062 unverified Apache-2.0 (permissive)
DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation 25 Jun 2025 apple/ml-diffucoder/src/open_r1/rewards.py ce353d566f3f2c9f ran no licence file found · pointer only
GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents 21 May 2025 yuqi-zhou/gui-g1/src/open-r1-multimodal/src/open_r1/grpo.py e89f2eec0a18d4c2 unverified Apache-2.0 (permissive)
VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank 20 May 2025 tianhewu/visualquality-r1/src/open-r1-multimodal/src/open_r1/grpo.py e89f2eec0a18d4c2 unverified Apache-2.0 (permissive)
VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning 18 May 2025 qiwang98/videorft/src/r1-v/src/open_r1/grpo.py 26720b6f9ee7eba4 unverified Apache-2.0 (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/rewards.py 0a5c0b6fb53cd48c unverified MIT (permissive)
Tina: Tiny Reasoning Models via LoRA 22 Apr 2025 shangshang-wang/tina/tina/post_train_hf/rewards.py 0a5c0b6fb53cd48c unverified Apache-2.0 (permissive)
SpaceR: Reinforcing MLLMs in Video Spatial Reasoning 2 Apr 2025 ouyangkun10/spacer/SpaceR-SG-RLVR/src/r1-v/src/open_r1/SG-RLVR.py f23cbd84b69ec52c ran · honoured contract licence not identified · pointer only
Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1 31 Mar 2025 tencentarc/seed-bench-r1/src/open_r1_egoplan/grpo.py 1fd4dec0e26848af unverified Apache-2.0 (permissive)
Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't 20 Mar 2025 knoveleng/open-rs/src/open_r1/rewards.py 0a5c0b6fb53cd48c unverified MIT (permissive)
TimeZero: Temporal Video Grounding with Reasoning-Guided LVLM 17 Mar 2025 www-ye/timezero/src/open_r1/grpo.py 26720b6f9ee7eba4 unverified Apache-2.0 (permissive)
Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering 14 Mar 2025 xiaomi-research/r1-aqa/src/utils/rewards.py 54511e51a854f064 unverified Apache-2.0 (permissive)
MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark 4 Sep 2024 opendatalab/pm4bench/src/pm4bench/qgo/reward.py c17d2901ecfbf4cb unverified Apache-2.0 (permissive)
Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Backbone Generation 30 May 2024 ding523/Curr_REFT/train_code/grpo/open-r1-multimodal/src/open_r1/Stage1_judge_math_resize.py baace3dc73e1da05 ran · honoured contract no licence file found · pointer only
arXiv:2025.emnlp-main.67 isyuhaochen/RRC-DSCD/code/rl/rewards.py 70ba7655c5039f8f unverified 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