Home › Code › compute_score

compute_score

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

compute_score appears in the code Syntology harvested for 49 papers, as 48 distinct code bodies found in 51 places (a place is one code body under one paper). At least one of them ran in 19 of the papers; 6 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 compute_score 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 19 of the 48 distinct code bodies named compute_score; 29 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

5ran · honoured contract
1ran · violated contract
6ran · our draft was wrong
0ran · fixture could not drive it
7ran
29unverified
6fingerprinted

Licence is a property of each copy, so it is counted per place: 26 of the 51 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

49 papers shown of 49, newest first; 51 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 25 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
RePolicy: Reinforcement Learning for Safety-Policy Invocation in Agent Safeguards REPOLICY: REINFORCEMENT LEARNING FOR SAFETY-POLICY INVOCATION IN AGENT SAFEGUARDS added by Syntology 2026-08 (from id) jianghoucheng/RePolicy/repolicy/reward.py f25814da449d7149 ran · our draft was wrong Apache-2.0 (permissive)
Handoff-H1: An Orchestrated Vision-Agent System for Material Quantity Takeoff from Construction Blueprints added by Syntology 2026-08 (from id) handoffai/residential-takeoff-benchmark/harbor/shared/scoring.py da2272374059a198 ran fingerprinted no licence file found · pointer only
ReFact: Adaptive Fact Restatement for Compact and Faithful Chain-of-Thought Reasoning added by Syntology 2026-07 (from id) NEUIR/REFACT/verl/verl/utils/reward_score/evdience_reward.py 3cd1dee651cfd765 ran · our draft was wrong MIT (permissive)
SCOPE-RL: Optimizing Reasoning Paths Before and After Success added by Syntology 2026-07 (from id) tokencraft-lab/SCOPE-RL/verl/recipe/scope_rl/reward_score/step_quality.py c596f8725f0cb8db unverified no licence file found · pointer only
Reward Modeling for Multi-Agent Orchestration added by Syntology 2026-06 (from id) Wang-ML-Lab/OrchRM/grpo/reward_function.py cca4d862eeb56fc8 unverified licence not identified · pointer only
Flexible Kernels for Protein Property Prediction added by Syntology 2026-06 (from id) luo-group/ConFit/confit/stat_utils.py 971af63fa165cef5 ran BSD-3-Clause (permissive)
SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning added by Syntology 2026-06 (from id) wlc2424762917/SafeMCP/verl_SafeMCP/verl/utils/reward_score/rlguard_safety_tools_todo_with_state.py 7b46fbfee5aaaed2 ran · our draft was wrong no licence file found · pointer only
Benchmarking LLM Agents on Financial Spreadsheets added by Syntology 2026-05 (from id) Longitude-Labs/bluefin/scoring/score.py d26c82c2360c51c7 ran licence not identified · pointer only
RLVR Datasets and Where to Find Them: Tracing Data Lineage for Better Training Data added by Syntology 2026-05 (from id) Celine-hxy/ATLAS/verl/verl/utils/reward_score/math_dapo.py 1dff957fd0164bac unverified no licence file found · pointer only
Efficient Agentic Reinforcement Learning with On-Policy Intrinsic Knowledge Boundary Enhancement added by Syntology 2026-05 (from id) CuSO4-Chen/AKBE/AKBE/verl_akbe/verl/utils/reward_score/reward_em_betagrpo.py 463c4ebb5ff2bcda unverified no licence file found · pointer only
Prosa: Rubric-Based Evaluation of LLMs on Real User Chats in Brazilian Portuguese added by Syntology 2026-05 (from id) maritaca-ai/Prosa/Prosa-benchmark/prosa/gen_score.py a258f3188fb6b6e9 ran · our draft was wrong fingerprinted no licence file found · pointer only
Discourse Diversity in Multi-Turn Empathic Dialogue added by Syntology 2026-04 (from id) honglizhan/mint-empathy/training/reward_verl.py 4e518f9c54f9f6ce unverified MIT (permissive)
Multi-Agent Debate with Memory Masking added by Syntology 2026-03 (from id) tmlr-group/MAD-MM/src/qwen_math.py 69c0f52e607086d3 unverified 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/utils/reward_score/omanic.py c61fba77fe67c4d0 unverified no licence file found · pointer only
Good Reasoning Makes Good Demonstrations: Implicit Reasoning Quality Supervision via In-Context Reinforcement Learning added by Syntology 2026-03 (from id) Mithas-114/IC-DAPO/verl/verl/utils/reward_score/math_dapo.py ad74ab2d82242089 unverified no licence file found · pointer only
CRISP: Compressed Reasoning via Iterative Self-Policy Distillation added by Syntology 2026-03 (from id) HJSang/OPSD_Reasoning_Compression/workspace/src/rewards/dual_path_math_verify.py 7adde3eb14aef96d unverified no licence file found · pointer only
When Domains Interact: Asymmetric and Order-Sensitive Cross-Domain Effects in Reinforcement Learning for Reasoning added by Syntology 2026-02 (from id) uservan/cross_domain/verify/score/gsm8k.py 5aefbfebf64faf9c unverified no licence file found · pointer only
When Domains Interact: Asymmetric and Order-Sensitive Cross-Domain Effects in Reinforcement Learning for Reasoning added by Syntology 2026-02 (from id) uservan/cross_domain/verify/score/puzzle.py 39c5fae4c67fd407 unverified no licence file found · pointer only
UCPO: Uncertainty-Aware Policy Optimization added by Syntology 2026-01 (from id) xzhouzeng/ucpo/train/recipe/ucpo/reward_fn/uc_reward_mc.py 57cabc812db1e524 unverified Apache-2.0 (permissive)
ETS: Energy-Guided Test-Time Scaling for Training-Free RL Alignment added by Syntology 2026-01 (from id) sheriyuo/ETS/llada/gsm8k.py 71625e4c2bfdcce7 unverified no licence file found · pointer only
Evaluating Morphological Plausibility of Subword Tokenization via Statistical Alignment with Morpho-Syntactic Features added by Syntology 2026-01 (from id) abishekjs/morph-tok-eval/align.py cb593aacaf0e736c ran · our draft was wrong no licence file found · pointer only
Mixing Expert Knowledge: Bring Human Thoughts Back To the Game of Go added by Syntology 2026-01 (from id) Entarochuan/LoGos/RL_utils/Go_reward.py 6026905b22ef8498 ran · honoured contract Apache-2.0 (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 c0adbd229f4b0ecb unverified MPL-2.0 (copyleft) · pointer only
TokenSqueeze: Performance-Preserving Compression for Reasoning LLMs added by Syntology 2025-11 (from id) zhangyx1122/TokenSqueeze/utils/math500_verify.py 054091f2e78d9eec unverified no licence file found · pointer only
SSL4RL: Revisiting Self-supervised Learning as Intrinsic Reward for Visual-Language Reasoning added by Syntology 2025-10 (from id) PKU-ML/SSL4RL/verl/utils/reward_score/ssl4rl.py 34c07eb4926bcb61 ran · honoured contract fingerprinted Apache-2.0 (permissive)
ReSeek: A Self-Correcting Framework for Search Agents with Instructive Rewards added by Syntology 2025-10 (from id) TencentBAC/ReSeek/verl/utils/reward_score/reseek_regex.py abc22ec3df477b0b ran · honoured contract no licence file found · pointer only
rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset 27 May 2025 microsoft/rstar/fused_compute_score/math_verify.py 6b72c80feeab1463 unverified MIT (permissive)
TinyV: Reducing False Negatives in Verification Improves RL for LLM Reasoning 20 May 2025 uw-nsl/tinyv/analysis_tool/verl_reward_score/math.py 054091f2e78d9eec unverified MIT (permissive)
TinyV: Reducing False Negatives in Verification Improves RL for LLM Reasoning 20 May 2025 uw-nsl/tinyv/analysis_tool/verl_reward_score/math_verify.py e3290e962238260a unverified MIT (permissive)
Optimizing Model Selection for Compound AI Systems 20 Feb 2025 LLMSELECTOR/LLMSELECTOR/llmselector/llmselector/compoundai/metric.py 075a2a4962fab858 unverified Apache-2.0 (permissive)
DISCERN: Decoding Systematic Errors in Natural Language for Text Classifiers 29 Oct 2024 rrmenon10/DISCERN/src/discern/refine.py 587e2ba5154f85b0 ran no licence file found · pointer only
PostMark: A Robust Blackbox Watermark for Large Language Models 20 Jun 2024 lilakk/PostMark/parse_human_annots.py c52efc764d0b2940 ran no licence file found · pointer only
RET-CLIP: A Retinal Image Foundation Model Pre-trained with Clinical Diagnostic Reports 23 May 2024 sstonemason/ret-clip/RET_CLIP/eval/evaluation.py 35eab6e5efe6dd4c ran · honoured contract no licence file found · pointer only
On Large Language Models' Hallucination with Regard to Known Facts 29 Mar 2024 dcdsf321/known_fact_hallucination/get_model_output_example_opt.py 6f8caf5f9c40198a ran · honoured contract fingerprinted MIT (permissive)
Generating Diverse and High-Quality Texts by Minimum Bayes Risk Decoding 10 Jan 2024 CyberAgentAILab/diverse-mbr/mbr/mbr_engine.py c0f020db5ebab266 ran MIT (permissive)
Evaluation Metrics in the Era of GPT-4: Reliably Evaluating Large Language Models on Sequence to Sequence Tasks 20 Oct 2023 protagolabs/seq2seq_llm_evaluation/main/automatic_evaluation/eval_errant_GEC.py 9037aa0c9007025d unverified MIT (permissive)
Post-hoc Bias Scoring Is Optimal For Fair Classification 9 Oct 2023 chenw20/biasscore/postprocess_dp.py d3b2da90b6341d9e ran · violated contract fingerprinted no licence file found · pointer only
FIRE: Food Image to REcipe generation 28 Aug 2023 prateekchhikara/fire/ingredients/sample.py 6a8674a68a7db5d5 ran no licence file found · pointer only
Universal and Transferable Adversarial Attacks on Aligned Language Models 27 Jul 2023 amanb2000/magic_words/magic_words/easy_gcg.py 13866ab049e2380b unverified MIT (permissive)
SwinGNN: Rethinking Permutation Invariance in Diffusion Models for Graph Generation 4 Jul 2023 qiyan98/swingnn/runner/sanity_check_helper.py 632d673f64dd5dcc unverified MIT (permissive)
Have LLMs Advanced Enough? A Challenging Problem Solving Benchmark For Large Language Models 24 May 2023 dair-iitd/jeebench/compute_metrics.py 771eaaca6b976e72 unverified MIT (permissive)
Discffusion: Discriminative Diffusion Models as Few-shot Vision and Language Learners 18 May 2023 eric-ai-lab/dsd/utils/losses.py 5bc35c622beca1cc unverified MIT (permissive)
Training Verifiers to Solve Math Word Problems 27 Oct 2021 volcengine/verl/verl/utils/reward_score/math_verify.py 20d6b98a03e76b63 unverified Apache-2.0 (permissive)
Towards Automatic Instrumentation by Learning to Separate Parts in Symbolic Multitrack Music 13 Jul 2021 salu133445/arranger/arranger/common/learn.py d8ee12ccc51e2e70 unverified MIT (permissive)
Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision 2 Jun 2021 harshm121/m3l/src/semi_supervised/cps.py 203e73feddb57884 ran · our draft was wrong fingerprinted no licence file found · pointer only
Malleable 2.5D Convolution: Learning Receptive Fields along the Depth-axis for RGB-D Scene Parsing 18 Jul 2020 David-zaiwang/114_rgbd_seg/furnace/seg_opr/metric.py 3e98ad928a86de29 unverified MIT (permissive)
Neural Pose Transfer by Spatially Adaptive Instance Normalization 16 Mar 2020 jiashunwang/Neural-Pose-Transfer/utils.py 32c50564ead0340c unverified Apache-2.0 (permissive)
Learnable Tree Filter for Structure-preserving Feature Transform 27 Sep 2019 StevenGrove/TreeFilter-Torch/furnace/seg_opr/metric.py 3e98ad928a86de29 unverified MIT (permissive)
QATM: Quality-Aware Template Matching For Deep Learning 18 Mar 2019 kamata1729/QATM_pytorch/utils.py aa24506cff049185 unverified MIT (permissive)
Exascale Deep Learning for Climate Analytics 2018-10 (from id) azrael417/mlperf-deepcam/src/deepCam/utils/utils.py c675309ea1a523a2 unverified MIT recorded; this copy not marked cleared · pointer only
BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation 2 Aug 2018 akinoriosamura/TorchSeg-mirror/furnace/seg_opr/metric.py 3e98ad928a86de29 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