Home › Code › normalize_answer

normalize_answer

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

normalize_answer appears in the code Syntology harvested for 304 papers, as 113 distinct code bodies found in 323 places (a place is one code body under one paper). At least one of them ran in 250 of the papers; 63 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 normalize_answer 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 64 of the 113 distinct code bodies named normalize_answer; 49 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
26ran · our draft was wrong
0ran · fixture could not drive it
38ran
49unverified
63fingerprinted

Licence is a property of each copy, so it is counted per place: 131 of the 323 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

100 papers shown of 304 (newest first; the JSON twin carries all 323 places); 104 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 64 papers added by Syntology; 19 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
Chopthin-Consensus Power Sampling: A Diversity-Preserving Approach to LLM Decoding added by Syntology 2026-09 (from id) MinooAhmadii/chopthin-consensus-power-sampling/ccps/graders/math_normalize.py d51cc295307937e6 unverified licence not identified · pointer only
S$^2$Prune: Spatially Structured Visual Token Pruning for Multimodal Large Language Models added by Syntology 2026-09 (from id) yuanyuanjia71-spec/S2Prune/s2prune/vizwiz_eval.py 3bea898e987fab1e unverified no licence file found · pointer only
ISO-RAG: Isoperimetric Noise Control for Retrieval-Augmented Generation added by Syntology 2026-09 (from id) ZaiizaiZHANG/ISO-RAG/analyze_predictions.py 0d2dc85735d18403 unverified no licence file found · pointer only
ISO-RAG: Isoperimetric Noise Control for Retrieval-Augmented Generation added by Syntology 2026-09 (from id) ZaiizaiZHANG/ISO-RAG/analyze_retrieval_qa_transfer.py 1691191d75c4338c unverified no licence file found · pointer only
Adaptive Memory and Reflection Multi-Agent System for Medical Question Answering added by Syntology 2026-08 (from id) mm-air/AMR-Agent/evaluate.py 9fc3dafdabb9a23a ran fingerprinted MIT (permissive)
EviReform: Evidence-Guided Query Reformulation for Multi-Hop Graph Retrieval added by Syntology 2026-08 (from id) XrazyMee/EviReform/src/evireform/metrics.py 77114e88a1e17b9b ran fingerprinted Apache-2.0 (permissive)
The Embedder's Dilemma: LLMs Are Better, but at What Cost? added by Syntology 2026-08 (from id) embeddings-benchmark/embedders-dilemma/llm_judge/evaluators/llm_rag_evaluator.py 97012cf96aa79266 ran fingerprinted Apache-2.0 (permissive)
OpenVisTool: An Open Recipe for Synthesizing Instructive Visual Tool-Use Trajectories added by Syntology 2026-08 (from id) Changhao-Xiang/OpenVisTool/distill/filter/evaluate_answer_rule.py 24e4999eff337610 ran fingerprinted MIT (permissive)
Prompt Embedding Probes (PEP): Hallucination Detection in LLMs from Hidden States added by Syntology 2026-08 (from id) zazamrykh/internal_probing/src/dataset/squad_eval.py 6a96435eba311b08 ran · our draft was wrong fingerprinted MIT (permissive)
The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale added by Syntology 2026-08 (from id) MBZUAI-CLeaR/IoE-Prompting/run_Hotpot_IoE.py b1a674018a8b1ccf ran · our draft was wrong fingerprinted no licence file found · pointer only
The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale added by Syntology 2026-08 (from id) MBZUAI-CLeaR/IoE-Prompting/run_math_IoE.py 5d6dae5b935c9916 ran fingerprinted no licence file found · pointer only
When Correct Solutions Repeat: Rarity-Aware Credit Redistribution for GRPO added by Syntology 2026-08 (from id) CzZ12/When-Correct-Solutions-Repeat-Rarity-Aware-Credit-Redistribution-for-GRPO/domain_config.py 6151d15713a7392f ran fingerprinted MIT (permissive)
CoEvoKG: Co-Evolving Knowledge Graphs with Self-Evolving Search Agents added by Syntology 2026-08 (from id) lazzy1225/CoEvoKG/coevokg/reward/score/coevokg_score.py dae7ab386661a4f4 ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
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 445de90902805074 ran · our draft was wrong fingerprinted MIT (permissive)
RIMS: Preference Optimization via Smoothed Multi-pair Aggregation for Small-Scale LLM Retrieval-Augmented Generation added by Syntology 2026-07 (from id) tptrix29/RIMS/baseline/baseline_instructrag.py dae7ab386661a4f4 ran · our draft was wrong fingerprinted MIT (permissive)
TrustMargin: Training-Free Arbitration between Parametric Memory and Retrieved Evidence in Large Language Models added by Syntology 2026-06 (from id) mojixu/TrustMargin/src/trustmargin.py 3dc410d21f1c3741 ran · our draft was wrong fingerprinted no licence file found · pointer only
Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents added by Syntology 2026-06 (from id) Ji-shuo/MRAgent/eval/evaluation.py e096279b3e0d7bd9 ran fingerprinted no licence file found · pointer only
VAMPS: Visual-Assisted Mathematical Problem Solving Benchmark added by Syntology 2026-06 (from id) vampsbenchmark/VAMPS/extract_answers.py 5c64b982057e8460 ran fingerprinted MIT (permissive)
Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling added by Syntology 2026-06 (from id) kaist-cvml/perception-judge/prepare-datasets/utils.py 2b85173eac27fd50 ran fingerprinted no licence file found · pointer only
OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources added by Syntology 2026-05 (from id) JinheonBaek/OmniRetrieval/src/evaluation/metrics.py 6a96435eba311b08 ran · our draft was wrong fingerprinted MIT (permissive)
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 6fcc2c2f4fe3ad67 ran · our draft was wrong fingerprinted no licence file found · pointer only
The Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT Truncation added by Syntology 2026-05 (from id) Yifan-Lan/zero-cot-probe/math_normalize.py 644c1663d2f9533f unverified MIT (permissive)
ChunkFT: Byte-Streamed Optimization for Memory-Efficient Full Fine-Tuning added by Syntology 2026-05 (from id) misonsky/chunk/metrics/cuad/compute_score.py e7e75981cb464788 ran · our draft was wrong fingerprinted no licence file found · pointer only
MINTEVAL: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems added by Syntology 2026-05 (from id) amy-hyunji/MINTEval/src/mem_alpha/memalpha/llm_agent/metrics.py 3b3fe5d04eaa0d33 ran · our draft was wrong fingerprinted no licence file found · pointer only
Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration added by Syntology 2026-05 (from id) PKU-SEC-Lab/SPEX/evaluate/evaluate_utils/math_normalize.py 101b1e54fcdadf90 ran fingerprinted no licence file found · pointer only
RSAT: Structured Attribution Makes Small Language Models Faithful Table Reasoners added by Syntology 2026-05 (from id) JugalGajjar/RSAT/src/rewards/answer_reward.py ee8c43ee40891b07 ran fingerprinted MIT (permissive)
GraphPlanner: Graph Memory-Augmented Agentic Routing for Multi-Agent LLMs added by Syntology 2026-04 (from id) ulab-uiuc/GraphPlanner/router_planner/shared/utils.py c2e95e64eec380a8 ran fingerprinted no licence file found · pointer only
Reasoning Primitives in Hybrid and Non-Hybrid LLMs: Do Architectural Differences Yield Advantages in State-Tracking and Recall? added by Syntology 2026-04 (from id) ultor1996/reasoning_primitives/src/utils.py 85ea1889d0093c0d ran fingerprinted no licence file found · pointer only
OMIBench: Benchmarking Olympiad-Level Multi-Image Reasoning in Large Vision-Language Models added by Syntology 2026-04 (from id) LightChen233/OMIBench/omi_bench.py 9ea845c01a954867 ran · our draft was wrong fingerprinted licence not identified · pointer only
Do LLMs Game Formalization? Evaluating Faithfulness in Logical Reasoning added by Syntology 2026-04 (from id) koreankiwi99/formalization-gaming/src/utils/answer_parsing.py 651b0f7470e1a3e9 unverified MIT (permissive)
Policy Split: Incentivizing Dual-Mode Exploration in LLM Reinforcement with Dual-Mode Entropy Regularization added by Syntology 2026-04 (from id) BITHLP/PolicySplit/verl/utils/reward_score/openai_math_grade.py 101b1e54fcdadf90 ran fingerprinted no licence file found · pointer only
A Systematic Analysis of the Impact of Persona Steering on LLM Capabilities added by Syntology 2026-04 (from id) cjia7/DPR/src/npti/eval/eval_bbh.py caa05d10c796877f unverified no licence file found · pointer only
CASK: Core-Aware Selective KV Compression for Reasoning Traces added by Syntology 2026-04 (from id) THUDM/LongBench/LongBench/metrics.py e7e75981cb464788 ran · our draft was wrong fingerprinted MIT (permissive)
WikiSeeker: Rethinking the Role of Vision-Language Models in Knowledge-Based Visual Question Answering added by Syntology 2026-04 (from id) zhuyjan/WikiSeeker/utils/infoseek_evaluation_utils.py 4925192ddc8dfa9a unverified Apache-2.0 (permissive)
REAM: Merging Improves Pruning of Experts in LLMs added by Syntology 2026-04 (from id) zai-org/glm-simple-evals/evals/grading/math_normalize.py 101b1e54fcdadf90 ran fingerprinted no licence file found · pointer only
Crystal: Characterizing Relative Impact of Scholarly Publications added by Syntology 2026-03 (from id) allenai/multicite/qa/qasper_evaluator.py d6eb7fc276a790c2 ran · our draft was wrong 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/eval/open_eval.py 5cdd5f07b69b4933 unverified no licence file found · pointer only
Temporal Conflicts in LLMs: Reproducibility Insights from Unifying DYNAMICQA and MULAN added by Syntology 2026-03 (from id) terrierteam/temporal_conflicts/fact_mutability/analysis/f1_score.py e7e75981cb464788 ran · our draft was wrong fingerprinted no licence file found · pointer only
Meta-Reinforcement Learning with Self-Reflection for Agentic Search added by Syntology 2026-03 (from id) tengxiao1/MR-Search/verl/utils/reward_score/search_r1_like_qa_em.py dae7ab386661a4f4 ran · our draft was wrong fingerprinted no licence file found · pointer only
Stacked from One: Multi-Scale Self-Injection for Context Window Extension added by Syntology 2026-03 (from id) Clement25/SharedLLM/LongBenchTest/metrics.py e7e75981cb464788 ran · our draft was wrong fingerprinted no licence file found · pointer only
Stacked from One: Multi-Scale Self-Injection for Context Window Extension added by Syntology 2026-03 (from id) Clement25/SharedLLM/utils.py 6c668580324cfd97 ran · our draft was wrong fingerprinted no licence file found · pointer only
Spectral Attention Steering for Prompt Highlighting added by Syntology 2026-03 (from id) waylonli/SEKA/pastalib/profiler/synthetic_profiler.py 76b695cd06f395b4 unverified Apache-2.0 (permissive)
SkillOrchestra: Learning to Route Agents via Skill Transfer added by Syntology 2026-02 (from id) jiayuww/SkillOrchestra/skillorchestra/eval/metrics.py f23e31c1141ee0fe unverified Apache-2.0 (permissive)
Powering Up Zeroth-Order Training via Subspace Gradient Orthogonalization added by Syntology 2026-02 (from id) OPTML-Group/ZO-Muon/llm/metrics.py e7e75981cb464788 ran · our draft was wrong fingerprinted MIT (permissive)
Small Reward Models via Backward Inference added by Syntology 2026-02 (from id) yikee/FLIP/metrics.py 5a9d2662f435748f unverified no licence file found · pointer only
CompactRAG: Reducing LLM Calls and Token Overhead in Multi-Hop Question Answering added by Syntology 2026-02 (from id) How-Young-X/CompactRAG/src/metrics/F1Eval.py 26a63699755bd04e unverified MIT (permissive)
Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation added by Syntology 2026-02 (from id) GasolSun36/BAR-RAG/filter.py 85fc7d4bd5e8711a ran · our draft was wrong fingerprinted no licence file found · pointer only
Reinforcement Fine-Tuning for History-Aware Dense Retriever in RAG added by Syntology 2026-02 (from id) zyc140345/HARR/metric/qa_em.py dae7ab386661a4f4 ran · our draft was wrong fingerprinted MIT (permissive)
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/utils/reward_score/graphdancer_qa_em.py dae7ab386661a4f4 ran · our draft was wrong fingerprinted no licence file found · pointer only
Alignment-Aware Model Adaptation via Feedback-Guided Optimization added by Syntology 2026-02 (from id) facebookresearch/TruthRL/evaluation/evaluate.py dae7ab386661a4f4 ran · our draft was wrong fingerprinted no licence file found · pointer only
Rethinking Hallucinations: Correctness, Consistency, and Prompt Multiplicity added by Syntology 2026-02 (from id) AI21Labs/in-context-ralm/eval_qa.py dae7ab386661a4f4 ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
On the Paradoxical Interference between Instruction-Following and Task Solving added by Syntology 2026-01 (from id) kijlk/IF-Interference/src/math_and_qa/qa_utils.py dae7ab386661a4f4 ran · our draft was wrong fingerprinted no licence file found · pointer only
Textual Equilibrium Propagation for Deep Compound AI Systems added by Syntology 2026-01 (from id) MinghuiChen43/TEP/src/tep/metrics/f1.py 03171efd2aab7e80 unverified Apache-2.0 (permissive)
SEEK: Steering LLM Reasoning for RAG via Internal Reasoning Sketches added by Syntology 2026-01 (from id) OpenBMB/PAGER/src/evaluate_infer.py d22718d531542ab7 ran · our draft was wrong fingerprinted MIT (permissive)
OpenDecoder: Open Large Language Model Decoding to Incorporate Document Quality in RAG added by Syntology 2026-01 (from id) fengranMark/OpenDecoder/src/evaluation.py 24a31436a8dbd623 unverified MIT (permissive)
Revealing the Attention Floating Mechanism in Masked Diffusion Models added by Syntology 2026-01 (from id) NEUIR/Attention-Floating/evaluate/evaluate_dream.py ff3b542378f5d19c unverified no licence file found · pointer only
HAPS: Hierarchical LLM Routing with Joint Architecture and Parameter Search added by Syntology 2026-01 (from id) zihangtian/HAPS/HotpotQA/joint_rl/rl_batch.py 6c668580324cfd97 ran · our draft was wrong fingerprinted no licence file found · pointer only
Decide Then Retrieve: A Training-Free Framework with Uncertainty-Guided Triggering and Dual-Path Retrieval added by Syntology 7 Jan 2026 ChenWangHKU/DTR/evaluation/metrics.py b92b07bb3574992a unverified no licence file found · pointer only
BaseCal: Unsupervised Confidence Calibration via Base Model Signals added by Syntology 2026-01 (from id) Tan-Hexiang/BaseCal/gen_metric/em.py 9891ffc5ad4f4684 unverified no licence file found · pointer only
Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning added by Syntology 2025-11 (from id) aiming-lab/Agent0/Agent0-VL/verl/evaluation/metrics.py e92c6c13f949ae88 unverified Apache-2.0 (permissive)
Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training added by Syntology 2025-11 (from id) griver/Q-RAG/eval_llm_openqa.py b51d54e1d87d8bd9 ran · our draft was wrong fingerprinted no licence file found · pointer only
LiteraryQA: Towards Effective Evaluation of Long-document Narrative QA added by Syntology 2025-10 (from id) SapienzaNLP/LiteraryQA/literaryqa/ngram_metrics.py dfcf1201010b7d31 unverified no licence file found · pointer only
BOOTSTRAPPING LLMS TO REASON OVER LONGER HORIZONS VIA REINFORCEMENT LEARNING added by Syntology 2025-10 (from id) AlesyaIvanova/h1/math_utils.py 101b1e54fcdadf90 ran fingerprinted no licence file found · pointer only
ReSeek: A Self-Correcting Framework for Search Agents with Instructive Rewards added by Syntology 2025-10 (from id) identical code first harvested elsewhere dae7ab386661a4f4 ran · our draft was wrong fingerprinted licence of this copy not recorded
Mamba Modulation On the Length Generalization of Mamba added by Syntology 2025-09 (from id) gnepul-ace/mamba_modulation/Mamba/LongBench/metrics.py e7e75981cb464788 ran · our draft was wrong fingerprinted MIT (permissive)
TableDART: Dynamic Adaptive Multi-Modal Routing for Table Understanding added by Syntology 2025-09 (from id) xiaobo-xing/TableDART/evaluate.py 90ce0a2b27b15e27 unverified MIT (permissive)
ConfTuner: Training Large Language Models to Express Their Confidence Verbally added by Syntology 2025-08 (from id) liushiliushi/ConfTuner/src/llama_recipes/datasets2/hotpot_qa.py dae7ab386661a4f4 ran · our draft was wrong fingerprinted no licence file found · pointer only
arXiv:2507.21892 2025-07 (from id) LHRLAB/Graph-R1/evaluation/eval_r.py 78b0c6179667e101 unverified MIT (permissive)
The Hallucination Dilemma: Factuality-Aware Reinforcement Learning for Large Reasoning Models 30 May 2025 nusnlp/fspo/evaluate/inference.py d22718d531542ab7 ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset 27 May 2025 microsoft/rstar/fused_compute_score/prime_math/math_normalize.py 31113f93a6e0e98a unverified MIT (permissive)
Iterative Self-Incentivization Empowers Large Language Models as Agentic Searchers 26 May 2025 mangopy/searchlm/src/utilize/metrics.py 93730b62e07a68f0 unverified Apache-2.0 (permissive)
R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning 22 May 2025 RUCAIBox/R1-Searcher/evaluation/metric_calc_rule.py d22718d531542ab7 ran · our draft was wrong fingerprinted MIT (permissive)
Fine-tuning Quantized Neural Networks with Zeroth-order Optimization 19 May 2025 maifoundations/qzo/large_language_models/metrics.py e7e75981cb464788 ran · our draft was wrong fingerprinted MIT (permissive)
Adaptive Orchestration of Modular Generative Information Access Systems 24 Apr 2025 informagi/AQA/Adaptive-RAG/evaluate.py 6a96435eba311b08 ran · our draft was wrong fingerprinted MIT (permissive)
TTRL: Test-Time Reinforcement Learning 22 Apr 2025 prime-rl/ttrl/verl/verl/utils/reward_score/ttrl_math/math_normalize.py 31113f93a6e0e98a unverified MIT (permissive)
Retrieval-Augmented Generation with Conflicting Evidence 17 Apr 2025 hannight/ramdocs/run_madam_rag.py 42413e5aa5425a3e ran · our draft was wrong fingerprinted MIT (permissive)
Out of Style: RAG's Fragility to Linguistic Variation 11 Apr 2025 springcty/rag-fragility-to-linguistic-variation/LLM_generation/c_eval_generation.py bf618b8796ac4942 unverified MIT (permissive)
Single-Pass Document Scanning for Question Answering 4 Apr 2025 mambaretriever/mambaretriever/rag_pipeline/metrics.py e7e75981cb464788 ran · our draft was wrong fingerprinted MIT (permissive)
Do Theory of Mind Benchmarks Need Explicit Human-like Reasoning in Language Models? 2 Apr 2025 bigai-ai/ToM-RL/verl/utils/reward_score/explore_tom.py 1436322b957b9b34 unverified MIT (permissive)
Do Theory of Mind Benchmarks Need Explicit Human-like Reasoning in Language Models? 2 Apr 2025 bigai-ai/ToM-RL/verl/utils/reward_score/explore_tom_2.py c5322e5a65a9bea1 unverified MIT (permissive)
Mind the Gap: Benchmarking Spatial Reasoning in Vision-Language Models 25 Mar 2025 stogiannidis/srbench/src/eval/acc.py 117783c12219bab5 unverified MIT (permissive)
Radar: Fast Long-Context Decoding for Any Transformer 13 Mar 2025 borealisai/radar-decoding/research/longbench/longbench.py e7e75981cb464788 ran · our draft was wrong fingerprinted LGPL-3.0 (copyleft) · pointer only
Agent models: Internalizing Chain-of-Action Generation into Reasoning models 9 Mar 2025 adam-bjtu/autocoa/evaluation/metrics.py 98a43410c5681732 unverified MIT (permissive)
Words or Vision: Do Vision-Language Models Have Blind Faith in Text? 4 Mar 2025 d-ailin/blind-faith-in-text/raw_code/hf_evaluator.py 0bcff406512311b4 ran · our draft was wrong fingerprinted MIT (permissive)
Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling 10 Feb 2025 RyanLiu112/compute-optimal-tts/src/envs/MATH/verify_utils.py 101b1e54fcdadf90 ran fingerprinted MIT (permissive)
C-3PO: Compact Plug-and-Play Proxy Optimization to Achieve Human-like Retrieval-Augmented Generation 10 Feb 2025 Chen-GX/C-3PO/C-3PO/metrics.py 37e0a25b59a4cc3e unverified Apache-2.0 (permissive)
Process Reinforcement through Implicit Rewards 3 Feb 2025 prime-rl/prime/data_preprocessing/math_util/math_normalize.py 101b1e54fcdadf90 ran fingerprinted Apache-2.0 (permissive)
Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Home 22 Jan 2025 s-nlp/AdaRAGUE/Adaptive_Rag/evaluate.py 6a96435eba311b08 ran · our draft was wrong fingerprinted MIT (permissive)
Tell me about yourself: LLMs are aware of their learned behaviors 19 Jan 2025 xuchanbao/behavioral-self-awareness/code/multiple-choice/evaluation/self-report-free-separate-rephrasings.py b75e3691451b3c33 unverified MIT (permissive)
Context-DPO: Aligning Language Models for Context-Faithfulness 18 Dec 2024 identical code first harvested elsewhere e7e75981cb464788 ran · our draft was wrong fingerprinted licence of this copy not recorded
Foundational Large Language Models for Materials Research 12 Dec 2024 M3RG-IITD/llamat/src/Kshot-val.py 6a96435eba311b08 ran · our draft was wrong fingerprinted MIT (permissive)
SiReRAG: Indexing Similar and Related Information for Multihop Reasoning 9 Dec 2024 SalesforceAIResearch/SiReRAG/evaluate_2wiki.py dae7ab386661a4f4 ran · our draft was wrong fingerprinted no licence file found · pointer only
Free Process Rewards without Process Labels 2 Dec 2024 lifan-yuan/implicitprm/eval/math_utils/math_normalize.py 101b1e54fcdadf90 ran fingerprinted Apache-2.0 (permissive)
AtomR: Atomic Operator-Empowered Large Language Models for Heterogeneous Knowledge Reasoning 25 Nov 2024 THU-KEG/AtomR/src/calculate_metrics.py 702b1281050dbc40 unverified no licence file found · pointer only
Squeezed Attention: Accelerating Long Context Length LLM Inference 14 Nov 2024 SqueezeAILab/SqueezedAttention/LongBench/metrics.py e7e75981cb464788 ran · our draft was wrong fingerprinted no licence file found · pointer only
Large Language Models Can Self-Improve in Long-context Reasoning 12 Nov 2024 sihengli99/sealong/eval_longbench_qa.py dae7ab386661a4f4 ran · our draft was wrong fingerprinted no licence file found · pointer only
Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning 25 Oct 2024 fyyfu/headkv/metrics.py e7e75981cb464788 ran · our draft was wrong fingerprinted no licence file found · pointer only
LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering 23 Oct 2024 QingFei1/LongRAG/src/metric.py c6a80c065d2e4851 ran · our draft was wrong fingerprinted no licence file found · pointer only
Trustworthy Alignment of Retrieval-Augmented Large Language Models via Reinforcement Learning 22 Oct 2024 zmzhang2000/trustworthy-alignment/dschat/utils/metrics.py 9706a9a0b961096b unverified no licence file found · pointer only
SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction 17 Oct 2024 sail-sg/simlayerkv/LongBench/metrics.py e7e75981cb464788 ran · our draft was wrong fingerprinted no licence file found · pointer only
RAP: Retrieval-Augmented Personalization for Multimodal Large Language Models 17 Oct 2024 hoar012/rap-mllm/eval/eval_qa.py 7927b07dcc328a1f ran fingerprinted no licence file found · pointer only
Synthetic Knowledge Ingestion: Towards Knowledge Refinement and Injection for Enhancing Large Language Models 12 Oct 2024 intuit-ai-research/knowledge-infused-ai/synthetic-knowledge-ingestion/finetuning/ft_llama_factory.py 6a96435eba311b08 ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
Zeroth-Order Fine-Tuning of LLMs in Random Subspaces 11 Oct 2024 zimingyy/subzero/large_models/metrics.py e7e75981cb464788 ran · our draft was wrong fingerprinted GPL-3.0 (copyleft) · pointer only
StablePrompt: Automatic Prompt Tuning using Reinforcement Learning for Large Language Models 10 Oct 2024 kmc0207/Stableprompt/utils.py d8af265929dc927f ran fingerprinted no licence file found · pointer only

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