remove_boxed
Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.
remove_boxed appears in the code Syntology harvested for 48 papers, as 21 distinct code bodies found in 49 places (a place is one code body under one paper). Of the 48 papers, 48 with a sample that ran: 5 with a run with no instrument failure, 43 where every run was a failure of Syntology's instrument. 13 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 remove_boxed 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; get_code(code_sha256="…") returns this sample's fingerprint on the shared battery, with the battery's shuffled null and lift; not shown on this site (how to connect). "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.
Samples Syntology
The 21 distinct code bodies named remove_boxed: 21 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 16 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. One tile per status, in the site's fixed vocabulary, each code body counted once:
Licence is a property of each copy, so it is counted per place: 33 of the 49 places are pointer only (Syntology does not serve that copy's text); at 4 of those this paper's copy is under a permissive licence, but the stored copy of the same code that Syntology serves is not cleared for its text (hover the licence cell for why). 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 “the contract check could not run” (RAISES, DEP_MISSING or TIMEOUT; hover a row's label for which) 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; “with no instrument failure” is honoured, violated and ran with no contract checked. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.
Papers
48 papers shown of 48, newest first; 49 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 17 papers added by Syntology; 4 papers have no page here and are shown by their id only (arXiv: for an arXiv id; an id from another venue, such as ACL Anthology or AAAI, is named as that venue's id, never as an arXiv id). 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. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.
| Paper | Date | File | Status Syntology | Licence |
|---|---|---|---|---|
| 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 bd6200a962c0b2b3 |
ran · our draft was wrong | no licence file found · pointer only |
| Learning from the Self-future: On-policy Self-distillation for dLLMs added by Syntology | 2026-06 (from id) | xingzhejun/d-OPSD/d-opsd/math500_utils.py 4e621edb2336a842 |
ran · our draft was wrong fingerprinted | no licence file found · pointer only |
| Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation added by Syntology | 2026-06 (from id) | YuYingLi0/FiRe-OPD/math_eval/eval_math.py 9a85fff3911bdfa2 |
ran · our draft was wrong fingerprinted | no licence file found · pointer only |
| GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models added by Syntology | 2026-05 (from id) | GaryBall/GDSD/gdsd/utils/math500_utils.py e4d5a8bc57ae4499 |
ran · our draft was wrong fingerprinted | Apache-2.0 (permissive) |
| 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 52adf1b5d14ad2a3 |
ran · our draft was wrong | 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 f6271eeda6c120b7 |
ran · our draft was wrong | no licence file found · pointer only |
| Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation added by Syntology | 2026-05 (from id) | caiyuchen-ustc/EffOPD/EffOPD/math_eval/eval_math.py 9a85fff3911bdfa2 |
ran · our draft was wrong fingerprinted | no licence file found · pointer only |
| GraphPlanner: Graph Memory-Augmented Agentic Routing for Multi-Agent LLMs added by Syntology | 2026-04 (from id) | ulab-uiuc/GraphPlanner/router_planner/shared/math_eval.py c70fa8b9ac912e78 |
ran · our draft was wrong | no licence file found · pointer only |
| TLoRA: Task-aware Low Rank Adaptation of Large Language Models added by Syntology | 2026-04 (from id) | Rambo-Yi/TLora/evaluate/math/eval_math.py f3bbe264b05aadd3 |
ran · our draft was wrong 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_math.py ed70d70cd67847d0 |
ran · our draft was wrong fingerprinted | no licence file found · pointer only |
| REAM: Merging Improves Pruning of Experts in LLMs added by Syntology | 2026-04 (from id) | zai-org/glm-simple-evals/evals/math_eval.py f3bbe264b05aadd3 |
ran · our draft was wrong fingerprinted | no licence file found · pointer only |
| UpSkill: Mutual Information Skill Learning for Structured Response Diversity in LLMs added by Syntology | 2026-02 (from id) | dshah02/upskill/src/DAPO_math_dapo.py 52adf1b5d14ad2a3 |
ran · our draft was wrong | no licence file found · pointer only |
| UpSkill: Mutual Information Skill Learning for Structured Response Diversity in LLMs added by Syntology | 2026-02 (from id) | dshah02/upskill/src/flex_extract.py 937ef0071534906e |
ran · our draft was wrong | no licence file found · pointer only |
| IAPO: Information-Aware Policy Optimization for Token-Efficient Reasoning added by Syntology | 2026-02 (from id) | YinhanHe123/IAPO/compute_reward.py ea98a34b07fe1bfa |
ran · our draft was wrong | MIT (permissive) |
| Diffusion-State Policy Optimization for Masked Diffusion Language Models added by Syntology | 2026-02 (from id) | dllm-reasoning/d1/diffu-grpo/math500_utils.py 4e621edb2336a842 |
ran · our draft was wrong fingerprinted | Apache-2.0 (permissive) here; the stored copy is pointer only |
| ETS: Energy-Guided Test-Time Scaling for Training-Free RL Alignment added by Syntology | 2026-01 (from id) | sheriyuo/ETS/aime24/utils.py 52adf1b5d14ad2a3 |
ran · our draft was wrong | no licence file found · pointer only |
| TokenSqueeze: Performance-Preserving Compression for Reasoning LLMs added by Syntology | 2025-11 (from id) | zhangyx1122/TokenSqueeze/utils/math500_verify.py 53a8a2e9d14cedfd |
ran · our draft was wrong | no licence file found · pointer only |
| DYNAACT: Large Language Model Reasoning with Dynamic Action Spaces added by Syntology | 2025-11 (from id) | zhaoxlpku/DynaAct/math_utils.py f3bbe264b05aadd3 |
ran · our draft was wrong fingerprinted | no licence file found · pointer only |
| Skywork-R1V3 Technical Report | 8 Jul 2025 | seephys/seephys-project/vlmeval/api/bluelm_api.py e531d45668a6c715 |
ran · our draft was wrong fingerprinted | no licence file found · pointer only |
| SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning | 30 Jun 2025 | spiral-rl/spiral/spiral/utils.py f3bbe264b05aadd3 |
ran · our draft was wrong fingerprinted | 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 53a8a2e9d14cedfd |
ran · our draft was wrong | MIT (permissive) here; the stored copy is pointer only |
| arXiv:2503.05188 | 2025-03 (from id) | identical code first harvested elsewhere f3bbe264b05aadd3 |
ran · our draft was wrong fingerprinted | licence of this copy not recorded |
| ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks | 2025-03 (from id) | hengzzzhou/reso/ReSo/agent_graph/agent_graph.py 8f1b63da3ae1c5a7 |
ran · our draft was wrong fingerprinted | no licence file found · pointer only |
| Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models | 24 Feb 2025 | synthlabsai/big-math/signals/rollouts_based_signals/math_eval.py 1fa9e0d56b6ac064 |
ran fingerprinted | MIT (permissive) |
| Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities? | 17 Feb 2025 | ZhiYuanZeng/test-time-scaling-eval/math_evaluator.py 9a85fff3911bdfa2 |
ran · our draft was wrong fingerprinted | Apache-2.0 (permissive) here; the stored copy is pointer only |
| Rethinking Fine-Tuning when Scaling Test-Time Compute: Limiting Confidence Improves Mathematical Reasoning | 11 Feb 2025 | allanraventos/refine/refine/training/filter_samples.py 45f1d7f7f2d4a1e5 |
ran fingerprinted | MIT (permissive) |
| What Do Learning Dynamics Reveal About Generalization in LLM Reasoning? | 12 Nov 2024 | katiekang1998/reasoning_generalization/math_eval_samples.py f3bbe264b05aadd3 |
ran · our draft was wrong fingerprinted | MIT (permissive) |
| Automatic Curriculum Expert Iteration for Reliable LLM Reasoning | 10 Oct 2024 | salesforceairesearch/auto-cei/data/MATH/data_pre.py 05ccbbbc214e3ed4 |
ran · our draft was wrong | Apache-2.0 (permissive) |
| LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning | 3 Oct 2024 | identical code first harvested elsewhere 9a85fff3911bdfa2 |
ran · our draft was wrong fingerprinted | licence of this copy not recorded |
| T2Vs Meet VLMs: A Scalable Multimodal Dataset for Visual Harmfulness Recognition | 29 Sep 2024 | nctu-eva-lab/vhd11k/autogen/math_utils.py 7e08ca15778b791e |
ran · our draft was wrong fingerprinted | CC-BY-4.0 · pointer only |
| To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning | 18 Sep 2024 | identical code first harvested elsewhere f3bbe264b05aadd3 |
ran · our draft was wrong fingerprinted | licence of this copy not recorded |
| BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Models | 8 Aug 2024 | cyp-jlu-ai/ba-lora/inference/math_inference.py f3bbe264b05aadd3 |
ran · our draft was wrong fingerprinted | no licence file found · pointer only |
| LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback | 20 Jun 2024 | kbsdjames/math-minos/evaluation/eval_math.py f3bbe264b05aadd3 |
ran · our draft was wrong fingerprinted | no licence file found · pointer only |
| Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models | 13 Jun 2024 | identical code first harvested elsewhere f3bbe264b05aadd3 |
ran · our draft was wrong fingerprinted | licence of this copy not recorded |
| Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B | 11 Jun 2024 | trotsky1997/mathblackbox/run_with_earlystopping.py 9a85fff3911bdfa2 |
ran · our draft was wrong fingerprinted | no licence file found · pointer only |
| VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks | 24 May 2024 | leo-yangli/VB-LoRA/math_instruction_tuning/instruction_tuning_eval/MATH_eval.py f3bbe264b05aadd3 |
ran · our draft was wrong fingerprinted | no licence file found · pointer only |
| Can LLMs Solve longer Math Word Problems Better? | 23 May 2024 | identical code first harvested elsewhere f3bbe264b05aadd3 |
ran · our draft was wrong fingerprinted | licence of this copy not recorded |
| Exploring the Compositional Deficiency of Large Language Models in Mathematical Reasoning | 5 May 2024 | tongjingqi/MathTrap/eval/eval_MATH_category2.py f3bbe264b05aadd3 |
ran · our draft was wrong fingerprinted | Apache-2.0 (permissive) |
| Make Your LLM Fully Utilize the Context | 25 Apr 2024 | microsoft/FILM/short_tasks/utils.py f3bbe264b05aadd3 |
ran · our draft was wrong fingerprinted | MIT (permissive) |
| Learning From Mistakes Makes LLM Better Reasoner | 31 Oct 2023 | microsoft/lema/inference_code/utils.py f3bbe264b05aadd3 |
ran · our draft was wrong fingerprinted | MIT (permissive) |
| NEFTune: Noisy Embeddings Improve Instruction Finetuning | 9 Oct 2023 | akjindal53244/arithmo/eval/MATH/MATH_compute_metric_zero_shot_CoT.py f3bbe264b05aadd3 |
ran · our draft was wrong fingerprinted | Apache-2.0 (permissive) |
| MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models | 21 Sep 2023 | meta-math/MetaMath/eval_math.py f3bbe264b05aadd3 |
ran · our draft was wrong fingerprinted | Apache-2.0 (permissive) |
| Re-Reading Improves Reasoning in Large Language Models | 12 Sep 2023 | tebmer/rereading-llm-reasoning/utils/util.py f3bbe264b05aadd3 |
ran · our draft was wrong fingerprinted | Apache-2.0 (permissive) |
| Sparks of Artificial General Intelligence: Early experiments with GPT-4 | 22 Mar 2023 | emrgnt-cmplxty/zero-shot-replication/zero_shot_replication/core/math_helpers.py 7ef45e32b9ecc76b |
ran fingerprinted | Apache-2.0 (permissive) |
| Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference | 8 Mar 2023 | kevin666aa/flaml/flaml/autogen/math_utils.py 33b20bbce665cc7a |
ran fingerprinted | MIT recorded; this copy not marked cleared · pointer only |
| Measuring Mathematical Problem Solving With the MATH Dataset | 5 Mar 2021 | identical code first harvested elsewhere f3bbe264b05aadd3 |
ran · our draft was wrong fingerprinted | licence of this copy not recorded |
| OpenReview id openreview_QrC8OgQyOI | viiika/Prism/Dream/Dream_Prism/metrics/gsmk8_eval.py fa5d8fca12c5c0c8 |
ran fingerprinted | Apache-2.0 (permissive) | |
| ACL Anthology id 2025.findings-emnlp.598 | RUCAIBox/MMATH/utils.py 9a85fff3911bdfa2 |
ran · our draft was wrong fingerprinted | MIT (permissive) here; the stored copy is pointer only | |
| ACL Anthology id 2024.findings-emnlp.407 | amayuelas/multi-agent-attack/multiagent_debate/math_parsing.py f3bbe264b05aadd3 |
ran · our draft was wrong fingerprinted | 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is under a permissive licence, but the stored copy of the same code that Syntology serves is not cleared for its text. 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