REVIEW 10 cited by
Addressing the Abstraction and Reasoning Corpus via Procedural Example Generation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
This work presents code to procedurally generate examples for the ARC training tasks. For each of the 400 tasks, an example generator following the transformation logic of the original examples was created. In effect, the assumed underlying distribution of examples for any given task was reverse engineered by implementing a means to sample from it. An attempt was made to cover an as large as reasonable space of possible examples for each task. That is, whenever the original examples of a given task may be limited in their diversity e.g. by having the dimensions of the grids, the set of symbols or number of objects constant or within tight bounds, even though the transformation does not require it, such constraints were lifted. Having access to not just a few examples per task, as the case for ARC, but instead very many, should enable a wide range of experiments that may be important stepping stones towards making leaps on the benchmark.
Forward citations
Cited by 10 Pith papers
-
TraceViT: Grounded Trace Supervision for Visual Abstract Reasoning
A looped visual transformer trained on program-derived intermediate grid milestones plus task-reference/object-workspace grounding reaches 67.8% pass@2 on ARC-AGI-1 and 24.3% on ARC-AGI-2.
-
From Global to Factor-Wise Expert Composition in Discrete Diffusion Models
Per-pixel confidence routing of discrete diffusion experts outperforms global scalar composition (SuperDiff, FKC, RNE) on ARC-AGI-style tasks, especially for complementary specialists.
-
Modality-Driven Search with Holistic Trace Judging for ARC-AGI-2
A modality-driven search system with holistic trace judging for ARC-AGI-2 reaches 72.9% on the semi-private set and 76.1% on the public set, outperforming GPT-5.2 Pro and Gemini 3 Pro by 18.7 points while releasing full code.
-
DiARC: Distinguishing Positive and Negative Samples Helps Improving ARC-like Reasoning Ability of Large Language Models
DiARC improves LLM performance on ARC-like tasks by fine-tuning on preference pairs of positive demonstrations and three classes of constructed negative samples.
-
DiARC: Distinguishing Positive and Negative Samples Helps Improving ARC-like Reasoning Ability of Large Language Models
DiARC improves LLM performance on ARC-like benchmarks by constructing and training on preference pairs from three types of negative samples while keeping demonstrations fixed.
-
Slots, Transitions, Loops: Learning Composable World Models for ARC
Loop-OWM uses color-prototype slots, demonstration-conditioned task summaries, and looped transitions to model ARC rules as visual-symbolic state changes and outperforms baselines on ARC-1 and ARC-2.
-
One Step Forward and K Steps Back: Better Reasoning with Denoising Recursion Models
Denoising Recursion Models train multi-step noise reversal in looped transformers and outperform the prior Tiny Recursion Model on ARC-AGI.
-
Recursive Vision Language Models for General Symbolic Reasoning
R-Qwen, a LoRA-adapted Qwen model that iteratively refines explicit candidate solutions under constraint projection, outperforms prior recursive models and zero-shot frontier LLMs on eight symbolic reasoning benchmarks.
-
Channel-Wise MLPs Improve the Generalization of Recurrent Convolutional Networks
Adding a gated channel-wise MLP to a recurrent convolutional network raises median exact-match accuracy on 185 Re-ARC tasks from 78.75% to 92.19% in-distribution and from 2.34% to 14.58% on harder out-of-distribution tasks.
-
Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale
Technical report announcing Ling-2.6 and Ring-2.6 models with hybrid linear attention, evolutionary CoT, and KPop RL for efficient agentic intelligence at scale.
Discussion (0). Sign in to comment.