THE INTERNET IS THINKING
Earlier sources: Artificial Intelligence
Artificial intelligence covers systems that learn from data, generate content, perceive their surroundings, or act toward a goal. Follow model research, agent tooling, evaluation, and the infrastructure used to build and run these systems.
SYMTRI organizes observations from public sources into a living map. Connections reflect shared subject matter; they do not establish causation or endorse a source.
Open in the map ↗6036 classified signals in the fourteen-day window. Recent momentum: steady. These counts include signals awaiting readable evidence.
Earlier sources
Up to ten sources with readable evidence, ordered by their feed timestamp. These archive sources can be older than the live fourteen-day window. This list is a sample, not a measure of total activity. Dates distinguish paper publication, repository creation, model/dataset activity, Hacker News posts, and KEV catalog additions. “First archived” records when SYMTRI first stored the signal.
- arXiv · Published · First archived
JudgeCast: Time Series Forecasting with Experience-Informed Covariate Judgements ↗
Covariate effects vary across contexts and shift over time, requiring forecasters to assess how to use them for each forecasting context. As forecasting proceeds, observations for earlier forecasts become available, providing feedback on past covariate use for subsequent forecasts. However, when multiple covariates act together, the forecast error reveals the numerical discrepancy from the observation but not how the covariates should have been used. We introduce JudgeCast, an experience-based framework for time series forecasting with covariates. Following the judgmental adjustment practice,…
- arXiv · Published · First archived
Chinese-Jev: Bringing System One Model to Chinese-Language Tasks ↗
System One models such as Jev offer an efficient alternative to generative language models for tasks that require decisions rather than open-ended responses. However, existing Jev models exhibit limited Chinese-language decision accuracy, restricting their utility in both general and specialized settings. In this paper, we introduce Chinese-Jev, a System One model that addresses this gap through a unified data processing and training pipeline. Our data processing protocol converts heterogeneous Chinese-language annotations into probability targets over candidate options, enabling a shared trai…
- Hugging Face · Model / dataset date · First archived
PBatch23888/birdspotter-yolo26s-640x640 — model update ↗
# BirdSpotter YOLO26-L bird detector YOLO26-L fine-tuned for single-class bird detection at 640 x 640 input resolution. BirdSpotter resizes and pads camera images to this input size. ## Files - `best.pt`: best Ultralytics/PyTorch training checkpoint. - `openvino-int8/`: static batch-one INT8 OpenVINO IR for 640 x 640 input. - `training/`: available training configuration, metrics, and plots. - `manifest.json`: SHA-256 checksums and sizes for the packaged artifacts. ## Usage ### Ultralytics ```python from ultralytics import YOLO model = YOLO("best.pt") results = model.predict("image.jpg", imgsz
- Hugging Face · Model / dataset date · First archived
cheonai/cheon-reranker-0.6b-v1 — model release ↗
# Cheon Reranker 0.6B v1 A reranker for legal and administrative document search, built on Qwen3-0.6B. Most rerankers score query-document pairs one at a time. This one instead encodes the query and all candidates together in a single context, then runs a small bidirectional refiner on top of the pooled candidate vectors so candidates can attend to each other before scoring. The refiner has no positional encoding, so shuffling the candidate order doesn't change the scores. - **Base**: Qwen3-0.6B (Apache-2.0) - **Params**: ~609M total (adapter already merged into the base weights) - **Refiner**
- arXiv · Published · First archived
VStress: Correlation-Aware Auditing and Adaptive Budget Allocation for Repeated Verifiers ↗
Repeated verifier calls are useful only when they contribute conditional information. We introduce VStress, an auditable replay contract, and VStress-CA, a correlation-aware allocation policy that estimates the conditional marginal information of an unqueried verifier on a sealed calibration split, discounts uncertainty, normalizes by call cost, and stops or abstains when the next call is not informative. The controller freezes its decision and cost ledger before joining the clean oracle; a dependence-shift alarm disables channel preference and falls back to exact-stop. The controlled audit gi…
- arXiv · Published · First archived
Beyond Readability: Evaluating Task Information Recoverability ↗
Direct visual readability and task-information recoverability are different quantities. Failure to decode a target from a fixed observation need not eliminate access to that target through another recovery route. We develop an evaluation perspective that makes the observation, query, target, and available knowledge explicit and measures the overlap between routes' success sets. For information available on the original visible surface under suitable imaging conditions, direct optical recovery reads the target from the image, optionally after restoration; entity-linked recovery uses residual vi…
- arXiv · Published · First archived
Controlled Decoding Attacks on Black-Box LLMs ↗
Manipulating next-token probabilities during generation can bypass the safety alignment of large language models. Existing approaches, however, rely on access to model weights or numerical token probabilities and therefore do not apply to interfaces that return only sampled text. Reconstructing probabilities from sampled outputs offers a possible alternative, but finite sampling produces sparse and noisy estimates, while repeating this process at every generation step incurs substantial query costs. Our empirical observations suggest that large distributional changes along successful jailbreak…
- arXiv · Published · First archived
Purlin: Separating Orchestration from the Datapath of Collectives ↗
Distributed inference depends on GPU collective communication that must keep pace with evolving hardware and specialized workloads. However, existing collective implementations often couple semantics, orchestration (where and when data moves), and the datapath (how data moves). This coupling makes it costly to adopt new hardware mechanisms and customize communication for applications. We present Purlin, a scale-up communication framework that separates these concerns. At the top of Purlin, we specify collectives as a naming of an input and output layout and a copy or reduction operation. In th…
- arXiv · Published · First archived
Cool the Sampler, Not the Learner: Sampling Temperature Moves the Staleness Cliff of Importance-Corrected GRPO ↗
Production RL for language models lets the sampler fall behind the learner and repairs the resulting mismatch with a truncated importance weight. We ask how long the sampler can go without a refresh under that correction, and find a cliff: on Qwen2.5-Math-1.5B and GSM8K, importance-corrected GRPO refreshed every 192 updates learns well for 180 steps and then degrades severely in all three data seeds before the refresh arrives. Published remedies for staleness act on the update; we act on the sampler instead. Decoupled cooling draws samples at temperature 0.8 while the learner, the reference mo…
- arXiv · Published · First archived
ER-JEPA: Experience Replay Improves Joint-Embedding Predictive Learning in Language Models ↗
Large language models (LLMs) excel at token-level generation but may learn undesirable abstract semantics and lack comprehensive perception. LLM-JEPA mitigates this by aligning different views of the same underlying knowledge via a joint-embedding predictive architecture (JEPA). However, strong alignment does not necessarily lead to accurate, stable predictions. To address this, we propose ER-JEPA, which adds an episodic replay path to LLM-JEPA. ER-JEPA stores training pairs in a memory. At each step, it stores and retrieves relevant data to provide additional supervision. This enables learnin…
Live window recorded . This is the ingestion observation time, not the publication or discovery date of each source.
How to assess evidence about Artificial Intelligence
Check each original source for its methods, release status, limitations, and supporting data. A repository announcement, a preprint, and a published study provide different kinds of evidence. SYMTRI’s subject classification helps discovery; it does not independently validate the source’s claims.
See the collection and counting methodology ↗ · Read the weekly synthesis ↗
Follow a thread
Explore related regions
These navigation suggestions are part of the map’s editorial structure, rather than measured evidence of a connection.