Record 30092026 · captured 2026-10-01
The world looked up Case Keenum. 30 tracked subjects, 25 discussions, 25 papers. This record is frozen and will not change.
Complete record JSON
What the most people looked up, ranked by Wikipedia pageviews for that day.
Casey Austin Keenum is an American professional football quarterback for the Chicago Bears of the National Football League (NFL). He played college football for the Houston Cougars, where he became the NCAA's all-time leader in total passing yards, touchdowns,
Christa Gail Pike is an American convicted murderer who is incarcerated on death row in Tennessee. In 1995, when she was 18, Pike murdered her 19-year-old Job Corps classmate Colleen Slemmer in Knoxville. Pike and two friends led Slemmer into the woods where t
The 2026 Asian Games, officially known as the XX Asian Games or Aichi–Nagoya 2026, is the largest sporting event in Asia governed by Olympic Council of Asia (OCA). They are currently being held from 19 September to 4 October 2026 in Aichi Prefecture and Nagoya
Dennis Button Haskins IV was an American actor known for his role as Principal Richard Belding in the teen sitcom Saved by the Bell, which ran from 1989 to 1993 on NBC. He then went on to star in Saved by the Bell: The New Class, which aired from 1993 to 2000.
Lizzie Andrew Borden was an American woman who was tried and acquitted of the murders of her father and stepmother in Fall River, Massachusetts. No other individuals were charged with the murders.
India is participating in the 2026 Asian Games in Aichi Prefecture, Japan from 19 September to 4 October 2026. This is the country's 20th consecutive appearance in the competition, having made its debut at the inaugural 1951 Asian Games. The Indian contingent
Theodore John Kaczynski, also known as the Unabomber, was an American mathematician and domestic terrorist. A mathematics prodigy, he abandoned his academic career in 1969 to pursue a reclusive primitive lifestyle and lone wolf terrorism campaign. Kaczynski mu
The 2026 Asian Games , officially the XX Asian Games (第二十回アジア競技大会) and also known as Aichi–Nagoya 2026 (愛知・名古屋2026), is an ongoing multi-sport event being held in Aichi Prefecture in Japan from 19 September to 4 October 2026 though several competitions started
Benjamin Satterley, better known by his ring name Pac, was an English professional wrestler. He was best known for his time in All Elite Wrestling (AEW), where he was a member of the Death Riders and Death Triangle, and WWE, where he previously performed under
The following notable deaths occurred in 2026. Names are reported under the date of death, in alphabetical order. A typical entry reports information in the following sequence:Name, age, country of citizenship at birth, subsequent nationality, what subject was
Aileen Carol Wuornos was an American serial killer. Between 1989 and 1990, while engaging in street prostitution along highways in Florida, Wuornos shot, killed, and robbed seven of her male clients. She initially claimed that her victims had either raped or a
Digger is a 2026 satirical black comedy film directed by Alejandro G. Iñárritu, who co-wrote the script with Sabina Berman, Alexander Dinelaris Jr., and Nicolás Giacobone, from a story by Iñárritu, Berman, and Jez Butterworth. It is a co-production of the Unit
Jeffrey Preston Bezos is an American businessman, and the founder, executive chairman, and former president and CEO of Amazon, the world's largest e-commerce and cloud computing company. According to the Bloomberg Billionaires Index and Forbes, he was the worl
The Paradise (2026 Indian film)
The Paradise is a 2026 Indian Telugu-language period action drama film directed by Srikanth Odela and produced by Sudhakar Cherukuri and Ishan Saksena, under SLV Cinemas and IVY Entertainment, respectively. The film stars Nani, Mohan Babu, Kayadu Lohar, Sonali
Katherine Elizabeth Upton is an American model and actress. She first appeared in the Sports Illustrated Swimsuit Issue in 2011, and was the cover model for the 2012, 2013, and 2017 issues. In addition, she was the subject of the 100th-anniversary Vanity Fair
Neatsville is an unincorporated community in Adair County, located in the U.S. state of Kentucky. It is located at the junction of Kentucky Route 206 and Kentucky Route 76. Its elevation is 705 feet (215 m). For unknown reasons, the town's name was spelled as
A hydraulic ram pump, ram pump, or hydram is a cyclic water pump powered by hydropower. It takes in water at one "hydraulic head" (pressure) and flow rate, and outputs water at a higher hydraulic head and lower flow rate. The device uses the water hammer effec
Primetime is a 2026 American psychological thriller film directed by Lance Oppenheim in his narrative feature film debut. Based on the 2007 Esquire article "Tonight on Dateline This Man Will Die" by Luke Dittrich, the film follows the production of the reality
Justin Brooks Verlander is an American former professional baseball pitcher who played 21 seasons of Major League Baseball (MLB). He played for the Detroit Tigers, Houston Astros, New York Mets, and San Francisco Giants. A three-time Cy Young Award winner, an
Sir Ranulph Twisleton-Wykeham-Fiennes, 3rd Baronet is an English explorer and writer who holds several endurance records.
Limonene is a slightly yellow-green liquid aliphatic hydrocarbon classified as a cyclic monoterpene, and is the major component in the fragrance and essential oil of citrus fruit peels, taking its name from Italian limone 'lemon'.
Monster: The Lizzie Borden Story
Monster: The Lizzie Borden Story is the fourth season of the American biographical crime drama anthology television series Monster, created by Ian Brennan for Netflix. The season centers on murder suspect Lizzie Borden who was tried and acquitted of the 1892 a
Resident Evil is a 2026 horror film directed by Zach Cregger and written by Cregger and Shay Hatten, based on the Resident Evil video game franchise by Capcom. It is the eighth live-action film of the Resident Evil film series, and serves as a reboot. The film
Andrew Gregory Dalton is an American professional football quarterback for the Philadelphia Eagles of the National Football League (NFL). Nicknamed "the Red Rifle", he played college football for the TCU Horned Frogs, winning MW Offensive Player of the Year tw
.xyz is a top-level domain name that was proposed in ICANN's new generic top-level domain (gTLD) Program for consisting of the last three letters of the Latin-script alphabet. XYZ.com and CentralNic are the registries for the domain, which was created by entre
Ansel Easton Adams was an American landscape photographer and environmentalist known for his black-and-white images of the American West. He helped found Group f/64, an association of photographers advocating "pure" photography which favored sharp focus and th
Lanterns is an American superhero television series created by Chris Mundy, Damon Lindelof, and Tom King for HBO, based on the DC Comics Green Lantern characters Hal Jordan and John Stewart. It is the third television series in the DC Universe (DCU). It featur
Dorothy is a 2026 Indian Tamil-language drama film directed by Karthik Subbaraj and produced by Guneet Monga Kapoor, Achin Jain and Jyoti Deshpande. The film stars Keerthy Suresh, Sananth and Rishikanth. It follows two inseparable friends whose lives are trans
Killing of the Clancy children
On January 24, 2023, Lindsay Clancy fatally strangled her three children—five-year-old Cora, three-year-old Dawson, and eight-month-old Callan—at the family's home in Duxbury, Massachusetts, United States. She then cut her wrists and neck and jumped from a sec
Tiana Lillian Marie Caffey is an American professional wrestler and former college soccer player. She is signed to WWE, where she performs on the Raw brand under the ring name Jaida Parker and is a member of The 946 stable alongside Royce Keys and OTM.
What the people building things argued about, from Hacker News.
Papers submitted to arXiv cs.AI that day.
Semifactual Credit-Augmented Policy Optimization
Reinforcement learning with verifiable rewards (RLVR) has improved the reasoning capabilities of large language models (LLMs), yet their predictions remain sensitive to task-irrelevant prompt features. We investigate this sensitivity through semifactual prompt interventions that preserve the underlying problem and its answer. Our analysis reveals substantial variation in token-level sensitivity and shows that suppres
ViTeX-Bench: Benchmarking High-Fidelity Video Scene Text Editing
Recent video generation is increasingly realistic and controllable, yet video editing remains less developed, particularly for precise local edits that must preserve the original scene dynamics. Video scene text editing replaces text on scene surfaces, such as storefront signs, whiteboards, and product labels, while preserving the surrounding content, motion, and camera dynamics. Although scene text editing is well s
Turbo Harness: Instance-Adaptive Harness Optimization
Automating the search for effective harnesses is an important step toward enabling agents to recursively self-improve. Existing harness optimizations typically produce a single global harness that is applied uniformly across task instances. However, a harness that works well on average may not be optimal for every instance. We introduce Turbo Harness, a framework that can adapt a globally optimized harness to each in
WorldAuditBench: Interactive 3D World Auditing with Multimodal Agents
As interactive 3D worlds are increasingly used to study intelligent behavior, it becomes important to develop efficient pipelines for identifying anomalies in these simulated environments, such as floating objects, traversable walls, or objects inconsistent with the surrounding scene. Multimodal AI systems, including vision-language models (VLMs) and vision-language-action models (VLAs), have shown potential for auto
Cogentic: Multi-Agent Orchestration for Automated Proof Discovery
We present Cogentic, a multi-agent harness for automated proof discovery on open research problems. While frontier language models can generate strong mathematical ideas in a single shot, single-shot generation is often insufficient for open problems that require exploring multiple competing conjectures, overcoming subtle technical obstructions, and retaining intermediate progress over a long horizon. Cogentic addres
MatLoom: Layered Text-to-Material Generation in a Compact Program Space
Material generation should produce not only an appearance, but also the rules that construct it. We introduce MatLoom, a compact, layer-oriented language for text-to-material generation with pretrained language models. Each program composes alpha-masked layers whose shared spatial expressions define coverage and physically based rendering (PBR) channels, making dependencies between patterns, color, and relief explici
Scaling Laws for Looped Mixture of Experts
Looped transformers and Mixture-of-Experts (MoE) offer complementary routes to efficient scaling: recurrence increases computational depth at fixed parameters, while MoE sparsity expands total capacity at fixed active compute. Yet existing scaling laws model recurrence or sparsity in isolation. In this work, we introduce Loop Scaling Laws, the first scaling law to jointly model recurrence and sparsity alongside model
DynaHarness: A Dynamic Physical Harness for Self-Evolving Robot Agents
Pretrained robot policies provide useful action priors, but long-horizon manipulation still requires coordination between semantic reasoning and physical execution. Semantic reasoning operates at a coarser timescale than physical interaction, while episode-level failures provide limited guidance on which system component should be revised. We propose DynaHarness, a dynamic physical harness that couples semantic reaso
How Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering?
Recent autonomous machine learning engineering (MLE) agents have made significant progress on public leaderboards. Often motivated by progress stagnation over long-horizon cycles and limited Large Language Model (LLM) primitives, modern MLE agents are deployed on top of increasingly elaborate machinery: multi-agent orchestrators, dedicated retrieval subagents, and more. While such harnesses expand, the use of more pr
CAS II: Symmetric Partitions as Kolmogorov Models
In algorithmic statistics a string x is explained by a finite set containing it, and Kolmogorov's structure function records the smallest such model at each level of complexity. Vereshchagin's strong models, those computable from the data by a total algorithm, are essentially the cells of simple partitions. We read a partition of binary strings as a hypothesis, with the cell containing x as its model, and develop alg
Linguistic Loopholes in LLM Unlearning: From a 174-Language Benchmark to Coverage-Aware Unlearning
Unlearning a fact in one language does not guarantee its removal in others as changing the query or even the requested answer language can reopen seemingly forgotten knowledge -- a cross-lingual loophole. The most straightforward solution to this challenge -- unlearning in all languages -- is neither scalable nor desirable as it amplifies damage to unrelated model capabilities. We introduce the task of language budge
PivotOPD: Learning to Recover from Pivotal Mistakes in Multi-Turn Agents
On-policy distillation (OPD) is a promising approach for training language agents, providing dense teacher supervision on student-generated trajectories. However, in multi-turn interaction, an incorrect action changes the states the student encounters later, so errors compound across turns. In preliminary experiments across three Qwen3 models (8B to 235B), we find that more than half of the failed rollouts contain a
cua-speedrun: Standardized Benchmarking of the Speed of Computer-Use Agents
Computer use agents (CUAs), which use graphical user interfaces (GUIs) to complete tasks on a computer, have recently surpassed human performance on many standard benchmarks, including difficult long-horizon tasks. Their capabilities are undoubtedly impressive, however, a key barrier to the widespread adoption and deployment of CUAs remains their speed and cost. Progress towards faster yet capable CUAs requires relia
Belief-Aware Multi-Agent Path Finding under Map Uncertainty
Multi-Agent Path Finding (MAPF) aims to find collision-free paths for multiple agents in a shared environment. Classical MAPF assumes that all static obstacles are known in advance, but real-world environments can change unexpectedly due to fallen objects, spills, or other local disturbances. When such changes are spatially correlated, an observation can inform traversability estimates beyond the observed location. P
ComputerSD: Online Self-Distillation from Real-Time Feedback for Computer-Use Agents
Online training enables computer-use agents (CUAs) to improve through interaction with executable environments. However, existing methods primarily rely on sparse outcome rewards, which provide no supervision for intermediate actions. On-policy self-distillation (OPSD) offers token-level learning signals through privileged rescoring, but directly applying it to CUA online training presents two challenges: fixed guida
EviRover: Reinforcing Agentic Perception Beyond a Glance
Visual perception is conventionally formulated as a one-shot prediction from a single glance at the image, under the assumption that the image content and the model's parametric knowledge suffice to resolve the query. This assumption often fails in real-world scenarios that hinge on fine-grained visual details or require knowledge-intensive and up-to-date information. We term such cases \textit{perception under insuf
PhantomEnvironments: Training LLM Agents in Fictional Worlds
Training LLM agents with reinforcement learning (RL) is bottlenecked by environments, which must provide verifiable rewards, support long-horizon interaction, and scale cheaply. Existing approaches rely on costly human-curated data or on LLM-generated environments that risk hallucinations and benchmark contamination. We show that LLMs can instead be trained into capable search agents using synthetic environments gene
World Action Models (WAMs) couple visual dynamics prediction with action generation, yet they do not explicitly support the reuse of action experience across manipulation tasks. Furthermore, existing WAMs struggle to capture underlying cross-task semantic relationships that could guide target action prediction, as redundant background elements interfere with the extraction of key visual information. To address these
SCB: SpeechConversationBench for Evaluating Multi-Turn Reasoning in Speech-to-Speech Models
Speech-to-speech systems must solve tasks whose requirements emerge across conversational turns. We introduce SpeechConversationBench (SCB), a focused evaluation of spoken mathematical reasoning using 103 sharded GSM8K problems. The framework compares the original problem delivered in one turn (full), its concatenated information shards delivered together (concat), and incremental spoken disclosure across turns (shar
MemLife: Curating and Reasoning over Long-Term Egocentric Video Memories
Long-term egocentric video enables personalized AI assistants to reason about daily life. However, as video histories grow to hundreds of hours spanning months or years, reprocessing raw clips for every query becomes computationally prohibitive. Memory systems offer a scalable alternative by compacting videos into text representations, but often fail on practical benchmarks: either the memory does not preserve key ev
Learning from Research: Toward Lifelong Agent Harness Evolution
Language agents are expected to solve increasingly complex tasks, creating a growing need for continual improvement. One promising approach is to evolve the agent harness, the software that governs tool use, memory management, and task execution, while keeping the underlying language model fixed. Recent methods automate this process by using a meta coding agent to modify the harness based on execution feedback. Howev
PrefPI: Preference-Guided Steering into Out-of-Distribution Behaviors
We present PrefPI (Preference-Guided Policy Iteration), an iterative framework for steering pretrained generative robot policies using only relative preferences over self-generated trajectories. Unlike prior preference-learning methods that primarily sharpen modes already represented by the policy, we study steering beyond the initial effective support, where desired behaviors are rarely or never observed under the i
Game-Guided Skill Discovery through Self-Play for Playable Agent Control
We present Game-Guided Skill Discovery (GGSD), a framework that uses self-play in games to discover motor skills that are directly playable by humans. Playable skills provide a compact abstraction for controlling embodied agents through a small set of learned behaviors rather than low-level actions. To be effective, these skills should be semantically distinct, interpretable, and expressive; properties that existing
Tactile Curiosity Drives Robot Interaction
Mastering robot manipulation skills via reinforcement learning (RL) remains largely sample-inefficient. The most common RL algorithms rely on random action sampling to discover new strategies, resulting in agents that allocate most of their training budget to motions in free space, away from the contacts from which manipulation skills emerge. Existing intrinsic motivation methods based on model disagreement or episte
On the (In)effectiveness of AMR Augmentation for Large Language Models
While Abstract Meaning Representation (AMR) has historically improved performance on a range of NLP tasks, the benefit---or lack thereof---of AMR augmentation for modern LLMs is thus far unclear. In this paper, we attempt to reproduce recent work that reported substantial downstream gains from AMR augmentation, finding that these are likely due to specific choices in the experimental settings used: using a consistent
Origins publishing files written for machines rather than people. Measured against a frozen cohort, so a change in the number means a change in adoption.
| Signal | Web head Tranco top 1,000 n=1,000 | Web tail sampled to rank 100k n=1,000 | AI-native model & dev platforms n=110 |
|---|---|---|---|
| Any agent-facing signal | 11.8% (118) | 4% (40) | 74.55% (82) |
| llms.txt (apex domain) | 9.5% (95) | 3.4% (34) | 60% (66) |
| llms.txt (docs subdomain) | 4.3% (43) | 0.8% (8) | 45.45% (50) |
| .well-known/mcp.json | 0.6% (6) | 0.2% (2) | 8.18% (9) |
| .well-known/agents.txt | 0.3% (3) | 0.2% (2) | 0% (0) |
| ai.txt | 0.2% (2) | 0.1% (1) | 0% (0) |
| ai-plugin.json (deprecated) | 0.6% (6) | 0.1% (1) | 0.91% (1) |
Notable events recorded on this day and month across all years.