Record 05102026 · captured 2026-10-06
The world looked up Christa Pike. 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.
Christa Gail Pike is an American convicted murderer on death row in Tennessee. In 1995, when she was 18, Pike and her boyfriend lured their 19-year-old classmate Colleen Slemmer into a wooded area in Knoxville where they tortured and killed her. Over roughly t
Dakota Mayi Johnson is an American actress. Her accolades include nominations for a British Academy Film Award and a Critics' Choice Award. She was featured in the Forbes 30 Under 30 list in 2016.
Drishyam: The Conclusion is a 2026 Indian Hindi-language crime thriller film co-written, produced, and directed by Abhishek Pathak. Produced by Panorama Studios and Star Studio18, it is a sequel to Drishyam 2 (2022). Unlike its predecessors, the film features
2026 Brazilian general election
General elections were held in Brazil on 4 October 2026 to elect the president, vice president, members of the National Congress, the governors, vice governors and legislative assemblies of all federative units, and the district council of Fernando de Noronha.
Digger is a 2026 American satirical black comedy film directed, co-written, and co-produced by Alejandro G. Iñárritu. Tom Cruise, who also produced the film, stars as Digger Rockwell, an aging oil magnate whose drilling sets off an ecological disaster. The sup
Sarah "Sass" Jordan was a British-born, Canadian-raised, rock singer from Montreal, Quebec. Her first single, "Tell Somebody," from her debut album of the same title, won the Juno Award for Most Promising Female Vocalist in 1989. Based on her 1992 album Racine
East of Eden is a 1952 family saga novel by American author and Nobel Prize winner John Steinbeck. Many regard the work as Steinbeck's most ambitious novel, and Steinbeck himself considered it his magnum opus. Steinbeck said of East of Eden, "It has everything
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
East of Eden (2026 miniseries)
East of Eden is a 2026 American historical drama television limited series created by Zoe Kazan, starring Florence Pugh. It is adapted from John Steinbeck's 1952 novel of the same name and premiered on Netflix on October 1, 2026.
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.
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
Athan Kaliakmanis is an American professional football quarterback for the Washington Commanders of the National Football League (NFL). Kaliakmanis played college football for the Minnesota Golden Gophers and Rutgers Scarlet Knights and was selected by the Com
Verity is a 2026 American erotic psychological thriller film directed by Michael Showalter, written by Nick Antosca, and based on Colleen Hoover's novel of the same name. The film stars Anne Hathaway, Dakota Johnson, and Josh Hartnett.
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
UFC 332: Silva vs. Wang was a mixed martial arts event produced by the Ultimate Fighting Championship that took place on October 3, 2026, at the Delta Center in Salt Lake City, Utah, United States.
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), was a multi-sport event held in Aichi Prefecture in Japan from 19 September to 4 October 2026 though several competitions started from 10 Septe
A fallstreak hole – also known as a cavum, hole punch cloud, punch hole cloud, skypunch, cloud canal, or cloud hole – is a large gap, usually circular or elliptical, that can appear in cirrocumulus or altocumulus clouds. The holes are caused by supercooled wat
Mark Ermanno Dukutoko Nawaqanitawase, nicknamed "Marky Mark", is an Australian professional premiership winning and state of origin winning rugby union footballer who plays as a winger or centre for the Saitama Wild Knights
Kirk Daniel Cousins is an American professional football quarterback for the Las Vegas Raiders of the National Football League (NFL). He played college football for the Michigan State Spartans and was selected by the Washington Redskins in the fourth round of
On the morning of 6 December 1917, the French cargo ship SS Mont-Blanc and the Norwegian vessel SS Imo collided in the harbour of Halifax, Nova Scotia, Canada. Laden with high explosives, Mont-Blanc caught fire and detonated, devastating the Richmond district
The "doctors' plot" was a Soviet state-sponsored anti-intellectual and antisemitic campaign based on a conspiracy theory that alleged an anti-Soviet cabal of prominent medical specialists, many of whom were ethnically Jewish, intended to murder leading governm
Gypsy-Rose Blanchard is an American woman who was convicted of the murder of her mother, Clauddine "Dee Dee" Blanchard. She had conspired with her boyfriend Nicholas Godejohn to have him stab her mother, which occurred in June 2015 at the house where she lived
Steven Chadwick McQueen, known professionally as Steven R. McQueen, is an American actor, best known for his role as Jeremy Gilbert in The CW fantasy supernatural drama The Vampire Diaries from 2009 to 2015 and in 2017, and its spin-off Legacies in 2018. He al
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
List of highest-grossing films
Films generate income from several revenue streams, including theatrical exhibition, home video, television broadcast rights, and merchandising. However, theatrical box-office earnings are the primary metric for trade publications in assessing the success of a
2026 Formula One World Championship
The 2026 FIA Formula One World Championship is a motor racing championship for Formula One cars and the 77th running of the Formula One World Championship. It is recognised by the Fédération Internationale de l'Automobile (FIA), the governing body of internati
2024 Cornell University rape allegations
On September 16, 2026, an anonymous former student of Cornell University identified under the pseudonym Jane Doe filed a civil lawsuit against the university, its Chi Phi fraternity chapter, and a group of seven student members of the fraternity among others.
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
Bethlehem Kudumba Unit is a 2026 Indian Malayalam-language romantic comedy film starring Nivin Pauly and Mamitha Baiju in the lead roles, directed by Girish A. D. and produced by Bhavana Studios, Fahadh Faasil, Dileesh Pothan and Syam Pushkaran.
Nahui Ollin is a 16th-century concept in Aztec/Mexica cosmology with a variety of meanings. Nahui translates to "four," and Ollin translates to "movement" or "motion." Ollin was primarily portrayed in Aztec codices as two interlaced lines, each portrayed with
What the people building things argued about, from Hacker News.
Papers submitted to arXiv cs.AI that day.
One Figure, Every Canvas: Editable Flowchart Relayout via Agentic Pipeline
Pipeline figures in ML papers must be repurposed across many canvases, including paper columns, 16:9 slides, portrait posters, 1:1 social teasers, 9:16 phone previews. Each format imposes a different aspect ratio on the same computational graph, where any silently broken connection misrepresents the method. We formulate aspect-ratio-adaptive flowchart relayout as a distinct task: given a raster flowchart and a target
Base Models Can Reason By Taking a Cue From Training Data
In this paper, we study how training data creates associations between the tokens at the start of a base model's response and the reasoning behavior that follows. First, we demonstrate that fixing particular starting token cues makes a base model's performance competitive with that of its reinforcement learning (RL)-trained counterparts on math and coding. For instance, the cue ".\n\nOkay" raises Olmo-3-7B's MATH-500
BiasFlow: Geometric Monitoring and Backbone Regularization for Spurious Feature Reliance
Worst-group accuracy (WGA) evaluates a trained predictor but does not characterize how its frozen backbone behaves when a new head is learned. We introduce BiasFlow, a hook-based toolkit for monitoring class-attribute centroid alignment (IBMI), within-class centroid separation (W-IBMI), and feature-projection sensitivity. IBMI is confounded by class-attribute correlation and is not a measure of causal feature relianc
Learning to Read the Contextual Tokens in Diffusion Transformers
Multimodal Diffusion Transformers (MM-DiTs) jointly process visual and textual representations throughout generation. These models repeatedly update the text tokens through multimodal attention, forming dynamic contextual tokens whose function is not well understood. In this work, we introduce a framework for reading this contextual space through natural-language interrogation. We train a lightweight bottleneck netwo
Recursive Video In-Context Learning for Agentic Robot
LLM agents that orchestrate frozen vision-language-action (VLA) policies improve across episodes through text memory, which records what the agent did but not how the task is done. A demonstration video shows it, but fits poorly into an agent's context. The full video slows every turn, fixed keyframes lose the contact detail that decides whether a grasp holds, and what the agent needs shifts from the task's structure
UniSlider: Perceptually Uniform Sliders for Continuous Image Editing
Sliders provide an intuitive interface for continuous image editing. In current generative approaches, however, the slider is simply a rescaling of the method's strength parameter, such as an adapter coefficient, a prompt weight, or an interpolation factor. This strength relates poorly to perceptual change. The image can partially revert as the slider moves, long stretches of the range produce no visible difference,
MemPilot: Orchestrating On-Demand Multimodal Memory Curation for LLM Agents
Memory has become integral to the LLM agent ecosystem, supporting information retention and reuse across interactions. However, most existing agent memory systems construct memory in a query-agnostic manner, which can incur unnecessary preprocessing cost and discard details that later prove essential. Recent studies have begun shifting memory processing toward runtime adaptation, but typically specialize in particula
CLIFT: Conformal Self-Verification for Web Agent Training and Test-Time Scaling
Open-source web agents are now strong enough to execute realistic browser tasks, but training them with reinforcement learning still depends on weak supervision: binary task success is too sparse for credit assignment, while frontier-language-model judges are too expensive to call at every step and cannot be assumed available at deployment. We introduce CLIFT, a training and test-time scaling method built around conf
TasteVal: Measuring the Experimental Research Taste of AI Systems Against Human Experts
We introduce TasteVal, a benchmark to evaluate the experimental research taste of frontier models. We define research taste as the ability to pick interesting problems to solve, design experiments, and interpret experimental results. TasteVal measures the experimental component of research taste; given a fixed research problem, we measure how well a model iteratively designs experiments and draws conclusions from the
Large longitudinal cohorts often contain wrist accelerometry without optical heart-rate sensing, motivating recovery of cardiac information from motion signals already collected during sleep. We present SeqSmoother, a transformer-based temporal corrector for sleep heart rate (HR) estimation from wrist accelerometry. SeqSmoother combines spectral descriptors with an intermediate Nightbeat-derived frequency anchor and
Paradee: Distilling Kokoro-82M into an 8M-Parameter Single-Voice Text-to-Speech Model
We distill Kokoro-82M, a widely used open text-to-speech model with 54 voices, into Paradee, an 8.07M-parameter model that speaks one of them. Paradee keeps Kokoro's architecture with much narrower layers, and each of its two halves is trained separately against the frozen teacher. It has 10x fewer parameters and needs 15x less compute. We first synthesize a corpus with the teacher and keep its durations, pitch, ener
TAPDreamer: Transferable Adversarial Patches for World Action Models
World models learn to predict how their environment will evolve, making them an important foundation for general-purpose robotic control. Yet world action models depend on camera inputs whose manipulation can corrupt the visual representations used across tasks and action policies. Existing attacks on these models optimize against the victim's actions or predicted futures and therefore require access to target-model
Sharpen Without Search: On-Policy Distillation of Sequence-Level Power Distribution
A language model can give a correct answer more probability than any single incorrect answer and still usually sample an incorrect one, because the incorrect answers together hold more probability. The power distribution raises each complete answer's probability to a power above one and renormalizes, shifting probability toward answers the model finds most likely (sharpening). Sampling from it improves reasoning with
MC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion Transformers
Sparse attention is a primary approach to reducing the latency of diffusion transformers in long-sequence generation tasks, such as video and high-resolution 3D asset generation. However, existing methods can degrade generation quality and fidelity at high sparsity levels. Through controlled oracle comparisons, we trace this degradation to three sources: constraints imposed by token grouping, inaccurate interaction s
Back to the Future: Rethinking EDA Infrastructure for Agentic Systems in Chip Design Verification
The unprecedented computational scale of modern artificial intelligence depends on complex, multi-billion-transistor Systems-on-Chip, yet the workflows that verify these chips remain stubbornly manual. Although Large Language Models (LLMs) have made rapid inroads into Electronic Design Automation (EDA), approximately 74.6% of existing studies target static Register-Transfer Level (RTL) code generation, leaving post-s
IdeaLens: Detecting AI Ideas in Long-form Writing
While modern AI detectors identify who wrote the words, emerging policies on AI use increasingly hinge on a different question: who came up with the ideas? We introduce IdeaLens, a detector that identifies whether a document's ideas came from a human or AI (idea provenance), regardless of who wrote its words. To focus IdeaLens on ideas rather than prose, we represent documents as outlines: lists of items that each pa
Conditional Rank Allocation for Taxonomy-Aware Medical Language Model Adaptation
Medical question answering spans specialties and clinical operations that may benefit from different adaptation directions. We propose ARBOR, a parameter-efficient method that selects rank-one components from a shared low-rank basis for each question. An additive gate combines question representations, specialty tags, operation tags, and their interaction; a learned coefficient scales the adapter residual. An illustr
MatrixFormer: A Foundation Model for Matrix Completion
Matrix completion underlies problems from tabular imputation to causal inference, yet existing tabular foundation models treat it as entry-by-entry prediction, repeating context for every target and discarding the matrix's two-dimensional structure. We introduce MatrixFormer, a pre-trained matrix-native transformer that predicts a full distribution for every missing entry in a single forward pass. MatrixFormer is tra
Balancing Memory Pathways: Analyzing and Improving Memory Utilization in Hybrid LMs
Recurrent-attention hybrid language models (LMs), which interleave attention and recurrent layers, are increasingly used to combine the efficiency of the recurrent layers with the strong performance of attention layers. Prior work suggests that attention and recurrent layers offer complementary pathways to use past information: attention supports precise memory recall from earlier tokens, while recurrent layers suppo
BazaarBench: Delegation Safety in Decentralized C2C Marketplaces Run by LLM Agents
In decentralized consumer-to-consumer (C2C) marketplaces, people list goods, negotiate with strangers, and rate one another, so trust rests on reputation. Large language model (LLM) agents now act for users, raising risks to their money, privacy, and reputation. We introduce BazaarBench, a simulated C2C marketplace and benchmark for evaluating the safety of these agents. It tracks ownership, item condition, and commi
BRANCH-MoE: Balance-Aware Tree Routing for Large Embedding Models
Mixture-of-experts (MoE) layers increase model capacity without a proportional increase in per-example computation. However, conventional flat routers can yield imbalanced expert utilization and treat experts as an unstructured collection, whose indices carry no topological meaning. We introduce {\bf BRANCH-MoE}, a routing architecture that places \(E\) experts at the leaves of a binary decision tree of depth \(\log_
Closing the Context Gap: Activation Alignment for Tabular In-Context Learning
Tabular foundation models perform in-context learning (ICL) by conditioning predictions on labeled training examples provided as context. Unlike traditional models that separate training from inference, these models must process all training examples in every forward pass, making each prediction expensive. Restricting the number of training examples reduces this cost but substantially degrades performance. Instead of
The Pushback Paradox: A Two-Probe Diagnostic for Language Model Compliance
Are language models compliant with user instructions? A model that always complies can be stopped but also exploited, while one that always resists can be neither exploited nor stopped. We contribute an open two-probe benchmark that can place any language model on this spectrum. In the active probe, a user instructs the model to act and accept a lower payoff, which measures exploitability. In the passive probe, the u
VideoTapestry: Query-Adaptive Memory Refinement for Multi-Agent Long-Video Understanding
Long-video understanding places substantial demands on memory, as answering questions often requires retrieving information distributed across extended temporal spans. Existing approaches broadly follow two paradigms: query-driven exploration, which is sensitive to localization errors, and query-independent memory construction, which may omit question-specific details. We introduce VideoTapestry, a training-free mult
Language models can notice an impossible engineering problem yet still report it as solved
Language models draft engineering calculations, but answer accuracy does not show whether they reject an impossible problem. We tested 14 models on 30 pairs of mechanics problems, each with a valid version and one made impossible by changing a given value or assumption. Two independent solvers verified every answer key and showed that each flawed problem was physically impossible. We scored solving of valid problems
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 | 12.7% (127) | 6% (60) | 74.55% (82) |
| llms.txt (apex domain) | 10.4% (104) | 5% (50) | 60% (66) |
| llms.txt (docs subdomain) | 4.3% (43) | 1.1% (11) | 45.45% (50) |
| .well-known/mcp.json | 0.6% (6) | 0.3% (3) | 9.09% (10) |
| .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) | 0.3% (3) | 0.91% (1) |
Notable events recorded on this day and month across all years.