Record 24082026 · captured 2026-08-25
The world looked up Spider-Man: Brand New Day. 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.
Spider-Man: Brand New Day is a 2026 American superhero film based on the Marvel Comics character Spider-Man. Produced by Columbia Pictures, Marvel Studios, and Pascal Pictures, and distributed by Sony Pictures Releasing, it is the 38th film in the Marvel Cinem
Hayden Lesley Panettiere was an American actress and singer. She starred as Claire Bennet on the NBC superhero series Heroes (2006–2010), Kirby Reed in the slasher horror franchise Scream (2011–2023), Juliette Barnes in the ABC/CMT musical drama series Nashvil
Joseph Kevin Keegan was an English football player and manager who played as an attacking midfielder or forward. Nicknamed "King Kev" or "Mighty Mouse", Keegan was recognised for his dribbling ability, finishing and presence in the air, as much as he was for h
The Odyssey is a 2026 epic action fantasy film written and directed by Christopher Nolan, who produced it with his wife Emma Thomas. An adaptation of Homer's ancient Greek epic poem the Odyssey, it stars an ensemble cast including Matt Damon, Tom Holland, Anne
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
Michele Ann Marie Fabares was an American actress and singer. She was known for her television roles as Francine Webster on One Day at a Time, Mary on the sitcom The Donna Reed Show (1958–1963) and as Christine Armstrong on the sitcom Coach (1989–1997), the la
Natalie Harp is an American political aide and former television anchor who has served as special assistant and executive assistant to the President of the United States since 2025.
Michael Wright was an American actor best known for his roles in the films The Five Heartbeats (1991), Streamers (1983) for which he won the Volpi Cup for Best Actor, and Sugar Hill (1994), and for his television roles Elias Taylor in V: The Series (1984–1985)
Neatsville is an unincorporated community in Adair County, 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 Neetsvil
Awarapan 2 is a 2026 Indian Hindi-language action thriller film directed by Nitin Kakkar, written by Kakkar, Bilal Siddiqui and Vishesh Bhatt, and produced under his banner Vishesh Films. A sequel to the 2007 film Awarapan, the film stars Emraan Hashmi, Disha
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
Alphadjo Cisse is an Italian professional footballer who plays as an attacking midfielder for Serie A club AC Milan. He is an Italian youth international.
Matthias Jaissle is a German professional football manager and former player who is currently the head coach of Premier League club Newcastle United.
Anna's Archive is an open source search engine for shadow libraries that was launched by the pseudonymous Anna shortly after law enforcement efforts to shut down Z-Library in 2022. The site aggregates records from Z-Library, Sci-Hub, and Library Genesis (LibGe
Obsession is a 2025 American supernatural horror film written, directed, and edited by Curry Barker. The film follows Bear, a music store employee who buys a supernatural toy that grants his wish for his friend Nikki to fall in love with him, which makes her b
Edward Jacob Lang is an American far-right activist and political candidate. He was a participant in the 2021 January 6 United States Capitol attack, for which he served four years in prison. Lang was one of those pardoned by President Donald Trump in his pard
Lesbian Space Princess is a 2025 Australian adult animated science fiction comedy film written and directed by Emma Hough Hobbs and Leela Varghese in their directorial debuts. It features the voices of Shabana Azeez, Bernie Van Tiel, Gemma Chua-Tran, Richard R
2026 Men's FIH Hockey World Cup
The 2026 Men's FIH Hockey World Cup is the 16th edition of the Men's FIH Hockey World Cup, the quadrennial world championship for men's national field hockey teams organized by the International Hockey Federation. It is being held from 15 to 30 August 2026 in
Carlos Espí Escrihuela is a Spanish professional footballer who plays as a forward for La Liga club Real Madrid.
Insidious: Out of the Further is a 2026 American supernatural horror film written and directed by Jacob Chase. It serves as a sequel to Insidious: The Red Door (2023) and is the sixth installment in the Insidious franchise. In the film, a young woman who can i
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
Saransh Jain is an Indian cricketer. He made his first-class debut for Madhya Pradesh in the 2014–15 Ranji Trophy on 21 December 2014. He made his List A debut for Madhya Pradesh in the 2016–17 Vijay Hazare Trophy on 25 February 2017.
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
UFC Fight Night: Hernandez vs. Rodrigues
UFC Fight Night: Hernandez vs. Rodrigues was a mixed martial arts event produced by the Ultimate Fighting Championship that took place on August 22, 2026, at the Golden 1 Center in Sacramento, California, United States.
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").
The End of Oak Street is a 2026 American science fiction survival film written, co-produced, and directed by David Robert Mitchell. It stars Anne Hathaway, Ewan McGregor, Maisy Stella and Christian Convery as a family whose suburban neighborhood has been trans
Vishwanath & Sons is a 2026 Indian Tamil language romance and family drama film written and directed by Venky Atluri. Produced by Sithara Entertainments and Fortune Four Cinemas, the film stars Suriya, alongside Mamitha Baiju, Raadhika Sarathkumar, and Raveena
List of Marvel Cinematic Universe films
The Marvel Cinematic Universe (MCU) centers on American superhero films produced by Marvel Studios, based on characters that appear in publications by Marvel Comics. The MCU is the shared universe in which all of the films are set. Marvel Studios has released
Shiyazh Tastohyinya Pete is an American professional football player who is an offensive tackle for the Dallas Cowboys of the National Football League (NFL). He played college football for the New Mexico State Aggies and Kentucky Wildcats.
The Odyssey is one of two major epics of ancient Greek literature attributed to Homer. It is one of the oldest surviving works of literature and remains popular with modern audiences. Like the Iliad, the Odyssey is divided into 24 books. It follows the heroic
What the people building things argued about, from Hacker News.
Papers submitted to arXiv cs.AI that day.
How to Train a Critic Stably and Efficiently
Group-based reinforcement learning methods such as GRPO for large language models avoid training a critic by sampling multiple responses for each prompt. A reliable critic could instead estimate token-level advantages from one response, but standard critic-based training recipes are often unstable. We study this instability and develop \textbf{Best-Practice Critic Optimization (BPCO)}, a recipe that combines DPPO, va
ReWorld: An Interactive World Model with Long-Horizon Memory
An interactive world model must follow the user's actions, remember the places it has shown, and stream in real time. The tension is structural: control wants a short horizon, memory wants an unbounded one. ReWorld separates the two during training and bounds them at inference. Mixed per-head attention windows confine most heads to the recent past while a small set of global heads attends over the entire history, and
SWE Refactor Bench: Can Coding Agents Complete a Long-Horizon, Whole-Repository Stack Migration?
Modern software systems accumulate technical debt over decades of development, which makes migration expensive and largely manual. As coding agents become increasingly capable at bug fixing, can they autonomously perform such migrations? Existing benchmarks cannot answer this question because they evaluate only behavioural correctness, not whether the migration actually occurred. This leads an easy hack: agents copy
EG-ARSA: An Expert-Grounded Open Model for Visual Road Safety Auditing in Low-Resource Settings
Road traffic injuries remain a major challenge in low- and middle-income countries, where proactive road safety auditing is limited by incomplete crash records, shortages of qualified auditors, and the high cost of large-scale field inspections. To address this problem, we propose Expert-Grounded Distillation (EGD), a novel artificial intelligence framework that transfers institutional road safety expertise into a co
Ballistocardiography (BCG) is promising for unobtrusive long-term blood pressure (BP) monitoring in laboratory settings, but traditional BCG signals are vulnerable to the variations in body-bed interaction with shifted fiducial points in temporal or amplitude axis, and BP varies with personal hemodynamic changes, causing misaligned representations that affect model generalizability and robustness. In this work, we pr
Prime Agent: A Self-Improving RLM Harness
Language models are sequential processors, but long-horizon agency requires external information and computation beyond model weights and active context. Prime Agent is an open-source harness for long-horizon evaluation and coding-agent workflows. A persistent IPython REPL follows the Recursive Language Model abstraction for programmatic context processing and test-time compute, while Continual Harness preserves hist
ConvergeFlow: Language Flow with Provable Convergence to Token Embeddings
Recent advances in continuous diffusion and flow-based language models (LMs) have achieved performance competitive with discrete LMs. However, existing continuous frameworks still rely on decoders supervised with cross entropy (CE) because the flow trajectories are not guaranteed to terminate at valid token embeddings. Motivated by this limitation, we introduce \textbf{ConvergeFlow}, an embedding-space flow-based LM,
How AI Assistance Affects Human Skill Development: A Study of Learning with Logic Puzzles
While AI assistance can improve human task performance in the short term, it may also undermine the development of skills in the longer term. We examine this tension in a controlled logic-puzzle experiment involving on-demand AI assistance, where participants complete tasks before, during, and after AI is available. By experimentally varying AI request costs, we find that lower-cost assistance induces more frequent A
The Interaction Tax: When Communication Erases Diversity in Multi-Agent Teams
Does multi-agent LLM interaction help or hurt? Some work reports gains from debate (Du et al., 2024), critique loops (Chen et al., 2025), and mixture-of-agents synthesis (Wang et al., 2025), while other work finds that interaction adds cost without improving quality under equal budgets (Tran & Kiela, 2026; Xu et al., 2026; Jarrett et al., 2025), or that independent sampling already captures multi-agent gains (Li
Adapter-Based Few-Shot Continual Learning for Malicious Packet Recognition
The continual evolution of malware variants necessitates detection systems that can adapt to new threats without retraining from scratch. However, continually updating models on new data often leads to catastrophic forgetting, where previously learned knowledge is overwritten. While continual learning has been increasingly explored for malware detection, the specific setting of Few-Shot Class-Incremental Learning (FS
Correcting a learned physical invariant improves world-model rollouts
World models can predict video without learning dynamics that they reliably preserve. We test whether a frozen DreamerV3 trained only on pendulum video learns a scalar that its own latent transition treats as approximately conserved. A label-free search recovers the same energy-like invariant across independently trained conservative models, while the same procedure finds no comparable invariant in matched damped mod
EarthVerse: Benchmarking Scientific Agents Across Dynamic Earth Systems and Natural Hazards
Earth-system analysis reconstructs changing physical processes from observations that differ in source, scale, timing, and modality. Natural hazards make this work consequential because incomplete evidence can change estimates of severity, exposure, and mechanism. We introduce EarthVerse, a benchmark that evaluates scientific agents through package-scoped investigations. Its 405 reproducible tasks are grounded in 199
The Measurement Revolution? Credible Measurement and Inference in the Age of AI
Artificial intelligence (AI) is transforming measurement in economics. AI models convert unstructured data, such as text and images, into structured variables at low cost, making previously prohibitive measurement feasible at scale. This shifts the bottleneck from finding any scalable measure of a phenomenon to choosing among many plausible ones, which may support different empirical conclusions. This review provides
Historical people may appear under different languages, scripts, and transcription traditions, while distinct individuals may share highly similar or even identical names. This makes historical identity reconciliation more than a problem of string matching or transliteration. We introduce MHER, a provenance-controlled benchmark for pairwise reconciliation of person-name attestations from the Mongol world. MHER contai
Mitigating Reasoning-Induced Misalignment via Safety-Direction Penalty
Reasoning-Induced Misalignment, where fine-tuning on reasoning data containing no harmful content, including mathematics, code, and problem-solving with chain-of-thought traces can induce harmful behaviors of LLM, posing a serious challenge to the safety of LLM reasoning. Cross-architecture, cross-scale, and cross-dataset checks show that RIM does not always emerge. Previous work attributed RIM to neuron-level entang
SRPO: Self-Reflective Policy Optimization for Long-Horizon Reasoning
Self-reflection is a powerful mechanism for credit assignment in human learning, converting sparse outcome feedback into actionable guidance. However, its potential for post-training Large Language Models (LLMs) remains underexplored. We propose Self-Reflective Policy Optimization (SRPO), a framework that internalizes this capability. SRPO enables LLMs to analyze their own completed trajectories, synthesize errors in
We present Team Semiintelligencn's solution for the ACM RecSys 2026 TalkPlayData Challenge, addressing conversational music recommendation through a multi-modal and personalized conversational recommender system. Our submitted system employs a three-stage pipeline: (1) multi-modal retrieval constructing decay-weighted centroids across seven dense embedding spaces - track- and user-level CF-BPR, Qwen3 (metadata, lyric
Act with Intent: Distilling Behavior Intent for Vision-Language-Action Models
Vision-Language-Action (VLA) models can turn multimodal context into robot actions, but their action decoders are still trained largely by behavior cloning. This supervises which motor command was demonstrated while leaving implicit the local objective served by the behavior under the instruction. Future-based supervision enriches action learning with frames, latent observations, trajectories, or motion representatio
StrategyBench: Evaluating Explicit Strategy Induction in Large Language Models
As large language models are increasingly used in data-scarce and evolving task scenarios, few-shot in-context learning (ICL) has become a key paradigm for task adaptation. However, direct ICL often uses a small set of examples without explicitly abstracting task rules, making it sensitive to example construction. In contrast, human learners often reduce such sensitivity by first summarizing task rules from examples
What's the Catch? Evaluating Temporal Consistency in Vision-Language Models
Vision-language models (VLMs) achieve strong performance on video and image-sequence benchmarks, yet it remains unclear whether they capture temporal structure. To study this question, we formulate temporal grounding as an anomaly detection problem, providing a simple and controlled evaluation that directly tests sensitivity to temporal consistency. We introduce TimeCatch, where temporal anomalies are created by swap
Time series forecasting (TSF) is evolving toward multimodal and agentic settings, yet using foundation models remains uneconomical in resource-constrained scenarios, where compact, specialized forecasters are more desirable. However, lightweight forecasters typically require substantial training data, limiting their use in domains with scarce, slowly accumulated, or privacy-sensitive time series. To address this dile
InjecMEM: Memory Injection Attack on LLM Agent Memory Systems
Memory is becoming a default subsystem in deployed LLM agents to provide persistent personalization and continuity. This naturally prompts a question: will memory system introduce new vulnerabilities into agents? Thus we propose InjecMEM, a novel memory injection attack paradigm that requires only a single interaction (no read/edit access to memory store) to steer later responses of related queries toward a pre-speci
Machine Learning Assisted Inverse Design of Pixelated mmWave Patch Antennas
A machine learning-assisted framework for the inverse design of pixelated millimetre-wave patch antennas targeting the 22--30 GHz band is presented. The antenna surface is represented as a 19x23 binary pixel grid on a Rogers RT/duroid 5880 substrate, where each pixel is either metal or empty, with a continuous electrical path from the feed enforced by design. An initial dataset of approximately 6,000 full-wave CST si
Reward-Free Continual Adaptation for Resilient Space Robots
Space robots operate in extreme environments where hardware degradation can critically compromise traditional control strategies. While continual reinforcement learning offers a promising mechanism for online adaptation, it inherently requires access to a reward signal during deployment. However, precise reward computation in space is often infeasible due to the lack of external tracking systems and the overall compl
Characterizing Necessary Losers to Explain Tournaments Losers
We study the problem of formally explaining why a candidate was not selected by a given tournament rule, by identifying sub-tournaments in which the candidate loses independently of how the rest of the tournament is completed. We define destructive minimal supports as any minimal sub-tournaments satisfying this property, which in formal explainable artificial intelligence correspond to abductive explanations for the
Notable events recorded on this day and month across all years.
89 New Zealand Native football team