@cowboys@darktundra.xyz2026-08-04 10:41:31
Forgotten Cowboys RB is Looking Like Next Training Camp Darling https://heavy.com/sports/nfl/dallas-cowboys/cowboys-israel-abanikanda-training-camp-darling/
@cowboys@darktundra.xyz2026-08-04 10:41:31
@NFL@darktundra.xyz2026-07-30 18:21:38
Baker Mayfield feels 'disrespected' by lack of contract extension ahead of training camp
https://www.cbssports.com/nfl/news/baker-mayfield-disre…
@cowboys@darktundra.xyz2026-08-04 20:36:26
Cowboys Make Decision on Key Starting Blocker at Camp https://heavy.com/sports/nfl/dallas-cowboys/tyler-guyton-nate-thomas-brian-schottenheimer/
@raiders@darktundra.xyz2026-07-21 18:48:13
NFL training camps set to open with 10 new head coaches, several QB changes and plenty of hope https://www.foxsports.com/articles/nfl/nfl-training-camps-set-to-open-with-10-new-head-coaches-several-qb-changes-and-…
@cowboys@darktundra.xyz2026-07-01 14:59:17
What We Learned About Dallas Cowboys Before Training Camp https://www.si.com/nfl/cowboys/onsi/what-learned-dallas-cowboys-before-training-camp
@cowboys@darktundra.xyz2026-07-01 14:22:31
What We Learned About Dallas Cowboys Before Training Camp https://www.si.com/nfl/cowboys/onsi/what-learned-dallas-cowboys-before-training-camp
@philip@mastodon.mallegolhansen.com2026-07-26 23:45:10
@… I think you are *correct* in the conclusion that hosting stuff on GitHub *is* putting it in a training set.
But it also feels a bit… tone deaf? To suggest people can’t be upset by that. When I put my project in GitHub a decade ago, that was very much *not* the expectation that was being set. I’m sure you know that.
The deal changed since then yes, and…
@NFL@darktundra.xyz2026-07-24 04:15:35
NFL training camps for 2026 season open this week https://www.nfl.com/news/nfl-training-camps-for-2026-season-open-this-week
@berlinbuzzwords@floss.social2026-05-24 17:00:15
Radu Gheorghe and Rafał Kuć are joining #bbuzz26 to talk about ways to untangle it: lexical search, significant terms, training an embedder from scratch, etc.
Learn more about their amazing session: https://2026.berlinbuzzwords.de/session/circular-dependency-fixes-when-bootstrapping-a-golden-set/
Join us for Berlin Buzzwords on June 7-9 at Kulturbrauerei or online
@raiders@darktundra.xyz2026-07-28 01:34:20
Raiders add defensive end, linebacker, receiver with camp set to start https://www.reviewjournal.com/sports/raiders/raiders-add-defensive-end-linebacker-receiver-with-camp-set-to-start-3855741/
@arXiv_physicsappph_bot@mastoxiv.page2026-07-22 07:54:16
Evaluation-Recording Contamination in Learned Nano-Quadrotor Dynamics: A Fresh-Seed Audit
David Shulman
https://arxiv.org/abs/2607.18482 https://arxiv.org/pdf/2607.18482 https://arxiv.org/html/2607.18482
arXiv:2607.18482v1 Announce Type: new
Abstract: Learned flight-dynamics models are often trained on short windows extracted from longer recordings. Randomly splitting these windows can place dependent samples from the same physical flight in both training and evaluation sets. We audit this issue using a fixed snapshot of the NanoBench Crazyflie 2.1 dataset. The experiment holds evaluation flights, rollout starts, training-window count, validation data, and optimization budget fixed. In the contaminated protocol, [LeakagePercent] percent of a recording-disjoint training set is replaced with windows from evaluation recordings, while both arms use the same clean validation set. We compare a world-coordinate delta multilayer perceptron with a relative-coordinate control across [NumSeeds] fresh training seeds and [NumEvalFlights] complete evaluation recordings. The primary endpoint is failure-aware position RMSE over 1-second rollouts, analyzed with paired crossed recording-by-seed inference. Contamination lowers apparent world-model error by 12.1 percent, from 0.299 m to 0.262 m, but the predeclared 95 percent confidence interval for contaminated minus disjoint error is -0.0735 to 0.0011 m. Because the interval crosses zero, the confirmatory result is negative. Secondary horizons and the relative-coordinate model show similar trends, but no coordinate-representation interaction is supported. Reliable leakage assessment therefore requires recording-level splits, failure-aware rollouts, replication across fresh seeds, and inference over both recordings and optimization seeds.
toXiv_bot_toot
@arXiv_csCR_bot@mastoxiv.page2026-07-24 08:12:32
Where You Tap Matters: A Probe-and-Model Benchmark for Open-Set RF Fingerprinting
Gabriele Oligeri, Savio Sciancalepore, Ingrid Huso, Fatima Al-Mousawi
https://arxiv.org/abs/2607.21564 https://arxiv.org/pdf/2607.21564 https://arxiv.org/html/2607.21564
arXiv:2607.21564v1 Announce Type: new
Abstract: Radio Frequency Fingerprint Identification (RFFI) enables transmitter identification at the physical layer by learning device-specific impairments from received signals, yet the literature is inconsistent about where in the receiver chain those samples should be collected. Since distinct transformations are applied to the signal by the different receiver operations, i.e., carrier recovery, gain normalization, pulse shaping, and timing recovery, they can either tighten within-transmitter variability or suppress the features RFFI requires for classification. We present a systematic real-world evaluation of open-set, reconstruction-error RFFI using data collected at five probe points along a standard BPSK receiver chain. Our results show that RFFI is strongly probe-dependent: timing recovery and, to a lesser extent, carrier recovery enable low false-acceptance operation with limited in-distribution-out-of-distribution overlap, whereas other stages often require a false-acceptance ratio above 0.1 to achieve a true-acceptance ratio of 0.9. To test the validity of our findings across model selection, we benchmark several LLM-designed autoencoders using a controlled pipeline that holds preprocessing and MSE scoring fixed. These architectures confirm that RFFI is probe-dependent. Moreover, they do not outperform the baseline at the chosen operating point and typically increase training time. Overall, probe selection dominates reconstruction-based open-set RFFI performance, more than the autoencoder complexity.
toXiv_bot_toot
@raiders@darktundra.xyz2026-07-24 13:17:18
Raiders Training Camp Roster: Full 90-Man Roster Entering Camp https://www.si.com/nfl/raiders/onsi/las-vegas-training-camp-roster-full-90-man-entering-camp
@cowboys@darktundra.xyz2026-07-28 16:07:19
6 Most Important Storylines Entering Dallas Cowboys Training Camp https://www.si.com/nfl/cowboys/onsi/most-important-storylines-dallas-cowboys-2026-nfl-training-camp
@cowboys@darktundra.xyz2026-06-22 18:46:44
Cowboys to report to training camp July 28; joint practice dates also set https://cowboyswire.usatoday.com/story/sports/nfl/cowboys/2026/06/22/cowboys-training-camp-report-date-july-28-joint-practi…
@NFL@darktundra.xyz2026-07-27 23:11:13
Vita Vea requests trade from Buccaneers ahead of training camp: Source https://www.nytimes.com/athletic/7473902/2026/07/27/vita-vea-trade-request-buccaneers-nfl/
@philip@mastodon.mallegolhansen.com2026-07-26 23:47:26
@… And, at this point, yes I won’t submit anything new to GitHub. But there’s probably little value in explicitly deleting what is already there.
Like you said, it’s already in the training set. That damage is done, and I’m upset about it.
@cowboys@darktundra.xyz2026-07-27 12:52:12
4 Dallas Cowboys X-Factors During 2026 Training Camp https://www.si.com/nfl/cowboys/onsi/4-dallas-cowboys-x-factors-during-2026-training-camp
@arXiv_physicsaoph_bot@mastoxiv.page2026-05-22 07:51:02
Visibility nowcasting in South Korea: a machine learning approach to class imbalance and distribution shift
Bong Gyun Shin, Chan Sik Lee, Hyesun Suh
https://arxiv.org/abs/2605.21507 https://arxiv.org/pdf/2605.21507 https://arxiv.org/html/2605.21507
arXiv:2605.21507v1 Announce Type: new
Abstract: Atmospheric visibility is a critical variable for transportation safety and air quality management, however, accurate prediction remains challenging due to the complex interactions between meteorological conditions and air pollutants, as well as the rarity of low-visibility events. This study introduces a machine learning framework to nowcast visibility in six major South Korean cities. To handle the imbalance in the 2018-2020 training data, we applied the Synthetic Minority Over-sampling Technique with Nominal and Continuous (SMOTENC) and Conditional Tabular Generative Adversarial Network (CTGAN). An ensemble approach combining machine learning and deep learning models was then used and evaluated on a 2021 test dataset. The results revealed a marked decline in predictive performance in the test set compared to the cross-validation phase. This degradation was attributed to a distributional shift between training and testing periods, which was quantitatively confirmed by measuring the Wasserstein distance of the most influential feature identified by SHAP analysis. In general, this study presents a methodology that aims to simultaneously address the dual challenges of data imbalance and temporal distributional shifts, and emphasizes the necessity of accounting for evolving external environmental factors when implementing nowcasting models on time-series data.
toXiv_bot_toot
@cowboys@darktundra.xyz2026-07-27 12:59:36
4 Dallas Cowboys X-Factors During 2026 Training Camp https://www.si.com/nfl/cowboys/onsi/4-dallas-cowboys-x-factors-during-2026-training-camp
@NFL@darktundra.xyz2026-07-16 12:31:15
Notable NFL injuries to monitor as training camps open: Latest on Mahomes, Nabers, Kittle and more
https://www.cbssports.com/nfl/news/nfl-injury-updates-2026-patri…
@cowboys@darktundra.xyz2026-07-27 20:56:09
All Eyes Are on $28.9 Million Playmaker at Cowboys Training Camp https://heavy.com/sports/nfl/dallas-cowboys/caleb-downs-dallas-cowboys-training-camp/
@pre@boing.world2026-05-28 19:09:55
Content warning: re: UK Pol - Not In Education/Training, Private ownership of wealth
You know there's a chance it would be legal for the King to just set up Brit-Coop as an act of resignation.
Transfer ownership of everything belonging to the crown to a new organization that has ownership by worker-hour, and a mission to rebuild the public infrastructure for the public good.
Use government connections to get it the contracts for welfare-money-for-training.
He won't. Nor will his kids.
Royals aren't about that. They aren't the country. They shouldn't be it's owners.
But it wouldn't be illegal I don't think. If anyone has his royal ear. His big ear.
#monarchy
@raiders@darktundra.xyz2026-07-28 19:30:43
Klint Kubiak says full roster of Raiders players ready day one of camp https://raiderswire.usatoday.com/story/sports/nfl/raiders/2026/07/28/klint-kubiak-full-raiders-roster-read…
@cowboys@darktundra.xyz2026-07-27 16:04:11
When and where are the Dallas Cowboys spending training camp in 2026? https://bolavip.com/en/nfl/when-and-where-are-the-dallas-cowboys-spending-training-camp-in-2026
@cowboys@darktundra.xyz2026-07-26 13:54:39
How to Attend Dallas Cowboys Training Camp: Tickets, Parking and Fan Guide https://www.si.com/nfl/cowboys/onsi/how-to-attend-dallas-cowboys-training-camp-tickets-parking-fan-guide
@raiders@darktundra.xyz2026-07-16 21:17:23
What Kubiak, Raiders Aim To Establish During Training Camp https://www.si.com/nfl/raiders/onsi/las-vegas-what-kubiak-aim-establish-during-training-camp
@cowboys@darktundra.xyz2026-07-26 11:47:18
How to Attend Dallas Cowboys Training Camp: Tickets, Parking and Fan Guide https://www.si.com/nfl/cowboys/onsi/how-to-attend-dallas-cowboys-training-camp-tickets-parking-fan-guide
@NFL@darktundra.xyz2026-07-20 13:24:27
Patriots set to begin training camp on a Saturday ... https://www.espn.com/nfl/story/_/id/49385736/new-england-patriots-starts-2026-training-camp-saturday-drake-maye
@raiders@darktundra.xyz2026-07-16 21:08:39
What Kubiak, Raiders Aim To Establish During Training Camp https://www.si.com/nfl/raiders/onsi/las-vegas-what-kubiak-aim-establish-during-training-camp
@arXiv_qbioNC_bot@mastoxiv.page2026-07-20 07:46:22
Toward a mechanistic understanding of inference in visual cortex and diffusion models
Zeyu Yun, Alexander Belsten, Dasheng Bi, Zahra Kadkhodaie, Yubei Chen, Bruno A. Olshausen
https://arxiv.org/abs/2607.15693 https://arxiv.org/pdf/2607.15693 https://arxiv.org/html/2607.15693
arXiv:2607.15693v1 Announce Type: new
Abstract: We describe a model of perceptual inference in primary visual cortex (V1) equivalent to a minimal diffusion model whose function can be readily understood from its parameters. The model is based on sparse coding with a non-factorial prior over latent variables in the form of an unconstrained, pairwise interaction matrix, extending standard sparse coding inference to a general recurrent dynamical system. We efficiently train these recurrent dynamics using a denoising score-matching objective and implicit differentiation. After training on natural images, the learned interaction matrix mirrors the structure of horizontal connections in superficial layers of V1 that link neurons of similar orientation tuning. This model exhibits exceptionally good denoising performance, restoring image features such as extended contours amid extreme visual ambiguity, nearly matching the behavior of standard, black-box diffusion architectures in generalization regime. Owing to the model's simplicity, the network's Jacobian can be decomposed directly in terms of the interaction matrix between latent variables, revealing mechanistically how the recurrent dynamics assign high probability over a continuous family of natural structural deformations. Intriguingly, within this circuit, a large fraction of latent variables learn to disconnect from visual input altogether, essentially forming a hierarchical representation that appears to enforce global consistency among image features. Together, the model and results bridge two distinct domains: for neuroscience, it generates concrete, testable hypotheses regarding functional connectivity in recurrent neural circuits during perceptual inference tasks; for machine learning, it elucidates the internal mechanisms learned by diffusion models that allow them to generate infinitely many novel images from a finite training set.
toXiv_bot_toot
@arXiv_eessAS_bot@mastoxiv.page2026-05-12 08:26:35
SF-Flow: Sound field magnitude estimation via flow matching guided by sparse measurements
Ege Erdem, Shoichi Koyama, Tomohiko Nakamura, Orchisama Das, Zoran Cvetkovi\'c
https://arxiv.org/abs/2605.10398 https://arxiv.org/pdf/2605.10398 https://arxiv.org/html/2605.10398
arXiv:2605.10398v1 Announce Type: new
Abstract: Reconstructing a 3D sound field from sparse microphone measurements is a fundamental yet ill-posed problem, which we address through Acoustic Transfer Function (ATF) magnitude estimation. ATF magnitude encapsulates key perceptual and acoustic properties of a physical space with applications in room characterization and correction. Although recent generative paradigms such as Flow Matching (FM) have achieved state-of-the-art performance in speech and music generation, their potential in spatial audio remains underexplored. We propose a novel framework for 3D ATF magnitude reconstruction as a guided generation task, with a 3D U-Net conditioned by a permutation-invariant set encoder. This architecture enables reconstruction from an arbitrary number of sparse inputs while leveraging the stable and efficient training properties of FM. Experimental results demonstrate that SF-Flow achieves accurate reconstruction up to \SI{1}{kHz}, trains substantially faster than the autoencoder baseline, and improves significantly with dataset size.
toXiv_bot_toot
@NFL@darktundra.xyz2026-07-22 11:30:22
Deebo Samuel: I still have 'at least three, four good years left' https://www.nfl.com/news/deebo-samuel-i-still-have-at-least-three-four-good-years-left
@arXiv_astrophGA_bot@mastoxiv.page2026-07-22 08:09:07
Estimating stellar metallicities from Gaia DR3 XP data using LAMOST DR10
Divyansh Srivastava, Andrzej Niedzielski, Rodolfo Smiljanic
https://arxiv.org/abs/2607.18707 https://arxiv.org/pdf/2607.18707 https://arxiv.org/html/2607.18707
arXiv:2607.18707v1 Announce Type: new
Abstract: Gaia DR3 provides astrophysical parameters for hundreds of millions of stars, but the metallicities [M/H] from its GSP-Phot module suffer from systematic biases. We estimate stellar metallicities from Gaia DR3 data using the homogeneous spectroscopic iron abundances [Fe/H] of LAMOST DR10 as training labels. We cross-matched LAMOST DR10 with Gaia DR3 and trained a gradient-boosted decision-tree regressor (XGBoost) on 1.20 million AFGK stars using only Gaia-derived inputs and proxies. We validated the estimates on held-out LAMOST stars, GALAH DR4, APOGEE DR17, and 46 open clusters, and applied the model to measure the radial metallicity gradient of the Milky Way disk. On the held-out test set, the model achieves a mean absolute error of 0.052 dex and $R^2=0.94$ with negligible bias, compared with 0.242 dex for GSP-Phot on the same stars. The estimates transfer well to external surveys, with mean absolute errors of 0.066 dex for GALAH and 0.068 dex for APOGEE. For open clusters, the median difference between our estimated [Fe/H] and spectroscopic values is 0.041 dex, smaller than both GSP-Phot (0.248 dex) and a previous APOGEE-trained XGBoost model (0.067 dex). Applied to the Galactic disk, our model recovers a broken thin-disk radial gradient, with inner and outer slopes of $ 0.119$ and $-0.058\,\mathrm{dex\,kpc^{-1}}$, respectively, and a break near 5.9 kpc, as well as an open-cluster gradient of $-0.066\,\mathrm{dex\,kpc^{-1}}$; both agree with previous high-resolution spectroscopic studies. Our [Fe/H] estimates are accurate to 0.05-0.07 dex for AFGK stars with $[\mathrm{Fe/H}]\gtrsim-2.5$; below this limit, the predictions should be treated as lower bounds. The catalogue and trained model are publicly available on Zenodo and are suitable for chemical studies of the Milky Way.
toXiv_bot_toot
@cowboys@darktundra.xyz2026-06-28 23:49:29
NFC East News: Revamped Linebacker Rooms and New Defensive Coordinators Reshaping the Division https://www.si.com/nfl/commanders/onsi/nfc-east-news-roundup-cowboys-eagles-giants-commanders-links
@cowboys@darktundra.xyz2026-06-28 16:49:35
Predicting Dallas Cowboys 53-Man Roster Entering July https://www.si.com/nfl/cowboys/onsi/predicting-dallas-cowboys-53-man-roster-entering-july
@cowboys@darktundra.xyz2026-06-28 16:17:16
Predicting Dallas Cowboys 53-Man Roster Entering July https://www.si.com/nfl/cowboys/onsi/predicting-dallas-cowboys-53-man-roster-entering-july
@NFL@darktundra.xyz2026-07-09 19:45:40
Vikings' QB battle: Kevin O'Connell looking for either Kyler Murray or J.J. McCarthy to set 'standard' https://www.nfl.com/news/vikings-qb-battle-kevin-oconnell-standard-kyler-murray-jj-mccarthy
@raiders@darktundra.xyz2026-07-22 19:15:25
5 home-grown Raiders on their final shot in Las Vegas https://raiderswire.usatoday.com/story/sports/nfl/raiders/2026/07/22/5-home-grown-raiders-final-shot-make-or-break-2026-las-vegas/91012120007/…
@cowboys@darktundra.xyz2026-07-26 13:54:36
Dallas Cowboys Veterans Who Could Lose Their Starting Jobs This Summer https://www.si.com/nfl/cowboys/onsi/dallas-cowboys-veterans-who-could-lose-starting-jobs-this-summer
@cowboys@darktundra.xyz2026-05-26 17:52:44
Joe Milton Named Cowboys Top Trade Candidate Entering 2026 Season https://www.si.com/nfl/cowboys/onsi/joe-milton-named-dallas-cowboys-top-trade-candidate-entering-2026-season
@cowboys@darktundra.xyz2026-07-25 16:57:14
Dallas Cowboys Veterans Who Could Lose Their Starting Jobs This Summer https://www.si.com/nfl/cowboys/onsi/dallas-cowboys-veterans-who-could-lose-starting-jobs-this-summer
@pre@boing.world2026-05-11 09:30:55
Content warning: ukpol - Starmer election response
Starmer is doing a thing about election results. Is he resigning? 
He says the elections were tough, he lost brilliant representatives. He feels the hurt and takes responsibility. Not just for the results, but also for explaining how they'll do better in the years ahead.
Times are dangerous, opponents are very dangerous, if we don't get it right the country will be on a very dark path.
He takes responsibility for navigation in this dangerous world and for not walking away.
Oh right, he's not resigning then. 😦
He says he'll prove his doubters wrong. He's learned a lot! And realizes now we need a bigger response to this unordinary times.
Times demand serious progressive leadership he says, and Zack or Nigel can't provide that. [Citation needed] Only Labour can [Really, come on, citation needed]
He's pleased to be reducing NHS waiting lists and crime, and for some reason is pleased migration is coming down too.
He says he realizes that people don't think Labour cares about them. So that's something.
So his plan to fix things after this election is to talk more about why he's doing things instead of just saying what he's doing.
Right. Sure. That'll help.
He admits millions of people, like his sister, don't get respect or help and are held back because the status quo doesn't work.
He says he's fighting for them but, eh, perhaps he should be doing that thing where he says more about why and how?
He says we need a complete break to take control of energy and defense and fairness (he isn't resigning though, not THAT complete a break)
"Strength Through Fairness, Hope and Urgency" is his plan.
Three concrete examples of the plan:
Sure, about time, not like the Greens are against that.
Doesn't sound like he wants a re-join though, so not really sure what this means. The EU don't allow partial memberships or cherry picking benefits. Some kind of external heart I guess, an outside-body heart pump?
No. He's going to guarantee training or work placements to school leavers.
So in response to likely being unelected next time, he'll nationalize steel (now he's failed to find a corporate buyer anyway), is going to renegotiate with Europe (again, they have no better offers to give), and offer apprenticeships to education-leavers (who are still going to be mostly in debt by then).
Right.
Oh, and he's going to ban more marches too. Almost forgot that.
What a cock.
He did sound a bit passionate at least for a change.
#ukpol #starmer