@cdarwin@c.im2025-11-22 21:13:45
NEW HAVEN, Conn. Nov 22, 2025
Dante Reno lit up No. 10 Harvard Crimson for 273 yards and three touchdowns
as No. 25 Yale Bulldogs seized an Ivy League FCS playoff berth
https://www.cbssports.com/college-football/gametracker/recap/NCAAF_2025112…
@memeorandum@universeodon.com2025-10-21 22:01:18
Trump wants $230 million from DOJ for investigating him: NYT (Dan Mangan/CNBC)
https://www.cnbc.com/2025/10/21/trump-doj-settlement-election-classified-documents.html
http://www.memeorandum.com/251021/p118#a251021p118
@ErikUden@mastodon.de2025-12-22 01:13:27
We watched the Joker ironically and then went on YouTube to watch whatever people made about the movie there back in the day, landed in the worst slop bubble, and dug so deep until we hit “JOKER QUOTES ABOUT WOMEN” and these videos could be classified as performance art, they're pure gold
@aral@mastodon.ar.al2025-11-20 18:53:54
No, please, tell me again how the United States of America is not a fascist country. https://masto.ai/@Nonilex/115583505315668293
@netzschleuder@social.skewed.de2025-12-22 08:00:08
dbpedia_genre: DBpedia work-genre network
A bipartite network of the affiliations between artists and their works on one side and genre classifications on the other, as extracted from Wikipedia by the DBpedia project. The date of this snapshot is uncertain.
This network has 266717 nodes and 463497 edges.
Tags: Informational, Relatedness, Unweighted
@arXiv_csLG_bot@mastoxiv.page2025-12-22 10:33:50
Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning
Wei Tang, Yin-Fang Yang, Weijia Zhang, Min-Ling Zhang
https://arxiv.org/abs/2512.17788 https://arxiv.org/pdf/2512.17788 https://arxiv.org/html/2512.17788
arXiv:2512.17788v1 Announce Type: new
Abstract: Multi-instance partial-label learning (MIPL) is a weakly supervised framework that extends the principles of multi-instance learning (MIL) and partial-label learning (PLL) to address the challenges of inexact supervision in both instance and label spaces. However, existing MIPL approaches often suffer from poor calibration, undermining classifier reliability. In this work, we propose a plug-and-play calibratable disambiguation loss (CDL) that simultaneously improves classification accuracy and calibration performance. The loss has two instantiations: the first one calibrates predictions based on probabilities from the candidate label set, while the second one integrates probabilities from both candidate and non-candidate label sets. The proposed CDL can be seamlessly incorporated into existing MIPL and PLL frameworks. We provide a theoretical analysis that establishes the lower bound and regularization properties of CDL, demonstrating its superiority over conventional disambiguation losses. Experimental results on benchmark and real-world datasets confirm that our CDL significantly enhances both classification and calibration performance.
toXiv_bot_toot
@seeingwithsound@mas.to2025-12-21 14:17:39
From China, on visual-to-auditory sensory substitution: Image-to-sound conversion and automated classification for blind assistance https://dl.acm.org/doi/10.1145/3773365.3773472 2025 8th International Conference on Computer Information Science and Artificial Intelligence, in Wuhan, Chin…
@seav@en.osm.town2025-11-17 10:11:46
#TIL but not surprised that the Dewey Decimal Classification, like many old things, is racist and bigoted.
https://en.wikipedia.org/wiki/Dewey_Decimal_Classification
On
@netzschleuder@social.skewed.de2025-12-21 16:00:04
webkb: WebKB graphs (1998)
Web graphs crawled from four Computer Science departments in 1998, with each page manually classified into one of 7 categories: course, department, faculty, project, staff, student, or other. All graphs included in a single .zip; also included are 'co-citation' graphs, which links i and j if they both point to some k. Edge weights count the number of links from i to j.
This network has 346 nodes and 26832 edges.
Tags: Informational, Web gr…
@netzschleuder@social.skewed.de2025-11-21 16:00:03
product_space: Atlas of Economic Complexity export network
Two networks of economic products, where a pair of products are connected if they are exported at similar rates by the same countries. The data are a projection from a bipartite network of nations and the products they export. Edges weights represent a similarity score (called "proximity"). Data based on UN Comtrade worldwide trade patterns. SITC network based on the Standard International Trade Classification and HS …
