iiinova — where your digital self keeps evolving

Reposted by Gabriel Agostini

Kenny Peng @kennypeng.bsky.social · 06/10/2026

Our new paper introduces a scientific theory of atomic features. We mathematically derive testable predictions. Our experiments challenge conventional wisdom. SAEs of different size and training data share many features. Large SAEs recover both parent and child features. 🧵

1217 0

Reposted by Gabriel Agostini

Kenny Peng @kennypeng.bsky.social · 18/08/2026

New York City 8th graders choose from 900+ high schools to apply to, in a process that’s spawned Facebook groups and dozens of expensive consulting services. Our new paper shows how application behavior leads to disparities, and how to effectively intervene. 🧵 www.nature.com/articles/s44...

1339 0

Reposted by Gabriel Agostini

Ira Globus-Harris @iraglobusharris.bsky.social · 03/07/2026

Are you at ICML next week? Feel like your decision-making for which sessions to attend might not be risk minimizing? Don't incur (swap) regret and come to my, @aaroth.bsky.social, and @ncollina.bsky.social's tutorial Monday on multicalibration, decision-making, and collaborative learning!

22011 0

Reposted by Gabriel Agostini

Arkadiy Saakyan @asaakyan.bsky.social · 02/06/2026

Excited to share #ICML2026 paper from my internship @ Google DeepMind! AI models are deployed globally, but AI safety datasets are largely geographically homogenous. What is the impact of culture on AI safety ratings? Is there any impact beyond standard demographics like age, gender, and ethnicity?

1113 0

Gabriel Agostini @gsagostini.bsky.social · 01/05/2026

Excited to see MIGRATE recognized in the IPUMS awards! Huge thanks to @emmapierson.bsky.social, @nkgarg.bsky.social, and our coauthors. Our work primarily aims to make spatiotemporal data more trustworthy and accessible to researchers, just like IPUMS. Read the paper to request data access!

094 0

Reposted by Gabriel Agostini

Kenny Peng @kennypeng.bsky.social · 24/04/2026

We made traversle.io, a new daily word game! The goal is to traverse from a start word to a target word through a network of related words. (Our motivating question: is it possible to construct a network that allows human navigation?)

3164 0

Reposted by Gabriel Agostini

Urban Data @urban-data.bsky.social · 23/04/2026

We are co-hosting the EAAMO colloquium next Monday (12pm EST) with Professor Rachel Franklin. Come hear her talk about spatial inequality and the smart city and feel free to share with colleagues! Register below to get the Zoom link: www.eaamo.org/colloquium/r...

032 0

Reposted by Gabriel Agostini

Kenny Peng @kennypeng.bsky.social · 26/03/2026

Excited to share our new research demo, where you can freely traverse the world of Bluesky through 20,000 interconnected trails, spanning “analysis of fictional tropes” to “rotisserie chicken” to “zoning and land use policy.” Try it out, and let us know what you think!

skytrails.org

skytrails · 20,000 trails through Bluesky

Can we regain freedom of movement on social media? Browse Bluesky via interconnected trails.

6459 0

Reposted by Gabriel Agostini

Divya Shanmugam @dmshanmugam.bsky.social · 23/03/2026

New in Nature Health: how might we move towards a world in which race is not used in clinical algorithms? We need (1) careful comparison of race-aware and race-neutral algorithms and (2) systemic efforts to address underlying disparities.

1219 0

Gabriel Agostini @gsagostini.bsky.social · 18/03/2026

Had a great time presenting our work on building MIGRATE–a new dataset of US migration–at the @geographers.bsky.social AAG Annual Meeting today. Happy to also share that we received an AAG student paper award for this work!!! Come chat if you are at #AAG26 this week. migrate.tech.cornell.edu

0123 0

Reposted by Gabriel Agostini

Kenny Peng @kennypeng.bsky.social · 17/02/2026

New paper! The Linear Representation Hypothesis is a powerful intuition for how language models work, but lacks formalization. We give a mathematical framework in which we can ask and answer a basic question: how many features can be stored under the hypothesis? 🧵 arxiv.org/abs/2602.11246

14514 0

Gabriel Agostini @gsagostini.bsky.social · 06/02/2026

I don’t think the methods would be hard to replicate—there is code on my GitHub repo! But I’d imagine we’d need some domain expertise about what are good sources of (noisy, biased) fine-grained migration records in these countries, or about the frequency of census data. Happy to chat more!

010 0

Reposted by Gabriel Agostini

Cornell Tech @cornelltech.bsky.social · 05/02/2026

New research is offering new insight on how Americans move — all the way to the neighborhood level. A new dataset, MIGRATE, maps annual moves with 4,600‑times more detail than standard public data, revealing patterns hidden in county‑level reporting: bit.ly/49XSD6w

052 0

Gabriel Agostini @gsagostini.bsky.social · 05/02/2026

There are over 100 academic, non-profit, governmental, and journalistic research teams from all over the world already using MIGRATE to study topics across the health, environmental, and social sciences! If you are a researcher interested in data access, visit migrate.tech.cornell.edu. 8/9

migrate.tech.cornell.edu

MIGRATE

150 0

Gabriel Agostini @gsagostini.bsky.social · 05/02/2026

MIGRATE is also useful for studying local migration trends. For example, it reveals dramatic rates of out-migration after wildfires in California that are invisible in previous Census datasets. 7/9

141 0

Gabriel Agostini @gsagostini.bsky.social · 05/02/2026

We found, for example, racial disparities in upward mobility —that is, the rate at which people move to higher-income areas varies according to the racial composition of their current area of residence, even after controlling for income levels. 6/9

152 0

Gabriel Agostini @gsagostini.bsky.social · 05/02/2026

A great advantage of MIGRATE is that CBG-level data allows us to more accurately discuss socioeconomic and demographic trends. We documented national migration patterns, such as how far do people move and what are the characteristics of the areas they move to. 5/9

120 0

Gabriel Agostini @gsagostini.bsky.social · 05/02/2026

MIGRATE is over 4,000x more spatially granular than publicly available migration datasets, highly correlated with Census data, and less biased than proprietary address data. We’re making it available to researchers asking all those important migration questions!! 4/9

110 0

Gabriel Agostini @gsagostini.bsky.social · 05/02/2026

We created and released MIGRATE: annual flows between all 47 billion pairs of US Census Block Groups. To do it, we developed an iterative-proportional-fitting based algorithm that harmonizes granular but biased proprietary data with coarser but more reliable Census data. 3/9

110 0

Gabriel Agostini @gsagostini.bsky.social · 05/02/2026

Migration data is key for studying responses to environmental disasters, policy impacts, etc. But public, county-level migration data is too coarse to capture many important dynamics. Proprietary, individual-level address histories are highly granular, but potentially biased. 2/9

120 0

Gabriel Agostini @gsagostini.bsky.social · 05/02/2026

Our paper “Inferring fine-grained migration patterns across the United States” is now out in @natcomms.nature.com! We released a new, highly granular migration dataset. 1/9

27327 0

Reposted by Gabriel Agostini

Urban Data @urban-data.bsky.social · 09/12/2025

November is over, but we still have some #30DayMapChallenge entries to share! And for our transport-themed day 26 map, MBTA data analyst Joe Hilleary takes us on a ride back in time: he shows current bus routes in Greater Boston by the earliest known year in which a direct percursor route ran a bus.

171 0

Reposted by Gabriel Agostini

Emma Pierson @emmapierson.bsky.social · 24/11/2025

We have a new paper in Science Advances proposing a simple test for bias: Is the same person treated differently when their race is perceived differently? Specifically, we study: is the same driver likelier to be searched by police when they are perceived as Hispanic rather than white? 1/

24316 0

Gabriel Agostini @gsagostini.bsky.social · 24/11/2025

My best workflow improvement since starting to work with spatial libraries in Python was to always include a `crs` dictionary on a variables file listing crs for lat-long projections, equidistant projections, and "maybe not satisfying any desiderata but the prettiest out there" projections.

020 0

Reposted by Gabriel Agostini

Urban Data @urban-data.bsky.social · 24/11/2025

#30DayMapChallenge day 20: water This map of Arsenic and Cadmium levels in Mexico's water show non-trace concentrations of Total and Soluble Arsenic and Cadium. Points are colored by the presence of high amounts of contaminants, and sized by their relative concentration. tinyurl.com/map20wtr

182 0

Reposted by Gabriel Agostini

Urban Data @urban-data.bsky.social · 21/11/2025

#30DayMapChallenge 15: Fire @sylviaimani.bsky.social visualized how Uganda’s transition toward electric cooking aligns with the reach of the national grid. Regions with denser grid networks show a strong correlation with higher household adoption of electric cooking technologies.

1122 0

Reposted by Gabriel Agostini

Kyle Walker @kylewalker.bsky.social · 18/11/2025

For #30DayMapChallenge Day 18: Out of this world, use the `fill_z_offset` param in mapgl to "elevate" your data. Just be careful - if you choose a value too high, you might lose your data in the sky! #rstats

072 0

Gabriel Agostini @gsagostini.bsky.social · 17/11/2025

I took me too long to accept that "Amsterdam is just 10th Ave"

010 0

Reposted by Gabriel Agostini

Urban Data @urban-data.bsky.social · 15/11/2025

#30DayMapChallenge day 10: Air @jessiefin.bsky.social + Francisco Marmolejo-Cossío visualize the presence of ladrilleras, or brick kilns, which emit pollution across the state. Data cleaned by Jacqueline Calderón and Lizet Jarquin at UASLP. Full interactive map: tinyurl.com/map10-air

182 0

Reposted by Gabriel Agostini

Urban Data @urban-data.bsky.social · 14/11/2025

#30DayMapChallenge day 9 asked us to get off our screens. @annaloganmc.bsky.social's "analog" map is a hand-painted postcard! 📫 "I chose to paint a postcard of a map of Ann Arbor where I currently live showing the Huron River!" she says

0135 0

Gabriel Agostini @gsagostini.bsky.social · 14/11/2025

tho it's very possible that the dataset misnamed a Subway or two. I filtered for the DOHMH restaurants doing business as "Subway": data.cityofnewyork.us/Health/DOHMH-New-York-City-Restaurant-Inspection-Results/43nn-pn8j

data.cityofnewyork.us

DOHMH New York City Restaurant Inspection Results | NYC Open Data

000 0

Gabriel Agostini @gsagostini.bsky.social · 14/11/2025

The LIC Subway between the Queens Plaza and Queensboro Plaza stations is there, but so close to both stations (and CBs are small there) that we only see a slit of purple! That's also the only Subway in LIC per Google Maps but I wonder if that one is also not up to date.

210 0

Gabriel Agostini @gsagostini.bsky.social · 13/11/2025

Proposing the Subway-subway (🥪-🚇) index

160 0

Gabriel Agostini @gsagostini.bsky.social · 11/11/2025

Great map(s) by @jennahgosciak.bsky.social ---can we count that for 6 days of mapping??---that show both the permanence and the vulnerability of ecological concepts in our urban landscapes! #30DayMapChallenge

040 0

Reposted by Gabriel Agostini

Urban Data @urban-data.bsky.social · 07/11/2025

We are slowly catching up to the #30DayMapChallenge! In our day 3: polygons submission, @zhixuanqi.bsky.social questioned the boundaries and fuzziness of polygons with an animated map that invites us to think about the (not-so-well-defined) idea of neighborhoods.

0164 0

Gabriel Agostini @gsagostini.bsky.social · 06/11/2025

Another dog map, this is 1 dog = 1 dot. And hopefully 1 day = 1 map for the next 30 days in our working group page 🗺️

010 0

Reposted by Gabriel Agostini

Arkadiy Saakyan @asaakyan.bsky.social · 04/11/2025

N-gram novelty is widely used as a measure of creativity and generalization. But if LLMs produce highly n-gram novel expressions that don’t make sense or sound awkward, should they still be called creative? In a new paper, we investigate how n-gram novelty relates to creativity.

N-gram novelty is widely used to evaluate language models' ability to generate text outside of their training data. More recently, it has also been adopted as a metric for measuring textual creativity. However, theoretical work on creativity suggests that this approach may be inadequate, as it does not account for creativity's dual nature: novelty (how original the text is) and appropriateness (how sensical and pragmatic it is). We investigate the relationship between this notion of creativity and n-gram novelty through 7542 expert writer annotations (n=26) of novelty, pragmaticality, and sensicality via close reading of human and AI-generated text. We find that while n-gram novelty is positively associated with expert writer-judged creativity, ~91% of top-quartile expressions by n-gram novelty are not judged as creative, cautioning against relying on n-gram novelty alone. Furthermore, unlike human-written text, higher n-gram novelty in open-source LLMs correlates with lower pragmaticality. In an exploratory study with frontier close-source models, we additionally confirm that they are less likely to produce creative expressions than humans. Using our dataset, we test whether zero-shot, few-shot, and finetuned models are able to identify creative expressions (a positive aspect of writing) and non-pragmatic ones (a negative aspect). Overall, frontier LLMs exhibit performance much higher than random but leave room for improvement, especially struggling to identify non-pragmatic expressions. We further find that LLM-as-a-Judge novelty scores from the best-performing model were predictive of expert writer preferences.

14110 0

Reposted by Gabriel Agostini

Divya Shanmugam @dmshanmugam.bsky.social · 17/10/2025

New #NeurIPS2025 paper: how should we evaluate machine learning models without a large, labeled dataset? We introduce Semi-Supervised Model Evaluation (SSME), which uses labeled and unlabeled data to estimate performance! We find SSME is far more accurate than standard methods.

1217 0

Gabriel Agostini @gsagostini.bsky.social · 14/10/2025

Very happy Divya has been around during my PhD. I might be deep into maps and she might be deep into health (...and so much more!) but I could always count on learning something from her. She's such a kind researcher and great science communicator!

140 0

Gabriel Agostini @gsagostini.bsky.social · 23/09/2025

New version of our preprint! More about the project and data access on our website migrate.tech.cornell.edu

migrate.tech.cornell.edu

MIGRATE

060 0

Gabriel Agostini @gsagostini.bsky.social · 03/09/2025

And if you think your work would be inspiring and interesting for this interdisciplinary audience, you might be a good guest speaker. We are still finalizing this semester's schedule, so send me a message!

010 0

Gabriel Agostini @gsagostini.bsky.social · 03/09/2025

We bring together PhD students, postdocs, faculty, and practitioners from many disciplines to focus on equity, access, and the role of data in shaping urban spaces. We have biweekly meetings with guest speakers, moderated paper discussions, and hands-on workshops. Come join us!

110 0

Gabriel Agostini @gsagostini.bsky.social · 03/09/2025

Are you a researcher using computational methods to understand cities? @mfranchi.bsky.social @jennahgosciak.bsky.social and I organize an EAAMO Bridges working group on Urban Data Science and we are looking for new members! Fill the interest form on our page: urban-data-science-eaamo.github.io

urban-data-science-eaamo.github.io

Urban Data Science & Equitable Cities | EAAMO Bridges

EAAMO Bridges Urban Data Science & Equitable Cities working group: biweekly talks, paper studies, and workshops on computational urban data analysis to explore and address inequities.

188 0

Reposted by Gabriel Agostini

Nikhil Garg @nkgarg.bsky.social · 28/08/2025

*Proud advisor moment* My (first) PhD student Zhi Liu (zhiliu724.github.io) is 1 of 4 finalists for the INFORMS Dantzig Dissertation Award, the premier dissertation award for the OR community. His dissertation spanned work with 2 NYC govt agencies, on measuring and mitigating operational inequities

Reposted by Gabriel Agostini

Streetsblog NYC @nyc.streetsblog.org · 30/06/2025

"Removing the protected bike lane won’t remove cyclists — it will only make the street less safe," the Department of Transportation said in new testimony. "The city risks legal liability for knowingly reducing safety on a Vision Zero priority corridor." buff.ly/QNgRyts

nyc.streetsblog.org

DOT Testimony: Removing Bedford Ave. Bike Lane Will 'Reduce Safety' - Streetsblog New York City

"Removing the protected bike lane won’t remove cyclists — it will only make the street less safe," the DOT said. "The city risks legal liability for knowingly reducing safety on a Vision Zero…

28720 0

Reposted by Gabriel Agostini

Divya Shanmugam @dmshanmugam.bsky.social · 14/06/2025

New work 🎉: conformal classifiers return sets of classes for each example, with a probabilistic guarantee the true class is included. But these sets can be too large to be useful. In our #CVPR2025 paper, we propose a method to make them more compact without sacrificing coverage.

A gif explaining the value of test-time augmentation to conformal classification. The video begins with an illustration of TTA reducing the size of the predicted set of classes for a dog image, and goes on to explain that this is because TTA promotes the true class's predicted probability to be higher, even when it's predicted to be unlikely.

3226 0

Reposted by Gabriel Agostini

Erica Chiang @ericachiang.bsky.social · 01/05/2025

I’m really excited to share the first paper of my PhD, “Learning Disease Progression Models That Capture Health Disparities” (accepted at #CHIL2025)! ✨ 1/ 📄: arxiv.org/abs/2412.16406

33610 0

Reposted by Gabriel Agostini

Arkadiy Saakyan @asaakyan.bsky.social · 01/05/2025

Can vision-language models understand figurative meaning in multimodal inputs, like visual metaphors, sarcastic captions or memes? Come find out at our #NAACL2025 poster on Friday at 9am! New task & dataset of images and captions with figurative phenomena like metaphor, idiom, sarcasm, and humor.

162 0