MIT computational cognitive scientist working on human-like AI evaluation and Bayesian models of mind
2
papers here
1
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
—
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-17) and cover the author's entire public record, not just the papers listed here. Reproducibility signal comes from Evolve's own reviews.
Research profile
Output—
No output metrics are available in this profile's data yet: publication counts, venue breakdowns, and yearly totals are absent. This axis would measure the volume, format, and consistency of scholarly output over time.
Impact—
Impact data is insufficient here: citation counts, h-index, and influence measures are absent from this snapshot. This axis would measure how widely the work is cited and the pull it exerts on subsequent research.
Focus100/100
The bibliometric snapshot places the entire indexed record in a single field - computational cognitive science / AI evaluation (field distribution weight 1.0) - producing a focus score of 100. Both Evolve-reviewed papers sit squarely in that area: one builds a large-scale cognitive benchmark, the other probabilistic models of induction and inquiry. Within this snapshot, topical breadth outside that field is simply not observed rather than ruled out.
Collaboration82/100
The record lists 60 distinct co-authors, yielding a collaboration score of 82. Both cataloged papers are multi-author efforts with Tenenbaum in middle and last author positions, and a recurring cluster of frequent co-authors - including Lance Ying, Katherine M. Collins, Akshay K. Jagadish, Guangyuan Jiang, and Sean Dae Houlihan - consistent with sustained team-based work rather than isolated authorship.
Activity—
Recent-activity signals such as yearly publication cadence are not available in this snapshot, so this axis is left unscored. It would measure how continuously the researcher has published across recent years.
Reproducibility55/100
Reproducibility is scored 55 (reproMean) from exactly one assessed paper (reproPapers 1), so the number is indicative rather than established. Both Evolve-reviewed releases carry a medium repro-readiness rating: CogGym ships a well-validated benchmark, while the induction-and-inquiry paper leaves statistical rigor and reproduction details comparatively thin per the review verdict.
Research summary
Joshua B. Tenenbaum is profiled here as a Massachusetts Institute of Technology researcher working at the intersection of computational cognitive science and AI evaluation. This full-tier profile is name-resolved from public bibliographic data (ORCID 0000-0002-1925-2035) and draws on two Evolve-reviewed 2026 releases. CogGym (2026) unifies 258 cognitive experiments into one comparative benchmark; Evolve's verdict finds LLM-human behavioral alignment scales with model size yet stays far below human reliability, calling it a rigorous, well-validated benchmark. The second, Induction and Inquiry via Probabilistic Reasoning over Language and Code (2026), runs LLM-guided sequential Monte Carlo over language-and-code hypothesis spaces to model human induction and active inquiry, matching human data while leaving statistical rigor and reproduction details comparatively thin. The bibliometric snapshot assigns the entire indexed record to a single field - computational cognitive science / AI evaluation - for a perfect focus score of 100, and lists 60 distinct co-authors (collaboration score 82) with a recurring cluster around Lance Ying, Katherine M. Collins, Akshay K. Jagadish, Guangyuan Jiang, and Sean Dae Houlihan. Reproducibility is scored 55 from one assessed paper, and both releases carry medium repro-readiness. Output, impact, and activity dimensions lack sufficient data and are not scored here. Together the two papers trace one agenda linking Bayesian cognitive modeling, the language of thought, program induction, and large-scale LLM evaluation.
Collaboration pattern
In both cataloged papers Tenenbaum holds middle and last author positions rather than first author, and both works come from large multi-author teams. The record counts 60 distinct co-authors, with a frequent cluster including Lance Ying, Jinzhou Wu, Katherine M. Collins, Akshay K. Jagadish, Guangyuan Jiang, and Sean Dae Houlihan - a pattern consistent with anchoring rotating project teams.
Research keywords
Highlights
CogGym: one benchmark unifying 258 cognitive experiments
Modeling induction and inquiry with LLM-guided probabilistic search
Timeline
- 2026CogGym released on arXiv: a comparative evaluation framework unifying 258 cognitive experiments for human-machine comparison.
- 2026Induction and Inquiry via Probabilistic Reasoning over Language and Code appears on arXiv, pairing LLM-guided sequential Monte Carlo with human induction and inquiry data.
- 2026Both Evolve-reviewed releases land in computational cognitive science / AI evaluation, each rated medium on repro-readiness.
Papers in the Evolve catalog
Frequent co-authors
About this profile
This profile is AI-structured by Evolve.Pub from public bibliographic data (OpenAlex) and Evolve's own paper reviews. It is not written or endorsed by the researcher unless the profile is claimed. Radar dimensions are computed from real bibliometrics with fixed formulas — raw figures are shown alongside; missing dimensions mean insufficient data, never zero. Errors? Claim the profile to correct or hide it.
- Dimension scores come from a public bibliometric snapshot; the reproducibility score rests on a single assessed paper (reproMean 55, reproPapers 1).
- Output, impact, and activity dimensions lack sufficient underlying data and are left unscored rather than estimated.
- Only the two listed Evolve-reviewed papers (both 2026, arXiv-sourced) inform the highlights, timeline, and keyword analysis.
- Profile is name-resolved from public bibliographic data (ORCID 0000-0002-1925-2035); the source record lists no country value.