Researcher pairing first-author work in active robot imitation learning with K-12 AI education outreach
2
papers here
2
reviewed by Evolve
2
first-author
0
corresponding
—
works · OpenAlex
—
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-09-19) 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—
Not yet scored: the current snapshot lacks sufficient publication-volume data (paper counts, venue list, yearly output) for this researcher, so the output axis — which measures the scale and consistency of scholarly production over time — cannot be computed.
Impact—
No impact score is available: citation counts, h-index, and venue-level influence data are absent from the current snapshot, so this axis — which would measure how widely the work is cited and adopted — remains unscored rather than estimated at zero.
Focus0/100
The focus score of 0 reflects maximal dispersion in the observed field distribution: the two reviewed papers split exactly 50/50 between machine learning (robot learning / imitation learning) and computing education (K-12 AI education outreach). Rather than thin work, this indicates a deliberate two-track portfolio — a technical active imitation learning paper and a CS-education framework paper — so readers should treat the score as breadth, not lack of depth.
Collaboration32/100
Collaboration scores 32 on a 0-100 scale, based on only 4 distinct coauthors across the reviewed work, indicating a compact collaboration footprint. Recurring partners include Yexiang Xue, Ahmed H. Qureshi, Gustavo Rodriguez-Rivera, and Petros Drineas, and both catalog papers are first-authored without a corresponding-author role, consistent with small-team execution rather than distributed consortium work.
Activity—
Activity is unscored: the snapshot provides no publication-year sequence beyond the two 2026 preprints, so this axis — which would measure publishing cadence and sustained research tempo across years — cannot yet be evaluated and is intentionally left blank.
Reproducibility55/100
Reproducibility averages 55 across the 2 papers with readiness assessments, and both are individually rated medium readiness. Evolve's reviews point to concrete anchors: the active imitation learning paper reports striking, easy-to-check results (100% success with 3 demos) but untested external validity, while the education paper combines a small single-site trial with a 40-year simulation built on assumed parameters, limiting independent replication.
Research summary
Maxwell J. Jacobson is a researcher whose Evolve profile is at an early stage, resting on two first-author arXiv preprints both dated 2026 and split evenly between two fields: machine learning (robot learning / imitation learning) and computing education (K-12 AI education outreach). The technical paper, Missing Bridges: Composition-Aware Active Imitation Learning, proposes AALT, an active imitation learning method that requests bridge demonstrations maximizing start-goal connectivity over a latent topology; Evolve's review calls the theory clean and highlights striking gains — 100% success with only 3 demos — while flagging untested external validity. The education paper, Teaching AI, Robotics, & Community, introduces ARC, a hubs-based K-12 robotics mentorship framework for rural schools built on near-peer mentorship and service learning; the review credits a promising but tiny single-site trial and cautions that a 40-year spatial Markov simulation rests on assumed rather than estimated parameters. Collaboration metrics indicate a compact footprint: 4 distinct coauthors and a collaboration score of 32, with recurring partners including Yexiang Xue, Ahmed H. Qureshi, Gustavo Rodriguez-Rivera, and Petros Drineas. Reproducibility averages 55 across the 2 reviewed papers, each rated medium readiness. Output, impact, and activity scores are absent because the underlying data is insufficient; this profile is name-resolved from public bibliographic data.
Collaboration pattern
The observed collaboration footprint is small: 4 distinct coauthors across the reviewed work, yielding a collaboration score of 32. Recurring partners named in the record are Yexiang Xue, Ahmed H. Qureshi, Gustavo Rodriguez-Rivera, and Petros Drineas. Both 2026 papers position Jacobson as first author without corresponding-author responsibility, suggesting compact small-team execution rather than large multi-institution consortia. The narrow coauthor set also means cross-institution reach cannot yet be assessed from this data.
Research keywords
Highlights
Active imitation learning that targets the missing bridges between behaviors
ARC: a hubs-based K-12 robotics framework for reaching rural schools
First-authored output on two tracks in the same year
Both catalog entries are 2026 arXiv preprints with Jacobson in the first-author position and no corresponding-author role — one advancing active imitation learning, the other K-12 AI education outreach — matching the exact 50/50 split in the bibliometric field distribution.
Timeline
- 2026First-author arXiv preprint Missing Bridges: Composition-Aware Active Imitation Learning introduces AALT, reporting 100% success with 3 bridge demonstrations.
- 2026First-author arXiv preprint Teaching AI, Robotics, & Community proposes the ARC hubs-based K-12 framework, supported by a single-site trial and a 40-year spatial Markov simulation.
- 2026Both catalog entries land in the same year, splitting evenly between robot learning and computing education — consistent with the 50/50 field distribution and the resulting focus score of 0.
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.
- Bibliometrics are computed from a narrow snapshot: only 2 reviewed arXiv preprints, both dated 2026, so the output, impact, and activity axes are unscored.
- No institutional affiliation, country, or ORCID is present; the profile is name-resolved from public bibliographic data, and the name Maxwell J. Jacobson may match multiple researchers.
- Citation counts, h-index, venue list, and publication history beyond the two catalog papers are unavailable and were not estimated.
- Qualitative verdicts (e.g., 100% with 3 demos, the 40-year simulation caveat) are Evolve's review summaries of the preprints, not independently verified results.