Roles for agent assistants in field science: understanding personal projects and collaboration
Bibliographic record
Abstract
A human-centered approach to computer systems design involves reframing analysis in terms of the people interacting with each other. The primary concern is not how people can interact with computers, but how work systems (facilities, tools, roles, and procedures) can be designed to help people pursue their personal projects, as they work independently and collaboratively. Two case studies provide empirical requirements. First, an analysis of astronaut interactions with CapCom on Earth during one traverse of Apollo 17 shows what kind of information was conveyed and what might be automated today. A variety of agent and robotic technologies are proposed that deal with recurrent problems in communication and coordination during the analyzed traverse. Second, an analysis of biologists and a geologist working at Haughton Crater in the High Canadian Arctic reveals how work interactions between people involve independent personal projects, sensitively coordinated for mutual benefit. In both cases, an agent or robotic system's role would be to assist people, rather than collaborating, because today's computer systems lack the identity and purpose that consciousness provides.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.008 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.004 | 0.002 |
| Science and technology studies | 0.005 | 0.017 |
| Scholarly communication | 0.012 | 0.023 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.005 | 0.003 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".