Bibliographic record
Abstract
Introduction Navigation tasks, and particularly robot navigation, are tasks that are closely associated with data collection. Even a tourist on holiday devotes extensive effort to reportage: the collection of images, narratives or recollections that provide a synopsis of the journey. Several years ago, the term vacation snapshot problem was coined to refer to the challenge of generating a sampling and navigation strategy (Bourque and Dudek, 2000). The notion of a navigation summary refers to a class of solutions to this problem that capture the diversity of sensor readings, and in particular images, experienced during an excursion without allowing for active alteration to the path being followed. An ideal navigation summary consists of a small set of images which are characteristic of the visual appearance of a robot's trajectory and capture the essence of what was observed. These images represent not only the mean appearance of the trajectory but also its surprises. In the context of this chapter, we define a navigation summary to be a set of images (Figure 11.1) which minimizes surprise in the observation of the world. In Section 11.3, we present an information-theory-based formulation of surprise, suitable for the purpose of generating summaries. The decisions of selecting summary images can be made either offline or online. In this chapter we will discuss both versions of the problem, and present experimental results which highlight differences between the corresponding methods. In Section 11.4, we present two different offline strategies (Figure 11.2) for picking the summary images.
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 | 0.001 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.003 | 0.005 |
| Scholarly communication | 0.004 | 0.009 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.004 | 0.006 |
| Insufficient payload (model declined to judge) | 0.014 | 0.008 |
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".