Large-Scale Application of MILATRAS: Case Study of the Toronto Transit Network
Bibliographic record
Abstract
This paper documents the efforts to operationalize the conceptual framework of MILATRAS (MIcrosimulation Learning-based Approach to TRansit Assignment) and its component models of departure time and path choices (Wahba and Shalaby, 2009a and 2009b). The methodology is applied to a large-scale real-world application, namely the multi-modal transit network of Toronto which is operated by the Toronto Transit Commission (TTC). The TTC transit service, in 2001, operated over 500 branches with more than 10,000 stops in the AM peak period (6-9AM). A mesoscopic model was developed to represent the dynamics of the transit service at the network level with a detailed representation of branch/vehicle-level operations. The developed mesoscopic model represents the movement of each transit vehicle between stops while it microscopically represents individual passenger alighting and boarding activities at each stop, including the interactions among passenger agents and between passenger agents and the transit network. The supply model acknowledges loading priorities at stops and represents congestion through fail-to-board handling. The demand for the TTC transit service for the modelling period is about 320,000 passengers including trips with four categories for trip purpose: home-based work trips (HBW, 67%), home-based school trips (HBS, 27%), home-based other trips (HBO, 4%), and non-home-based trips (NHB, 2%). A learning-based departure time and path choice model was adopted using the concept of mental models for the modelling of the transit assignment problem as a Markovian Decision Process (MDP). The generalized cost, GC, is assumed to be a function of the parameters r " , fixed-cost components r " , and variable-cost components r X. These variables components largely depend on passengers ’ travel choices and the transportation network performance. For a state s and an action a, the GC(S,a) is defined as:
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.000 |
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".