PANIC!: An interactive AI playground for creating feedback loops of generative AI models
Bibliographic record
Abstract
PANIC! v3.0.0 - Ash Framework Migration (October 2024) Major architectural migration to the Ash Framework, representing a complete modernization of PANIC!'s codebase. Architecture SQLite + Ash Framework + GenServer Declarative resource definitions with Ash Integrated authentication via AshAuthentication Major Changes Ecto contexts → Ash domains: Business logic now organized in declarative domains Ecto schemas → Ash resources: Data modeling with powerful built-in querying Custom auth → AshAuthentication: Standardized authentication with multiple strategies Finitomata FSM → GenServer-based NetworkRunner: Simplified process architecture Terminology update: 'Prediction' → 'Invocation' for clearer semantics Benefits of Ash Framework Declarative resource definitions: Attributes, relationships, and actions defined in one place Powerful query interface: Composable queries with filtering, sorting, and loading Built-in authorization: Policy-based access control integrated into resources Code interfaces: Type-safe functions generated from resource definitions Extensibility: Easy to add new capabilities through Ash's extension system Technical Improvements Better separation of concerns with domain-driven design More maintainable codebase with less boilerplate Type-safe interfaces throughout the application Improved test architecture using Ash generators This version brings PANIC! into the modern Elixir ecosystem while maintaining backward compatibility with SQLite data storage. The Ash Framework provides a solid foundation for future development and makes the codebase significantly more maintainable.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.003 | 0.000 |
| Scholarly communication | 0.004 | 0.003 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.023 | 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; both teacher heads agree on what is shown here.
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".