Synthetic Cognition Meets Data Deluge: Architecting Agentic AI Models for Self-Regulating Knowledge Graphs in Heterogeneous Data Warehousing
Bibliographic record
Abstract
The realities of contemporary data management and representation are evolving at an increasing rate. However, we still lack the broad foundational bridges of core data warehousing principles relating to how high-level reports are generated internally so that users can psychologically intuit where they are in the vast and complex repository of data that resides in a typical data warehouse. IT workers must constantly support users or worry about failed ad-hoc or automated operations or whose results appear without explanation. Data management may not yet exist as a science. We need a more complete transformational view of the details of the internal mappings between data from diverse sources and conceptual data model object types. Cognitive model-driven and symbolic techniques have been approached to design and develop systems to automate and rationalize these transformational processes and to support user navigation and work. These techniques are now being displaced by advanced statistical learning methods. As designed, these methods mostly do knowledge creation in the basic steps of the transformational process, but they likewise at times pave data as well. Through AI as Intentional Cognition supplemented by language, this inhibition may be bypassed. Thus, despite both their synthetic and agentic capabilities, these approaches follow a surprising and quite diverse transition. The goal of this work is to show what tasks of data management and representation these methods might be able to tackle and when and how they might interleave towards a more collaborative AI Data Management. We conclude with directions for future work.
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 | 0.003 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.004 |
| Scholarly communication | 0.006 | 0.006 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.002 | 0.002 |
| 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".