Defining personalized concepts for XBRL using iPAD‐drawn fuzzy sets
Bibliographic record
Abstract
Summary An efficient and effective analysis of business data requires a better understanding of what the data represents, and to what degree. A human‐like way of accomplishing that without being too detailed yet learning more about data content is to summarize and map the data into concepts familiar to a person performing analysis. Processes of summarization help identify the most essential facts that are embedded in the data. All this is of significant importance for analysis of large amounts of business data required to make good and sound financial decisions. There are two aspects enabling more comprehensive yet easier processing of data: a standardized representation format of financial data; and a human‐friendly way of defining concepts and using them for building personalized models representing processing data. The first of the aspects has been addressed by the eXtensible Business Reporting Language (XBRL)—a standardized format of defining, representing and exchanging corporate and financial information. The second aspect is related to providing individuals with the ability to gain understanding of data content via determining a degree of truth of statements summarizing data based on their own perception of concepts they are looking for. In this paper, we introduce a tablet application—Tablet‐based input of Fuzzy Sets (TiFS)—and demonstrate its usefulness for entering personalized definitions of concepts and terms that enable a quick analysis of financial data. Such analysis means utilization of soft queries and operations of aggregation that extract and summarize the data and present it in a form familiar to analysts. The application allows for defining concepts and terms with ‘finger‐made’ drawings representing a person's perception of concepts. Further, these definitions are used to build summarization statements for exploring XBRL data. They are equipped with ‘drawn’ definitions of linguistic terms (e.g. LARGE, SMALL, FAST) and linguistic quantifiers (e.g. ALL, MOSTLY), and enable summarization of data content from the perspective of a user's interests. The ‘drawn’ linguistic terms and quantifiers represent membership functions of fuzzy sets. Utilization of fuzzy sets allows for performing operations of data summarization in a human‐like way. The application of TiFS illustrates ease of inputting personalized definitions of concepts and their influence on the interpretation of data. This introduces aspects of personalization and adaptation of artificial intelligence systems to perceptions and views of individuals. The proposed application is used to perform a basic analysis of an XBRL document.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.011 | 0.002 |
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".