Strategies for analyzing the guessing game "Wordle"
Bibliographic record
Abstract
Nowadays, games have become indispensable for people's entertainment. Among them, the five-letter decryption game "world" launched by the New York Times has swept the world. Many players also reported their scores on Twitter. Through these published data, we found some interesting information. According to the information and requirements given by the topic, the table data attached to the topic is preprocessed. Find an exception in the data and delete it. The attributes of a given word are extracted by data encoding. We draw a line graph of the data, observe its trend change and perform curve fitting. The study found that the first half of the curve rose rapidly and the second half fell slowly. The fitting curve function was obtained, and the goodness of fit were 0.9521 and 0.9629, respectively. Using the curve, the quantitative range of results reported on March 1, 2023 is [5805.390,6075.43]. The sensitivity analysis was carried out by changing the four parameters of the fitting curve. The results show that the predicted value is within the reasonable range. Based on the parts of speech classification and the number of letter repeats, we investigate whether they affect the percentage distribution of difficult sentence patterns. Secondly, we optimize the LSTM model based on particle swarm optimization algorithm, and carry out hyperparameter optimization processing to build the PSO-LSTM model. Compared with LSTM, it is found that its model expression is better than that of single LSTM model. The MAPE value of the test set is 1.248, which means the uncertainty is 1.248%, so we have 98.752 percent confidence in the accuracy of the model. The EERIE data were encoded and put into the established PSO-LSTM model, and the correlation percentages were 0.432, 3.631, 19.326, 30.291, 26.954, 14.234 and 5.132, respectively.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.004 | 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".