MétaCan
Menu
Back to cohort

HouseOfTheDragonQA: Open-Domain Long-form Context-Aware QA Pairs for TV Series

2024· article· en· W4410086952 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldSocial Sciences
TopicMultimedia Communication and Technology
Canadian institutionsToronto Metropolitan University
Fundersnot available
KeywordsSeries (stratigraphy)Computer scienceContext (archaeology)Domain (mathematical analysis)Open domainInformation retrievalMathematicsHistory

Abstract

fetched live from OpenAlex

This paper proposes a novel approach to develop an open-domain and long-form Over-The-Top (OTT) Question-Answering (QA) dataset, HouseOfTheDragonQA, specifically oriented to the “House of the Dragon” TV series. Most of the existing QA datasets have focused on short, fact-based answers sourced almost solely from Wikipedia articles-bereft of the depth and contextual richness required for sophisticated narrative understanding. Our dataset is curated using legally admissible and high-quality open-domain sources to combine full episode summaries from HBO and fandom wiki websites, user reviews from IMDb and Rotten Tomatoes, and structured data from repositories such as WikiData. The dataset provides a multidimensional context, capturing complex character dynamics and plot developments from these varied sources. On equal terms, rigorous data preprocessing and filtering methods ensure that only meaningful and non-spam, unbiased reviews will be present in this enhanced dataset. The long-form answers generated from this enriched context provide comprehensive insights, making this dataset particularly valuable for improving conversational AI, narrative analysis, sentiment analysis, summarization techniques, and relation extraction. Comparative analysis with state-of-the-art QA datasets like SQuAD 2.0, TriviaQA, and Natural Questions (NQ) demonstrates the unique advantages of our dataset in terms of contextual complexity and answer length. The inclusion of detailed reviews offers added layers of audience sentiment and narrative interpretation, setting a new benchmark for quality in domain-specific QA tasks. Our effort enables advanced comprehension of entertainment-industry content and paves the way for more knowing and creative AI-driven interactions within digital media settings.

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.

Full frame distilled prediction

Teacher imitation

Not 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.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesInsufficient payload (model declined to judge)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.935
Threshold uncertainty score0.999

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0010.000
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0020.000

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.

Opus teacher head0.057
GPT teacher head0.372
Teacher spread0.315 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Quick stats

Citations1
Published2024
Admission routes1
Has abstractyes

Explore more

Same topicMultimedia Communication and TechnologyFrench-language works237,207