MétaCan
Menu
Back to cohort
Record W7081965627 · doi:10.11159/icbb25.161

Paperparser: A Bioinformatic Tool That Synthesizes Scientific Literature through Advanced AI Techniques, Enhancing Scholarly Insights While Mimicking Human-Like Expression

2025· article· en· W7081965627 on OpenAlexvenueno aff

Bibliographic record

VenueProceedings of the World Congress on New Technologies · 2025
Typearticle
Languageen
FieldComputer Science
TopicGeochemistry and Geologic Mapping
Canadian institutionsnot available
Fundersnot available
KeywordsExpression (computer science)Scientific literatureScientific discoverySociology of scientific knowledge

Abstract

fetched live from OpenAlex

In this output-obsessed era, as scientific publishing continues its exponential growth, we've unthinkingly created a paradox: the cumulative advancement of knowledge by humanity now threatens to drive us all into information overload.Into the breach steps, PaperParser, a bioinformatic conductor crafted to gap this mental chasm.At a high level, PaperParser leverages Scrapy's raw extraction strength to crawl PubMed articles, combines this rich knowledge stream with the abstractive summarization ability of the SciLitLLM-14B.It's in the tool's layered construction, however-combining RAG methodologies, an autonomous Read-Eval-Print Loop (REPL) agent and Large Language Models-that the system's complexity truly emerges.By following users' queries fluently, PaperParser keeps dynamically grouping cohorts of relevant articles that come out from the huge number of articles of the PubMed repository.But the path from data to insight is anything but a straight one: initial corpora is refined through FAISS indexing for fast, relevance-weighted passage retrieval.Drafts are shaped with GPT-40, powered by RAG retrievers that lash generative capability to the evidentiary backbone of a bespoke vector emporium.Further growth of these drafts requires nothing more than an agile AI agent given the reins of GPT-4.1 inside of a Python REPL skeleton.This agile editorial loop yields semantic accuracy as well as emergent clarity.And then, the 'humanization' phase.Here, OpenAI's o3-mini-2025-01-31 is deftly tuned using a Prompt Engineering interface by invoking stylistic signal harvested from target author exemplars through LangChain.PaperParser does not speak as a pure automaton, but as an intermediary, reconciling machine processing speed with a thoughtful, human-touched expression.It allows academics to go beyond mindless reading, shifting their focus to innovative interpretation and critique.We hope to extend this to paywalled periodicals and to perform source relevance-weighting-a further step towards a more discerning and contextsensitive literature navigator.In conclusion: PaperParser represents a new form of scientific intelligence enhancement.

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 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)0.000
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Scholarly communication
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: Bench or experimental
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.286
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.002
Science and technology studies0.0010.000
Scholarly communication0.0020.004
Open science0.0040.002
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

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 head0.013
GPT teacher head0.243
Teacher spread0.230 · 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

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designBench or experimental
Domainnot available
GenreEmpirical

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".

Quick stats

Citations1
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueProceedings of the World Congress on New TechnologiesSame topicGeochemistry and Geologic MappingFrench-language works237,207