paper_id | string | ✓ | Unique fact-based identifier for the paper, prefixed with “PAP” (e.g. PAP-XXXXXXXX). |
id_doi | string | | Digital Object Identifier (DOI). |
id_openalex | string | | OpenAlex identifier. |
id_pmid | string | | PubMed identifier (PMID). |
id_pmcid | string | | PubMed Central identifier (PMCID). |
slug | string | | URL-friendly identifier derived from the English display title. |
title | string | | Original title in source language. |
title_en | string | | English translation of the original title. |
title_display | string | | Shortened original-language title. |
title_display_en | string | | Shortened English title. |
abstract | string | | Full plain-text abstract in original language. |
abstract_en | string | | English-translated abstract. |
abstract_index | string | | Positional word index of the abstract (copyright-safe). |
paper_type | string | | Categorical type (journal-article, conference-paper, preprint, book-chapter). |
paper_language | string | | ISO 639-1 two-letter language code. |
paper_version | string | | Version identifier (e.g. “v1”, “v2”). |
paper_license | string | | License (e.g. CC-BY, CC-BY-NC). |
paper_landing_page_url | string | | URL of the paper’s official landing page. |
paper_pdf_url | string | | Direct URL to the open-access PDF. |
paper_retracted | boolean | | True if the paper has been retracted. |
paper_paratext | boolean | | True if classified as paratext (editorial note, front matter). |
ginc_paper | boolean | | True if relevant to the GINC domain. |
publication_date | time | | Full publication date. |
embedding_title_en | string | | Vector embedding of the English title. |
embedding_title_abstract_en | string | | Vector embedding of title + abstract. |