{"work":{"id":"6a3d465e-7b27-4f5e-b63d-a4948b7bc866","openalex_id":"https://openalex.org/W4402950921","doi":"10.48550/arxiv.2408.09869","arxiv_id":"2408.09869","raw_key":null,"title":"Docling Technical Report","authors":null,"authors_text":"Docling Technical Report , author =","year":2024,"venue":"cs.CL","abstract":"This technical report introduces Docling, an easy to use, self-contained, MIT-licensed open-source package for PDF document conversion. It is powered by state-of-the-art specialized AI models for layout analysis (DocLayNet) and table structure recognition (TableFormer), and runs efficiently on commodity hardware in a small resource budget. The code interface allows for easy extensibility and addition of new features and models.","external_url":"https://arxiv.org/abs/2408.09869","cited_by_count":8,"metadata_source":"pith","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":"2408.09869","created_at":"2026-05-11T15:46:48.448015+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":false,"display_title":"arXiv preprint arXiv:2408.09869 , year=","render_title":"arXiv preprint arXiv:2408.09869 , year="},"hub":{"state":{"work_id":"6a3d465e-7b27-4f5e-b63d-a4948b7bc866","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":16,"external_cited_by_count":8,"distinct_field_count":8,"first_pith_cited_at":"2025-10-06T17:12:53+00:00","last_pith_cited_at":"2026-07-07T11:48:14+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-21T20:40:00.537192+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"method","n":2},{"context_role":"background","n":1}],"polarity_counts":[{"context_polarity":"use_method","n":2},{"context_polarity":"background","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}