{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RRBHMRJWEPRSG64AWXHOETSFL4","short_pith_number":"pith:RRBHMRJW","schema_version":"1.0","canonical_sha256":"8c4276453623e3237b80b5cee24e455f165f5b16eda518b30c1634f2c6578cd1","source":{"kind":"arxiv","id":"2408.09869","version":5},"attestation_state":"computed","paper":{"title":"Docling Technical Report","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.SE"],"primary_cat":"cs.CL","authors_text":"Ahmed Nassar, Cesar Berrospi Ramis, Christoph Auer, Fabian Lindlbauer, Ingmar Meijer, Kasper Dinkla, Lokesh Mishra, Lucas Morin, Maksym Lysak, Matteo Omenetti, Michele Dolfi, Nikolaos Livathinos, Panos Vagenas, Peter W. J. Staar, Rafael Teixeira de Lima, Shubham Gupta, Valery Weber, Viktor Kuropiatnyk, Yusik Kim","submitted_at":"2024-08-19T10:20:06Z","abstract_excerpt":"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."},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2408.09869","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-19T10:20:06Z","cross_cats_sorted":["cs.CV","cs.SE"],"title_canon_sha256":"b0ed6f7b1824dd10bc7539131272d463ed1441a9dbff0ef4ffcd7ddff87a1a4c","abstract_canon_sha256":"d7a92046ece81e457fc96b5761bdea9b06fd732ac1e8ebfdd4af6c2496b62b1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:52.783112Z","signature_b64":"npNZ0xhw7006EYj3W15T3+JPfTXV8RbQlMRu5JTHOhJXiYlnmPDU1wZdSe58U1x2pb/gPX7KqmHO5ry+a7MKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c4276453623e3237b80b5cee24e455f165f5b16eda518b30c1634f2c6578cd1","last_reissued_at":"2026-07-05T09:45:52.782656Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:52.782656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Docling Technical Report","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.SE"],"primary_cat":"cs.CL","authors_text":"Ahmed Nassar, Cesar Berrospi Ramis, Christoph Auer, Fabian Lindlbauer, Ingmar Meijer, Kasper Dinkla, Lokesh Mishra, Lucas Morin, Maksym Lysak, Matteo Omenetti, Michele Dolfi, Nikolaos Livathinos, Panos Vagenas, Peter W. J. Staar, Rafael Teixeira de Lima, Shubham Gupta, Valery Weber, Viktor Kuropiatnyk, Yusik Kim","submitted_at":"2024-08-19T10:20:06Z","abstract_excerpt":"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."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09869","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2408.09869/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2408.09869","created_at":"2026-07-05T09:45:52.782711+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.09869v5","created_at":"2026-07-05T09:45:52.782711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09869","created_at":"2026-07-05T09:45:52.782711+00:00"},{"alias_kind":"pith_short_12","alias_value":"RRBHMRJWEPRS","created_at":"2026-07-05T09:45:52.782711+00:00"},{"alias_kind":"pith_short_16","alias_value":"RRBHMRJWEPRSG64A","created_at":"2026-07-05T09:45:52.782711+00:00"},{"alias_kind":"pith_short_8","alias_value":"RRBHMRJW","created_at":"2026-07-05T09:45:52.782711+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06170","citing_title":"The Documentation and Traceability Burden of the Indian EV Transition","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2606.27316","citing_title":"LLM-Based Examination of Eligibility Criteria from Securities Prospectuses at the German Central Bank","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07401","citing_title":"RealDocBench: A Benchmark for Field-Level QA and Layout Understanding on Real-World Regulated Documents","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25030","citing_title":"MimirRAG: A Multi-Agent RAG Framework for Financial Data Retrieval with Metadata Integration","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27446","citing_title":"Causal Connections: Leveraging Multilingual Fine-Tuning for Financial QA@FinCausal 2026","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00224","citing_title":"An AI-ready, Polarized Electron-Positron Collision Dataset","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27316","citing_title":"LLM-Based Examination of Eligibility Criteria from Securities Prospectuses at the German Central Bank","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12623","citing_title":"DocAtlas: Multilingual Document Understanding Across 80+ Languages","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18818","citing_title":"Operationalizing Document AI: A Microservice Architecture for OCR and LLM Pipelines in Production","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2510.05038","citing_title":"Guided Query Refinement: Multimodal Hybrid Retrieval with Test-Time Optimization","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2512.00127","citing_title":"Generating Verifiable Chain of Thoughts from Exection-Traces","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22755","citing_title":"RADIANT-LLM: an Agentic Retrieval Augmented Generation Framework for Reliable Decision Support in Safety-Critical Nuclear Engineering","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04948","citing_title":"From PDF to RAG-Ready: Evaluating Document Conversion Frameworks for Domain-Specific Question Answering","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26382","citing_title":"Benchmarking Complex Multimodal Document Processing Pipelines: A Unified Evaluation Framework for Enterprise AI","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26835","citing_title":"HalluCiteChecker: A Lightweight Toolkit for Hallucinated Citation Detection and Verification in the Era of AI Scientists","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10296","citing_title":"Qwen Goes Brrr: Off-the-Shelf RAG for Ukrainian Multi-Domain Document Understanding","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10296","citing_title":"Qwen Goes Brrr: Off-the-Shelf RAG for Ukrainian Multi-Domain Document Understanding","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00803","citing_title":"Can Coding Agents Reproduce Findings in Computational Materials Science?","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RRBHMRJWEPRSG64AWXHOETSFL4","json":"https://pith.science/pith/RRBHMRJWEPRSG64AWXHOETSFL4.json","graph_json":"https://pith.science/api/pith-number/RRBHMRJWEPRSG64AWXHOETSFL4/graph.json","events_json":"https://pith.science/api/pith-number/RRBHMRJWEPRSG64AWXHOETSFL4/events.json","paper":"https://pith.science/paper/RRBHMRJW"},"agent_actions":{"view_html":"https://pith.science/pith/RRBHMRJWEPRSG64AWXHOETSFL4","download_json":"https://pith.science/pith/RRBHMRJWEPRSG64AWXHOETSFL4.json","view_paper":"https://pith.science/paper/RRBHMRJW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.09869&json=true","fetch_graph":"https://pith.science/api/pith-number/RRBHMRJWEPRSG64AWXHOETSFL4/graph.json","fetch_events":"https://pith.science/api/pith-number/RRBHMRJWEPRSG64AWXHOETSFL4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RRBHMRJWEPRSG64AWXHOETSFL4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RRBHMRJWEPRSG64AWXHOETSFL4/action/storage_attestation","attest_author":"https://pith.science/pith/RRBHMRJWEPRSG64AWXHOETSFL4/action/author_attestation","sign_citation":"https://pith.science/pith/RRBHMRJWEPRSG64AWXHOETSFL4/action/citation_signature","submit_replication":"https://pith.science/pith/RRBHMRJWEPRSG64AWXHOETSFL4/action/replication_record"}},"created_at":"2026-07-05T09:45:52.782711+00:00","updated_at":"2026-07-05T09:45:52.782711+00:00"}