{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HTJ7KKLXIOZAVYT64VZMPUFELM","short_pith_number":"pith:HTJ7KKLX","schema_version":"1.0","canonical_sha256":"3cd3f5297743b20ae27ee572c7d0a45b31275faffbd13316f1a3b0baf3e7f081","source":{"kind":"arxiv","id":"2501.17887","version":1},"attestation_state":"computed","paper":{"title":"Docling: An Efficient Open-Source Toolkit for AI-driven Document Conversion","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, Ingmar Meijer, Kasper Dinkla, 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":"2025-01-27T19:40:00Z","abstract_excerpt":"We introduce Docling, an easy-to-use, self-contained, MIT-licensed, open-source toolkit for document conversion, that can parse several types of popular document formats into a unified, richly structured representation. 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. Docling is released as a Python package and can be used as a Python API or as a CLI tool. Docling's modular architecture and efficient document representation make it easy to"},"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":"2501.17887","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T19:40:00Z","cross_cats_sorted":["cs.CV","cs.SE"],"title_canon_sha256":"3a533cdf1ddbef43dcce20f1b559df0696a004301a6fc3b9726536b05e28de5f","abstract_canon_sha256":"4775dd120aaa455e8e7ed7c130c4d4b31f4977ba02b4ec1e3a2c95b74762aa6f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:07:03.583393Z","signature_b64":"VniSevjJ8olDRY5SEoqBXtu6RzKXL9O3WtrBAyEZPJnbxSnux5g0KASTHPewaKAwOU1OLchqtycr63mCBfpqBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3cd3f5297743b20ae27ee572c7d0a45b31275faffbd13316f1a3b0baf3e7f081","last_reissued_at":"2026-07-05T10:07:03.582890Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:07:03.582890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Docling: An Efficient Open-Source Toolkit for AI-driven Document Conversion","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, Ingmar Meijer, Kasper Dinkla, 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":"2025-01-27T19:40:00Z","abstract_excerpt":"We introduce Docling, an easy-to-use, self-contained, MIT-licensed, open-source toolkit for document conversion, that can parse several types of popular document formats into a unified, richly structured representation. 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. Docling is released as a Python package and can be used as a Python API or as a CLI tool. Docling's modular architecture and efficient document representation make it easy to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.17887","kind":"arxiv","version":1},"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/2501.17887/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":"2501.17887","created_at":"2026-07-05T10:07:03.582952+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.17887v1","created_at":"2026-07-05T10:07:03.582952+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.17887","created_at":"2026-07-05T10:07:03.582952+00:00"},{"alias_kind":"pith_short_12","alias_value":"HTJ7KKLXIOZA","created_at":"2026-07-05T10:07:03.582952+00:00"},{"alias_kind":"pith_short_16","alias_value":"HTJ7KKLXIOZAVYT6","created_at":"2026-07-05T10:07:03.582952+00:00"},{"alias_kind":"pith_short_8","alias_value":"HTJ7KKLX","created_at":"2026-07-05T10:07:03.582952+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05658","citing_title":"Agent-Orchestrated Adaptive RAG: A Comparative Study on Structured and Multi-Hop Retrieval","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02915","citing_title":"Any2Poster: Any-Source Poster Generation Across Modalities and Domains","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28365","citing_title":"CAMI: Cost-Aware Agent-Guided Multi-Indexing for Semantic Retrieval","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27978","citing_title":"ABot-OCR Technical Report","ref_index":27,"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":81,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19866","citing_title":"Structured Layout Priors for Robust Out-of-Distribution Visual Document Understanding","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2509.11253","citing_title":"VideoAgent: Personalized Synthesis of Scientific Videos","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22186","citing_title":"MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06179","citing_title":"ARIA: Adaptive Retrieval Intelligence Assistant -- A Multimodal RAG Framework for Domain-Specific Engineering Education","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2603.15118","citing_title":"VAREX: A Benchmark for Multi-Modal Structured Extraction from Documents","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27064","citing_title":"ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12678","citing_title":"No One Knows the State of the Art in Geospatial Foundation Models","ref_index":47,"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":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11969","citing_title":"Narrative-Driven Paper-to-Slide Generation via ArcDeck","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08538","citing_title":"ParseBench: A Document Parsing Benchmark for AI Agents","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04771","citing_title":"MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HTJ7KKLXIOZAVYT64VZMPUFELM","json":"https://pith.science/pith/HTJ7KKLXIOZAVYT64VZMPUFELM.json","graph_json":"https://pith.science/api/pith-number/HTJ7KKLXIOZAVYT64VZMPUFELM/graph.json","events_json":"https://pith.science/api/pith-number/HTJ7KKLXIOZAVYT64VZMPUFELM/events.json","paper":"https://pith.science/paper/HTJ7KKLX"},"agent_actions":{"view_html":"https://pith.science/pith/HTJ7KKLXIOZAVYT64VZMPUFELM","download_json":"https://pith.science/pith/HTJ7KKLXIOZAVYT64VZMPUFELM.json","view_paper":"https://pith.science/paper/HTJ7KKLX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.17887&json=true","fetch_graph":"https://pith.science/api/pith-number/HTJ7KKLXIOZAVYT64VZMPUFELM/graph.json","fetch_events":"https://pith.science/api/pith-number/HTJ7KKLXIOZAVYT64VZMPUFELM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HTJ7KKLXIOZAVYT64VZMPUFELM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HTJ7KKLXIOZAVYT64VZMPUFELM/action/storage_attestation","attest_author":"https://pith.science/pith/HTJ7KKLXIOZAVYT64VZMPUFELM/action/author_attestation","sign_citation":"https://pith.science/pith/HTJ7KKLXIOZAVYT64VZMPUFELM/action/citation_signature","submit_replication":"https://pith.science/pith/HTJ7KKLXIOZAVYT64VZMPUFELM/action/replication_record"}},"created_at":"2026-07-05T10:07:03.582952+00:00","updated_at":"2026-07-05T10:07:03.582952+00:00"}