{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:A6MXJY6TX7NHWBH2XOHXUL2JZW","short_pith_number":"pith:A6MXJY6T","schema_version":"1.0","canonical_sha256":"079974e3d3bfda7b04fabb8f7a2f49cdadab0f334aeff63dba961a3c3055c042","source":{"kind":"arxiv","id":"2412.15262","version":1},"attestation_state":"computed","paper":{"title":"Advanced ingestion process powered by LLM parsing for RAG system","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Arnau Perez, Xavier Vizcaino","submitted_at":"2024-12-16T20:33:33Z","abstract_excerpt":"Retrieval Augmented Generation (RAG) systems struggle with processing multimodal documents of varying structural complexity. This paper introduces a novel multi-strategy parsing approach using LLM-powered OCR to extract content from diverse document types, including presentations and high text density files both scanned or not. The methodology employs a node-based extraction technique that creates relationships between different information types and generates context-aware metadata. By implementing a Multimodal Assembler Agent and a flexible embedding strategy, the system enhances document co"},"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":"2412.15262","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T20:33:33Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"15f25bab1fa7334ddbd1e1c5d5887a11650fab28449ec59639f32e8640aa9d95","abstract_canon_sha256":"e6c0db1b57a9945b0c4ccec1ca37dcf62a8c0bfab35ec80570297c6d82b0b31f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:00.716614Z","signature_b64":"wqEuyxCX2cvqldtfuckmUVve+Ctq8ln9aZkrHvrQhG0on9q9K+RA/kCd+Gal7LcUq5mno+nRW3K6ThnSz5zyBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"079974e3d3bfda7b04fabb8f7a2f49cdadab0f334aeff63dba961a3c3055c042","last_reissued_at":"2026-07-05T09:52:00.716148Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:00.716148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Advanced ingestion process powered by LLM parsing for RAG system","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Arnau Perez, Xavier Vizcaino","submitted_at":"2024-12-16T20:33:33Z","abstract_excerpt":"Retrieval Augmented Generation (RAG) systems struggle with processing multimodal documents of varying structural complexity. This paper introduces a novel multi-strategy parsing approach using LLM-powered OCR to extract content from diverse document types, including presentations and high text density files both scanned or not. The methodology employs a node-based extraction technique that creates relationships between different information types and generates context-aware metadata. By implementing a Multimodal Assembler Agent and a flexible embedding strategy, the system enhances document co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15262","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/2412.15262/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":"2412.15262","created_at":"2026-07-05T09:52:00.716208+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.15262v1","created_at":"2026-07-05T09:52:00.716208+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15262","created_at":"2026-07-05T09:52:00.716208+00:00"},{"alias_kind":"pith_short_12","alias_value":"A6MXJY6TX7NH","created_at":"2026-07-05T09:52:00.716208+00:00"},{"alias_kind":"pith_short_16","alias_value":"A6MXJY6TX7NHWBH2","created_at":"2026-07-05T09:52:00.716208+00:00"},{"alias_kind":"pith_short_8","alias_value":"A6MXJY6T","created_at":"2026-07-05T09:52:00.716208+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.15262","citing_title":"Advanced ingestion process powered by LLM parsing for RAG system","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A6MXJY6TX7NHWBH2XOHXUL2JZW","json":"https://pith.science/pith/A6MXJY6TX7NHWBH2XOHXUL2JZW.json","graph_json":"https://pith.science/api/pith-number/A6MXJY6TX7NHWBH2XOHXUL2JZW/graph.json","events_json":"https://pith.science/api/pith-number/A6MXJY6TX7NHWBH2XOHXUL2JZW/events.json","paper":"https://pith.science/paper/A6MXJY6T"},"agent_actions":{"view_html":"https://pith.science/pith/A6MXJY6TX7NHWBH2XOHXUL2JZW","download_json":"https://pith.science/pith/A6MXJY6TX7NHWBH2XOHXUL2JZW.json","view_paper":"https://pith.science/paper/A6MXJY6T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.15262&json=true","fetch_graph":"https://pith.science/api/pith-number/A6MXJY6TX7NHWBH2XOHXUL2JZW/graph.json","fetch_events":"https://pith.science/api/pith-number/A6MXJY6TX7NHWBH2XOHXUL2JZW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A6MXJY6TX7NHWBH2XOHXUL2JZW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A6MXJY6TX7NHWBH2XOHXUL2JZW/action/storage_attestation","attest_author":"https://pith.science/pith/A6MXJY6TX7NHWBH2XOHXUL2JZW/action/author_attestation","sign_citation":"https://pith.science/pith/A6MXJY6TX7NHWBH2XOHXUL2JZW/action/citation_signature","submit_replication":"https://pith.science/pith/A6MXJY6TX7NHWBH2XOHXUL2JZW/action/replication_record"}},"created_at":"2026-07-05T09:52:00.716208+00:00","updated_at":"2026-07-05T09:52:00.716208+00:00"}