{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:A6MXJY6TX7NHWBH2XOHXUL2JZW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e6c0db1b57a9945b0c4ccec1ca37dcf62a8c0bfab35ec80570297c6d82b0b31f","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T20:33:33Z","title_canon_sha256":"15f25bab1fa7334ddbd1e1c5d5887a11650fab28449ec59639f32e8640aa9d95"},"schema_version":"1.0","source":{"id":"2412.15262","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15262","created_at":"2026-07-05T09:52:00Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15262v1","created_at":"2026-07-05T09:52:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15262","created_at":"2026-07-05T09:52:00Z"},{"alias_kind":"pith_short_12","alias_value":"A6MXJY6TX7NH","created_at":"2026-07-05T09:52:00Z"},{"alias_kind":"pith_short_16","alias_value":"A6MXJY6TX7NHWBH2","created_at":"2026-07-05T09:52:00Z"},{"alias_kind":"pith_short_8","alias_value":"A6MXJY6T","created_at":"2026-07-05T09:52:00Z"}],"graph_snapshots":[{"event_id":"sha256:3d44a6b967d67248f423c0fd2db782b02ef07d101b6951f8dd246298e88f5e20","target":"graph","created_at":"2026-07-05T09:52:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.15262/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Arnau Perez, Xavier Vizcaino","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T20:33:33Z","title":"Advanced ingestion process powered by LLM parsing for RAG system"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15262","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7562b1369bae3c6b3ff23644c0db455a87a4d47862ad95ae648c94a424b88b39","target":"record","created_at":"2026-07-05T09:52:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e6c0db1b57a9945b0c4ccec1ca37dcf62a8c0bfab35ec80570297c6d82b0b31f","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T20:33:33Z","title_canon_sha256":"15f25bab1fa7334ddbd1e1c5d5887a11650fab28449ec59639f32e8640aa9d95"},"schema_version":"1.0","source":{"id":"2412.15262","kind":"arxiv","version":1}},"canonical_sha256":"079974e3d3bfda7b04fabb8f7a2f49cdadab0f334aeff63dba961a3c3055c042","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"079974e3d3bfda7b04fabb8f7a2f49cdadab0f334aeff63dba961a3c3055c042","first_computed_at":"2026-07-05T09:52:00.716148Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:52:00.716148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wqEuyxCX2cvqldtfuckmUVve+Ctq8ln9aZkrHvrQhG0on9q9K+RA/kCd+Gal7LcUq5mno+nRW3K6ThnSz5zyBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:52:00.716614Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.15262","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7562b1369bae3c6b3ff23644c0db455a87a4d47862ad95ae648c94a424b88b39","sha256:3d44a6b967d67248f423c0fd2db782b02ef07d101b6951f8dd246298e88f5e20"],"state_sha256":"7cbbddfbfcd805bd3e2da873c5dc157a1cdad44153c5082e3fc06d9a089efa60"}