{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XCPUAQY5ABZIBE7HJISFHTJ7PL","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":"f9be6a8642321a58c9d97726003997e0ab537e6058494ce39f94a4f6c5adefeb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-07-03T15:53:12Z","title_canon_sha256":"df1c1e37720f0828000adaa3b7be571901273f54acd99bb12ea075a64ab82352"},"schema_version":"1.0","source":{"id":"2607.03440","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.03440","created_at":"2026-07-07T02:17:46Z"},{"alias_kind":"arxiv_version","alias_value":"2607.03440v1","created_at":"2026-07-07T02:17:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03440","created_at":"2026-07-07T02:17:46Z"},{"alias_kind":"pith_short_12","alias_value":"XCPUAQY5ABZI","created_at":"2026-07-07T02:17:46Z"},{"alias_kind":"pith_short_16","alias_value":"XCPUAQY5ABZIBE7H","created_at":"2026-07-07T02:17:46Z"},{"alias_kind":"pith_short_8","alias_value":"XCPUAQY5","created_at":"2026-07-07T02:17:46Z"}],"graph_snapshots":[{"event_id":"sha256:0956f1c5fbc94224fc9fcff5da8b205e88a6731d0d5ce966634417eb40852056","target":"graph","created_at":"2026-07-07T02:17:46Z","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/2607.03440/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Digitized historical archives are large, heterogeneous cultural heritage repositories, but access methods for such archives face challenges such as noisy optical character recognition (OCR) output and rigid keyword-based retrieval, which limit retrieval quality. In this work, we present an end-to-end archival processing and retrieval framework that integrates large language models (LLMs) into the archival pipeline. Our system introduces two core components: (i) an LLM-based OCR refinement module that improves text quality, and (ii) a semantic retrieval and cross-encoder reranking pipeline supp","authors_text":"Alexis Erne, Faruk Zahiragic, Hayman Lotfy, Michalis Vlachos, Min-Yen Kan, Stergios Konstantinidis","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-07-03T15:53:12Z","title":"Improving Access to Historical Archives with Real-time RAG-based Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03440","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":"sha256:9e66f3f9867d545f3ed001190d9990924b4c737955a719e88db3fdabfd9d344d","target":"record","created_at":"2026-07-07T02:17:46Z","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":"f9be6a8642321a58c9d97726003997e0ab537e6058494ce39f94a4f6c5adefeb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-07-03T15:53:12Z","title_canon_sha256":"df1c1e37720f0828000adaa3b7be571901273f54acd99bb12ea075a64ab82352"},"schema_version":"1.0","source":{"id":"2607.03440","kind":"arxiv","version":1}},"canonical_sha256":"b89f40431d00728093e74a2453cd3f7acfa8ad343de0b075126ec26fdf83187a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b89f40431d00728093e74a2453cd3f7acfa8ad343de0b075126ec26fdf83187a","first_computed_at":"2026-07-07T02:17:46.914525Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:17:46.914525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mMs9L7pnocCriJ06GI5GVzXkvUZAfP6XozCHZQVSPnSX5Gnjt2Dh/n8kP3A7WK/1JvdkW/yt5utHRen7LqE9CQ==","signature_status":"signed_v1","signed_at":"2026-07-07T02:17:46.915132Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.03440","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e66f3f9867d545f3ed001190d9990924b4c737955a719e88db3fdabfd9d344d","sha256:0956f1c5fbc94224fc9fcff5da8b205e88a6731d0d5ce966634417eb40852056"],"state_sha256":"7c7a6fb2fe4486237a0e510ddbdca5d0d3a5120b83425c0c1bd4016c280eaab4"}