{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:X4D5MLTQ6FLMST53HEBDPRFZPY","short_pith_number":"pith:X4D5MLTQ","schema_version":"1.0","canonical_sha256":"bf07d62e70f156c94fbb390237c4b97e3c059e7492fc53b1eb349d72122a4922","source":{"kind":"arxiv","id":"2605.29606","version":1},"attestation_state":"computed","paper":{"title":"HiKEY: Hierarchical Multimodal Retrieval for Open-Domain Document Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.AI","authors_text":"Gyuho Shim, Heuiseok Lim, Jaehyung Seo, Jeongbae Park, Joongmin Shin","submitted_at":"2026-05-28T08:42:21Z","abstract_excerpt":"Retrieval-augmented generation (RAG) for document-based Open-domain Question Answering (ODQA) on large-scale industrial corpora faces two critical bottlenecks: routing failure in locating the correct document and evidence fragmentation in integrating scattered information. Existing approaches relying on flat text chunks or page-level images inherently struggle to (i) precisely pinpoint the target document among thousands of candidates and (ii) organically connect multimodal evidence, such as tables and figures, within a limited token budget. To address these challenges, we propose HiKEY, a hie"},"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":"2605.29606","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T08:42:21Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"a62c070f6861f572c592efd52c6f0c925b6c77bc92207c0d28a895e6d4ab018a","abstract_canon_sha256":"e5ae7605f3f0134d66dab84b67f03a8a6e3f4b0c252ccd6ec9d4f224968fd36d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:50.687683Z","signature_b64":"xvn39BzmKwdwqK0XyekTnklfPFnXLB3aor0CrBSAUB1vt25RBIKrwt8yjLZ1t6B2FVtOCXbXxu4TRkZvYrhZAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf07d62e70f156c94fbb390237c4b97e3c059e7492fc53b1eb349d72122a4922","last_reissued_at":"2026-05-29T01:05:50.686967Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:50.686967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HiKEY: Hierarchical Multimodal Retrieval for Open-Domain Document Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.AI","authors_text":"Gyuho Shim, Heuiseok Lim, Jaehyung Seo, Jeongbae Park, Joongmin Shin","submitted_at":"2026-05-28T08:42:21Z","abstract_excerpt":"Retrieval-augmented generation (RAG) for document-based Open-domain Question Answering (ODQA) on large-scale industrial corpora faces two critical bottlenecks: routing failure in locating the correct document and evidence fragmentation in integrating scattered information. Existing approaches relying on flat text chunks or page-level images inherently struggle to (i) precisely pinpoint the target document among thousands of candidates and (ii) organically connect multimodal evidence, such as tables and figures, within a limited token budget. To address these challenges, we propose HiKEY, a hie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29606","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/2605.29606/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":"2605.29606","created_at":"2026-05-29T01:05:50.687062+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29606v1","created_at":"2026-05-29T01:05:50.687062+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29606","created_at":"2026-05-29T01:05:50.687062+00:00"},{"alias_kind":"pith_short_12","alias_value":"X4D5MLTQ6FLM","created_at":"2026-05-29T01:05:50.687062+00:00"},{"alias_kind":"pith_short_16","alias_value":"X4D5MLTQ6FLMST53","created_at":"2026-05-29T01:05:50.687062+00:00"},{"alias_kind":"pith_short_8","alias_value":"X4D5MLTQ","created_at":"2026-05-29T01:05:50.687062+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X4D5MLTQ6FLMST53HEBDPRFZPY","json":"https://pith.science/pith/X4D5MLTQ6FLMST53HEBDPRFZPY.json","graph_json":"https://pith.science/api/pith-number/X4D5MLTQ6FLMST53HEBDPRFZPY/graph.json","events_json":"https://pith.science/api/pith-number/X4D5MLTQ6FLMST53HEBDPRFZPY/events.json","paper":"https://pith.science/paper/X4D5MLTQ"},"agent_actions":{"view_html":"https://pith.science/pith/X4D5MLTQ6FLMST53HEBDPRFZPY","download_json":"https://pith.science/pith/X4D5MLTQ6FLMST53HEBDPRFZPY.json","view_paper":"https://pith.science/paper/X4D5MLTQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29606&json=true","fetch_graph":"https://pith.science/api/pith-number/X4D5MLTQ6FLMST53HEBDPRFZPY/graph.json","fetch_events":"https://pith.science/api/pith-number/X4D5MLTQ6FLMST53HEBDPRFZPY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X4D5MLTQ6FLMST53HEBDPRFZPY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X4D5MLTQ6FLMST53HEBDPRFZPY/action/storage_attestation","attest_author":"https://pith.science/pith/X4D5MLTQ6FLMST53HEBDPRFZPY/action/author_attestation","sign_citation":"https://pith.science/pith/X4D5MLTQ6FLMST53HEBDPRFZPY/action/citation_signature","submit_replication":"https://pith.science/pith/X4D5MLTQ6FLMST53HEBDPRFZPY/action/replication_record"}},"created_at":"2026-05-29T01:05:50.687062+00:00","updated_at":"2026-05-29T01:05:50.687062+00:00"}