{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VGQD7TC34BWXYZUPSRVHU4YBMX","short_pith_number":"pith:VGQD7TC3","schema_version":"1.0","canonical_sha256":"a9a03fcc5be06d7c668f946a7a730165f64980bd540606d4b5d7b89e78df8c93","source":{"kind":"arxiv","id":"2608.01147","version":1},"attestation_state":"computed","paper":{"title":"UniHEAR: Unified Heterogeneous-Source Attentive Retrieval for Knowledge-Based Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.IR","authors_text":"Ganzhong Luo, Hanyong Wang, Menglong Yang, Shuyu Zheng, Yang Ren","submitted_at":"2026-08-02T10:57:53Z","abstract_excerpt":"Knowledge-Based Visual Question Answering (KB-VQA) requires retrieving relevant entity knowledge from external sources to answer visually grounded questions. Existing retrieval-augmented systems suffer from two critical limitations. First, relying on a single retrieval modality creates a Single-Source Retrieval Bottleneck, missing ground-truth entities that are only accessible through complementary sources. Second, dual-tower pointwise rerankers suffer from Retrieval-Source-Blind Reranking, as they overlook retrieval origins and candidate-level retrieval priors, leading to redundant modality r"},"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":"2608.01147","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-08-02T10:57:53Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"b4de068da4f949ef68687c463af3cf76696856ae79301a3c3a1665a4a4f4081c","abstract_canon_sha256":"d9ddd8cbad3fd1913c2079d519ab0185542bd3b6dfa51f2a88fee36709501755"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T01:57:05.978219Z","signature_b64":"pPx7dmZ2r7l+K5Av++Z0BjWzCeS0jqvXXO450P32fmd1RgA+QOTOAFYgCghhmBkzSSPNb3i6MdiMTFSeMrPJCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9a03fcc5be06d7c668f946a7a730165f64980bd540606d4b5d7b89e78df8c93","last_reissued_at":"2026-08-04T01:57:05.976705Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T01:57:05.976705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniHEAR: Unified Heterogeneous-Source Attentive Retrieval for Knowledge-Based Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.IR","authors_text":"Ganzhong Luo, Hanyong Wang, Menglong Yang, Shuyu Zheng, Yang Ren","submitted_at":"2026-08-02T10:57:53Z","abstract_excerpt":"Knowledge-Based Visual Question Answering (KB-VQA) requires retrieving relevant entity knowledge from external sources to answer visually grounded questions. Existing retrieval-augmented systems suffer from two critical limitations. First, relying on a single retrieval modality creates a Single-Source Retrieval Bottleneck, missing ground-truth entities that are only accessible through complementary sources. Second, dual-tower pointwise rerankers suffer from Retrieval-Source-Blind Reranking, as they overlook retrieval origins and candidate-level retrieval priors, leading to redundant modality r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01147","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/2608.01147/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":"2608.01147","created_at":"2026-08-04T01:57:05.978029+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01147v1","created_at":"2026-08-04T01:57:05.978029+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01147","created_at":"2026-08-04T01:57:05.978029+00:00"},{"alias_kind":"pith_short_12","alias_value":"VGQD7TC34BWX","created_at":"2026-08-04T01:57:05.978029+00:00"},{"alias_kind":"pith_short_16","alias_value":"VGQD7TC34BWXYZUP","created_at":"2026-08-04T01:57:05.978029+00:00"},{"alias_kind":"pith_short_8","alias_value":"VGQD7TC3","created_at":"2026-08-04T01:57:05.978029+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/VGQD7TC34BWXYZUPSRVHU4YBMX","json":"https://pith.science/pith/VGQD7TC34BWXYZUPSRVHU4YBMX.json","graph_json":"https://pith.science/api/pith-number/VGQD7TC34BWXYZUPSRVHU4YBMX/graph.json","events_json":"https://pith.science/api/pith-number/VGQD7TC34BWXYZUPSRVHU4YBMX/events.json","paper":"https://pith.science/paper/VGQD7TC3"},"agent_actions":{"view_html":"https://pith.science/pith/VGQD7TC34BWXYZUPSRVHU4YBMX","download_json":"https://pith.science/pith/VGQD7TC34BWXYZUPSRVHU4YBMX.json","view_paper":"https://pith.science/paper/VGQD7TC3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01147&json=true","fetch_graph":"https://pith.science/api/pith-number/VGQD7TC34BWXYZUPSRVHU4YBMX/graph.json","fetch_events":"https://pith.science/api/pith-number/VGQD7TC34BWXYZUPSRVHU4YBMX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VGQD7TC34BWXYZUPSRVHU4YBMX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VGQD7TC34BWXYZUPSRVHU4YBMX/action/storage_attestation","attest_author":"https://pith.science/pith/VGQD7TC34BWXYZUPSRVHU4YBMX/action/author_attestation","sign_citation":"https://pith.science/pith/VGQD7TC34BWXYZUPSRVHU4YBMX/action/citation_signature","submit_replication":"https://pith.science/pith/VGQD7TC34BWXYZUPSRVHU4YBMX/action/replication_record"}},"created_at":"2026-08-04T01:57:05.978029+00:00","updated_at":"2026-08-04T01:57:05.978029+00:00"}