{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PUGXW6BVQW5LJBJ7CSZPVDBR5F","short_pith_number":"pith:PUGXW6BV","schema_version":"1.0","canonical_sha256":"7d0d7b783585bab4853f14b2fa8c31e943a18cc5bcfc031fc5d6bcd041072af9","source":{"kind":"arxiv","id":"2404.11025","version":3},"attestation_state":"computed","paper":{"title":"NeuroHash: A Hyperdimensional Neuro-Symbolic Framework for Spatially-Aware Image Hashing and Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mohsen Imani, Ryozo Masukawa, Sanggeon Yun, Sungheon Jeong","submitted_at":"2024-04-17T03:01:47Z","abstract_excerpt":"Customizable image retrieval from large datasets remains a critical challenge, particularly when preserving spatial relationships within images. Traditional hashing methods, primarily based on deep learning, often fail to capture spatial information adequately and lack transparency. In this paper, we introduce NeuroHash, a novel neuro-symbolic framework leveraging Hyperdimensional Computing (HDC) to enable highly customizable, spatially-aware image retrieval. NeuroHash combines pre-trained deep neural network models with HDC-based symbolic models, allowing for flexible manipulation of hash val"},"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":"2404.11025","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-17T03:01:47Z","cross_cats_sorted":[],"title_canon_sha256":"64cec65f3d47ffdbd4bf0d846125c59be2ee8e9e3564ea0cac2d036d2484fc35","abstract_canon_sha256":"1636a9b0ab56888c2c833b92ee08ed19e94ef056a6426b4c7de19a1afcee9eda"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:52.670093Z","signature_b64":"JwH994NQ8qp/1L+4W+htOhS4xR8lKW/oQApZl3f1CMxZR6RBYGbWqydQzVTap6ZvpAPSIamop+nbRXfcO2iNDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d0d7b783585bab4853f14b2fa8c31e943a18cc5bcfc031fc5d6bcd041072af9","last_reissued_at":"2026-07-05T08:21:52.669648Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:52.669648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NeuroHash: A Hyperdimensional Neuro-Symbolic Framework for Spatially-Aware Image Hashing and Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mohsen Imani, Ryozo Masukawa, Sanggeon Yun, Sungheon Jeong","submitted_at":"2024-04-17T03:01:47Z","abstract_excerpt":"Customizable image retrieval from large datasets remains a critical challenge, particularly when preserving spatial relationships within images. Traditional hashing methods, primarily based on deep learning, often fail to capture spatial information adequately and lack transparency. In this paper, we introduce NeuroHash, a novel neuro-symbolic framework leveraging Hyperdimensional Computing (HDC) to enable highly customizable, spatially-aware image retrieval. NeuroHash combines pre-trained deep neural network models with HDC-based symbolic models, allowing for flexible manipulation of hash val"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.11025","kind":"arxiv","version":3},"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/2404.11025/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":"2404.11025","created_at":"2026-07-05T08:21:52.669708+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.11025v3","created_at":"2026-07-05T08:21:52.669708+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.11025","created_at":"2026-07-05T08:21:52.669708+00:00"},{"alias_kind":"pith_short_12","alias_value":"PUGXW6BVQW5L","created_at":"2026-07-05T08:21:52.669708+00:00"},{"alias_kind":"pith_short_16","alias_value":"PUGXW6BVQW5LJBJ7","created_at":"2026-07-05T08:21:52.669708+00:00"},{"alias_kind":"pith_short_8","alias_value":"PUGXW6BV","created_at":"2026-07-05T08:21:52.669708+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.14612","citing_title":"Exploiting Boosting in Hyperdimensional Computing for Enhanced Reliability in Healthcare","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PUGXW6BVQW5LJBJ7CSZPVDBR5F","json":"https://pith.science/pith/PUGXW6BVQW5LJBJ7CSZPVDBR5F.json","graph_json":"https://pith.science/api/pith-number/PUGXW6BVQW5LJBJ7CSZPVDBR5F/graph.json","events_json":"https://pith.science/api/pith-number/PUGXW6BVQW5LJBJ7CSZPVDBR5F/events.json","paper":"https://pith.science/paper/PUGXW6BV"},"agent_actions":{"view_html":"https://pith.science/pith/PUGXW6BVQW5LJBJ7CSZPVDBR5F","download_json":"https://pith.science/pith/PUGXW6BVQW5LJBJ7CSZPVDBR5F.json","view_paper":"https://pith.science/paper/PUGXW6BV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.11025&json=true","fetch_graph":"https://pith.science/api/pith-number/PUGXW6BVQW5LJBJ7CSZPVDBR5F/graph.json","fetch_events":"https://pith.science/api/pith-number/PUGXW6BVQW5LJBJ7CSZPVDBR5F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PUGXW6BVQW5LJBJ7CSZPVDBR5F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PUGXW6BVQW5LJBJ7CSZPVDBR5F/action/storage_attestation","attest_author":"https://pith.science/pith/PUGXW6BVQW5LJBJ7CSZPVDBR5F/action/author_attestation","sign_citation":"https://pith.science/pith/PUGXW6BVQW5LJBJ7CSZPVDBR5F/action/citation_signature","submit_replication":"https://pith.science/pith/PUGXW6BVQW5LJBJ7CSZPVDBR5F/action/replication_record"}},"created_at":"2026-07-05T08:21:52.669708+00:00","updated_at":"2026-07-05T08:21:52.669708+00:00"}