{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4EPRZRCXGLLGP32PDW5KJVDZKS","short_pith_number":"pith:4EPRZRCX","schema_version":"1.0","canonical_sha256":"e11f1cc45732d667ef4f1dbaa4d479549056b3c82ef7ad75d6c5c98a71afea43","source":{"kind":"arxiv","id":"2409.17383","version":1},"attestation_state":"computed","paper":{"title":"VectorSearch: Enhancing Document Retrieval with Semantic Embeddings and Optimized Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB","cs.LG","cs.PF"],"primary_cat":"cs.IR","authors_text":"Dongfang Zhao, Irene Lau, Shubing Yang, Solmaz Seyed Monir","submitted_at":"2024-09-25T21:58:08Z","abstract_excerpt":"Traditional retrieval methods have been essential for assessing document similarity but struggle with capturing semantic nuances. Despite advancements in latent semantic analysis (LSA) and deep learning, achieving comprehensive semantic understanding and accurate retrieval remains challenging due to high dimensionality and semantic gaps. The above challenges call for new techniques to effectively reduce the dimensions and close the semantic gaps. To this end, we propose VectorSearch, which leverages advanced algorithms, embeddings, and indexing techniques for refined retrieval. By utilizing in"},"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":"2409.17383","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-09-25T21:58:08Z","cross_cats_sorted":["cs.AI","cs.DB","cs.LG","cs.PF"],"title_canon_sha256":"15fd4630253a069bb49e3d1e2d2b15f21cfe512a6a3b8b3fb7175a48cee435b4","abstract_canon_sha256":"3400559955165a3201a7ff5299014318bbe93a206ddafbbdb40942bd22af1de5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:11:52.775280Z","signature_b64":"NK7ShVJCh/1uc/woc6XZ+pV3CfznIcK4pqZMheQ59P9glpnEX39AU+xOxRnGNZ5GC19EDUAg/Lg2MjerSiY1Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e11f1cc45732d667ef4f1dbaa4d479549056b3c82ef7ad75d6c5c98a71afea43","last_reissued_at":"2026-07-05T09:11:52.774638Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:11:52.774638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VectorSearch: Enhancing Document Retrieval with Semantic Embeddings and Optimized Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB","cs.LG","cs.PF"],"primary_cat":"cs.IR","authors_text":"Dongfang Zhao, Irene Lau, Shubing Yang, Solmaz Seyed Monir","submitted_at":"2024-09-25T21:58:08Z","abstract_excerpt":"Traditional retrieval methods have been essential for assessing document similarity but struggle with capturing semantic nuances. Despite advancements in latent semantic analysis (LSA) and deep learning, achieving comprehensive semantic understanding and accurate retrieval remains challenging due to high dimensionality and semantic gaps. The above challenges call for new techniques to effectively reduce the dimensions and close the semantic gaps. To this end, we propose VectorSearch, which leverages advanced algorithms, embeddings, and indexing techniques for refined retrieval. By utilizing in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.17383","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/2409.17383/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":"2409.17383","created_at":"2026-07-05T09:11:52.774739+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.17383v1","created_at":"2026-07-05T09:11:52.774739+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.17383","created_at":"2026-07-05T09:11:52.774739+00:00"},{"alias_kind":"pith_short_12","alias_value":"4EPRZRCXGLLG","created_at":"2026-07-05T09:11:52.774739+00:00"},{"alias_kind":"pith_short_16","alias_value":"4EPRZRCXGLLGP32P","created_at":"2026-07-05T09:11:52.774739+00:00"},{"alias_kind":"pith_short_8","alias_value":"4EPRZRCX","created_at":"2026-07-05T09:11:52.774739+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.14941","citing_title":"WindVE: Collaborative CPU-NPU Vector Embedding","ref_index":2024,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4EPRZRCXGLLGP32PDW5KJVDZKS","json":"https://pith.science/pith/4EPRZRCXGLLGP32PDW5KJVDZKS.json","graph_json":"https://pith.science/api/pith-number/4EPRZRCXGLLGP32PDW5KJVDZKS/graph.json","events_json":"https://pith.science/api/pith-number/4EPRZRCXGLLGP32PDW5KJVDZKS/events.json","paper":"https://pith.science/paper/4EPRZRCX"},"agent_actions":{"view_html":"https://pith.science/pith/4EPRZRCXGLLGP32PDW5KJVDZKS","download_json":"https://pith.science/pith/4EPRZRCXGLLGP32PDW5KJVDZKS.json","view_paper":"https://pith.science/paper/4EPRZRCX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.17383&json=true","fetch_graph":"https://pith.science/api/pith-number/4EPRZRCXGLLGP32PDW5KJVDZKS/graph.json","fetch_events":"https://pith.science/api/pith-number/4EPRZRCXGLLGP32PDW5KJVDZKS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4EPRZRCXGLLGP32PDW5KJVDZKS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4EPRZRCXGLLGP32PDW5KJVDZKS/action/storage_attestation","attest_author":"https://pith.science/pith/4EPRZRCXGLLGP32PDW5KJVDZKS/action/author_attestation","sign_citation":"https://pith.science/pith/4EPRZRCXGLLGP32PDW5KJVDZKS/action/citation_signature","submit_replication":"https://pith.science/pith/4EPRZRCXGLLGP32PDW5KJVDZKS/action/replication_record"}},"created_at":"2026-07-05T09:11:52.774739+00:00","updated_at":"2026-07-05T09:11:52.774739+00:00"}