{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:RJWESUSISUI6MJCIN3JQAG5OJX","short_pith_number":"pith:RJWESUSI","schema_version":"1.0","canonical_sha256":"8a6c4952489511e624486ed3001bae4dd70eb489d6509e5301054deadf07751f","source":{"kind":"arxiv","id":"2008.03917","version":1},"attestation_state":"computed","paper":{"title":"Beyond Lexical: A Semantic Retrieval Framework for Textual SearchEngine","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Kuan Fang, LiWen Fan, Long Zhao, RiKang Zhour, Ruixing Wang, Zhan Shen","submitted_at":"2020-08-10T06:37:47Z","abstract_excerpt":"Search engine has become a fundamental component in various web and mobile applications. Retrieving relevant documents from the massive datasets is challenging for a search engine system, especially when faced with verbose or tail queries. In this paper, we explore a vector space search framework for document retrieval. Specifically, we trained a deep semantic matching model so that each query and document can be encoded as a low dimensional embedding. Our model was trained based on BERT architecture. We deployed a fast k-nearest-neighbor index service for online serving. Both offline and onli"},"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":"2008.03917","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-08-10T06:37:47Z","cross_cats_sorted":[],"title_canon_sha256":"725afff2797f86e5e9eb90d15ea5a6db81c6ebfd47cbbb0108cf9e57edb42c89","abstract_canon_sha256":"ea58aa7179de0759e2ee5585c8c5e2f2a0dbf71ffbc37ac3b270ace95b9ad00f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:25:57.881892Z","signature_b64":"Xhkc6bULqsqeXoG5a/5b8Ko6hM/QKr+hoSR1Ml84gtra3t1Hg/31Gt3RQYsy0kbvsyvNdDkBDXaD/ZVujFPrAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a6c4952489511e624486ed3001bae4dd70eb489d6509e5301054deadf07751f","last_reissued_at":"2026-07-05T01:25:57.881471Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:25:57.881471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Lexical: A Semantic Retrieval Framework for Textual SearchEngine","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Kuan Fang, LiWen Fan, Long Zhao, RiKang Zhour, Ruixing Wang, Zhan Shen","submitted_at":"2020-08-10T06:37:47Z","abstract_excerpt":"Search engine has become a fundamental component in various web and mobile applications. Retrieving relevant documents from the massive datasets is challenging for a search engine system, especially when faced with verbose or tail queries. In this paper, we explore a vector space search framework for document retrieval. Specifically, we trained a deep semantic matching model so that each query and document can be encoded as a low dimensional embedding. Our model was trained based on BERT architecture. We deployed a fast k-nearest-neighbor index service for online serving. Both offline and onli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.03917","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/2008.03917/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":"2008.03917","created_at":"2026-07-05T01:25:57.881532+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.03917v1","created_at":"2026-07-05T01:25:57.881532+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.03917","created_at":"2026-07-05T01:25:57.881532+00:00"},{"alias_kind":"pith_short_12","alias_value":"RJWESUSISUI6","created_at":"2026-07-05T01:25:57.881532+00:00"},{"alias_kind":"pith_short_16","alias_value":"RJWESUSISUI6MJCI","created_at":"2026-07-05T01:25:57.881532+00:00"},{"alias_kind":"pith_short_8","alias_value":"RJWESUSI","created_at":"2026-07-05T01:25:57.881532+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/RJWESUSISUI6MJCIN3JQAG5OJX","json":"https://pith.science/pith/RJWESUSISUI6MJCIN3JQAG5OJX.json","graph_json":"https://pith.science/api/pith-number/RJWESUSISUI6MJCIN3JQAG5OJX/graph.json","events_json":"https://pith.science/api/pith-number/RJWESUSISUI6MJCIN3JQAG5OJX/events.json","paper":"https://pith.science/paper/RJWESUSI"},"agent_actions":{"view_html":"https://pith.science/pith/RJWESUSISUI6MJCIN3JQAG5OJX","download_json":"https://pith.science/pith/RJWESUSISUI6MJCIN3JQAG5OJX.json","view_paper":"https://pith.science/paper/RJWESUSI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.03917&json=true","fetch_graph":"https://pith.science/api/pith-number/RJWESUSISUI6MJCIN3JQAG5OJX/graph.json","fetch_events":"https://pith.science/api/pith-number/RJWESUSISUI6MJCIN3JQAG5OJX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RJWESUSISUI6MJCIN3JQAG5OJX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RJWESUSISUI6MJCIN3JQAG5OJX/action/storage_attestation","attest_author":"https://pith.science/pith/RJWESUSISUI6MJCIN3JQAG5OJX/action/author_attestation","sign_citation":"https://pith.science/pith/RJWESUSISUI6MJCIN3JQAG5OJX/action/citation_signature","submit_replication":"https://pith.science/pith/RJWESUSISUI6MJCIN3JQAG5OJX/action/replication_record"}},"created_at":"2026-07-05T01:25:57.881532+00:00","updated_at":"2026-07-05T01:25:57.881532+00:00"}