{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KFA3SS6JS5SYZ23P5EULV3B5FZ","short_pith_number":"pith:KFA3SS6J","schema_version":"1.0","canonical_sha256":"5141b94bc997658ceb6fe928baec3d2e47233b6ecca45d6cc260c26cb764f50d","source":{"kind":"arxiv","id":"2304.09287","version":1},"attestation_state":"computed","paper":{"title":"Integrity and Junkiness Failure Handling for Embedding-based Retrieval: A Case Study in Social Network Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Chiyao Shen, Guangdeng Liao, Hao Fu, Pramodh Karanth Prabhakar, Shuai Ding, Wenping Wang, Yunxi Guo","submitted_at":"2023-04-18T20:53:47Z","abstract_excerpt":"Embedding based retrieval has seen its usage in a variety of search applications like e-commerce, social networking search etc. While the approach has demonstrated its efficacy in tasks like semantic matching and contextual search, it is plagued by the problem of uncontrollable relevance. In this paper, we conduct an analysis of embedding-based retrieval launched in early 2021 on our social network search engine, and define two main categories of failures introduced by it, integrity and junkiness. The former refers to issues such as hate speech and offensive content that can severely harm user"},"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":"2304.09287","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-04-18T20:53:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"960529509ee0b90f841923cd7b2b669484c782952a09ca53d5ae7eefaef42a8d","abstract_canon_sha256":"2a6f2f4c98a8416e0ec75935a8e8dd224876772f9aff9d4c0e7c5be97c0dd33a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:02:36.328429Z","signature_b64":"tNyZtqZvssa7cfmCNHWryW6mWQIdwFnL6/BCI7QZYCdDdHqbf0iUXIiNV5idLanpNecSXoq37GQxWuN4NnG0Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5141b94bc997658ceb6fe928baec3d2e47233b6ecca45d6cc260c26cb764f50d","last_reissued_at":"2026-07-05T06:02:36.328026Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:02:36.328026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Integrity and Junkiness Failure Handling for Embedding-based Retrieval: A Case Study in Social Network Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Chiyao Shen, Guangdeng Liao, Hao Fu, Pramodh Karanth Prabhakar, Shuai Ding, Wenping Wang, Yunxi Guo","submitted_at":"2023-04-18T20:53:47Z","abstract_excerpt":"Embedding based retrieval has seen its usage in a variety of search applications like e-commerce, social networking search etc. While the approach has demonstrated its efficacy in tasks like semantic matching and contextual search, it is plagued by the problem of uncontrollable relevance. In this paper, we conduct an analysis of embedding-based retrieval launched in early 2021 on our social network search engine, and define two main categories of failures introduced by it, integrity and junkiness. The former refers to issues such as hate speech and offensive content that can severely harm user"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.09287","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/2304.09287/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":"2304.09287","created_at":"2026-07-05T06:02:36.328093+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.09287v1","created_at":"2026-07-05T06:02:36.328093+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.09287","created_at":"2026-07-05T06:02:36.328093+00:00"},{"alias_kind":"pith_short_12","alias_value":"KFA3SS6JS5SY","created_at":"2026-07-05T06:02:36.328093+00:00"},{"alias_kind":"pith_short_16","alias_value":"KFA3SS6JS5SYZ23P","created_at":"2026-07-05T06:02:36.328093+00:00"},{"alias_kind":"pith_short_8","alias_value":"KFA3SS6J","created_at":"2026-07-05T06:02:36.328093+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/KFA3SS6JS5SYZ23P5EULV3B5FZ","json":"https://pith.science/pith/KFA3SS6JS5SYZ23P5EULV3B5FZ.json","graph_json":"https://pith.science/api/pith-number/KFA3SS6JS5SYZ23P5EULV3B5FZ/graph.json","events_json":"https://pith.science/api/pith-number/KFA3SS6JS5SYZ23P5EULV3B5FZ/events.json","paper":"https://pith.science/paper/KFA3SS6J"},"agent_actions":{"view_html":"https://pith.science/pith/KFA3SS6JS5SYZ23P5EULV3B5FZ","download_json":"https://pith.science/pith/KFA3SS6JS5SYZ23P5EULV3B5FZ.json","view_paper":"https://pith.science/paper/KFA3SS6J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.09287&json=true","fetch_graph":"https://pith.science/api/pith-number/KFA3SS6JS5SYZ23P5EULV3B5FZ/graph.json","fetch_events":"https://pith.science/api/pith-number/KFA3SS6JS5SYZ23P5EULV3B5FZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KFA3SS6JS5SYZ23P5EULV3B5FZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KFA3SS6JS5SYZ23P5EULV3B5FZ/action/storage_attestation","attest_author":"https://pith.science/pith/KFA3SS6JS5SYZ23P5EULV3B5FZ/action/author_attestation","sign_citation":"https://pith.science/pith/KFA3SS6JS5SYZ23P5EULV3B5FZ/action/citation_signature","submit_replication":"https://pith.science/pith/KFA3SS6JS5SYZ23P5EULV3B5FZ/action/replication_record"}},"created_at":"2026-07-05T06:02:36.328093+00:00","updated_at":"2026-07-05T06:02:36.328093+00:00"}