{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:E2LSXA33MYLSPCK5BOSLCWCFHW","short_pith_number":"pith:E2LSXA33","schema_version":"1.0","canonical_sha256":"26972b837b661727895d0ba4b158453db099e01fea46bc23465e675527395b2b","source":{"kind":"arxiv","id":"2210.14958","version":2},"attestation_state":"computed","paper":{"title":"Constrained Approximate Similarity Search on Proximity Graph","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Ping Li, Shulong Tan, Weijie Zhao","submitted_at":"2022-10-26T18:15:47Z","abstract_excerpt":"Search engines and recommendation systems are built to efficiently display relevant information from those massive amounts of candidates. Typically a three-stage mechanism is employed in those systems: (i) a small collection of items are first retrieved by (e.g.,) approximate near neighbor search algorithms; (ii) then a collection of constraints are applied on the retrieved items; (iii) a fine-grained ranking neural network is employed to determine the final recommendation. We observe a major defect of the original three-stage pipeline: Although we only target to retrieve $k$ vectors in the fi"},"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":"2210.14958","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2022-10-26T18:15:47Z","cross_cats_sorted":[],"title_canon_sha256":"b9ecbb13afb9cf3432db7eceb31be821ce68be77b764344ab71f3d94150c4455","abstract_canon_sha256":"c6140a5cbd6b00a120092ec69516d54cbf1159de96c9d2eb2126cb0129974d4a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:13:57.958482Z","signature_b64":"iTWpHUc6DXbnxcdakn69I3f89R1dpFNtJxxILjYL3cV9WCvZAt9u4qqra1r5/vmfhqnyk8njZhxn4Pz+15cTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26972b837b661727895d0ba4b158453db099e01fea46bc23465e675527395b2b","last_reissued_at":"2026-07-05T05:13:57.958068Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:13:57.958068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Constrained Approximate Similarity Search on Proximity Graph","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Ping Li, Shulong Tan, Weijie Zhao","submitted_at":"2022-10-26T18:15:47Z","abstract_excerpt":"Search engines and recommendation systems are built to efficiently display relevant information from those massive amounts of candidates. Typically a three-stage mechanism is employed in those systems: (i) a small collection of items are first retrieved by (e.g.,) approximate near neighbor search algorithms; (ii) then a collection of constraints are applied on the retrieved items; (iii) a fine-grained ranking neural network is employed to determine the final recommendation. We observe a major defect of the original three-stage pipeline: Although we only target to retrieve $k$ vectors in the fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.14958","kind":"arxiv","version":2},"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/2210.14958/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":"2210.14958","created_at":"2026-07-05T05:13:57.958124+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.14958v2","created_at":"2026-07-05T05:13:57.958124+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.14958","created_at":"2026-07-05T05:13:57.958124+00:00"},{"alias_kind":"pith_short_12","alias_value":"E2LSXA33MYLS","created_at":"2026-07-05T05:13:57.958124+00:00"},{"alias_kind":"pith_short_16","alias_value":"E2LSXA33MYLSPCK5","created_at":"2026-07-05T05:13:57.958124+00:00"},{"alias_kind":"pith_short_8","alias_value":"E2LSXA33","created_at":"2026-07-05T05:13:57.958124+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00734","citing_title":"EMA: Approximate Nearest Neighbor Search with General Attribute Filtering and Dynamic Updates","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02522","citing_title":"Opal: Private Memory for Personal AI","ref_index":279,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07770","citing_title":"FAVOR: Efficient Filter-Agnostic Vector ANNS Based on Selectivity-Aware Exclusion Distances","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E2LSXA33MYLSPCK5BOSLCWCFHW","json":"https://pith.science/pith/E2LSXA33MYLSPCK5BOSLCWCFHW.json","graph_json":"https://pith.science/api/pith-number/E2LSXA33MYLSPCK5BOSLCWCFHW/graph.json","events_json":"https://pith.science/api/pith-number/E2LSXA33MYLSPCK5BOSLCWCFHW/events.json","paper":"https://pith.science/paper/E2LSXA33"},"agent_actions":{"view_html":"https://pith.science/pith/E2LSXA33MYLSPCK5BOSLCWCFHW","download_json":"https://pith.science/pith/E2LSXA33MYLSPCK5BOSLCWCFHW.json","view_paper":"https://pith.science/paper/E2LSXA33","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.14958&json=true","fetch_graph":"https://pith.science/api/pith-number/E2LSXA33MYLSPCK5BOSLCWCFHW/graph.json","fetch_events":"https://pith.science/api/pith-number/E2LSXA33MYLSPCK5BOSLCWCFHW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E2LSXA33MYLSPCK5BOSLCWCFHW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E2LSXA33MYLSPCK5BOSLCWCFHW/action/storage_attestation","attest_author":"https://pith.science/pith/E2LSXA33MYLSPCK5BOSLCWCFHW/action/author_attestation","sign_citation":"https://pith.science/pith/E2LSXA33MYLSPCK5BOSLCWCFHW/action/citation_signature","submit_replication":"https://pith.science/pith/E2LSXA33MYLSPCK5BOSLCWCFHW/action/replication_record"}},"created_at":"2026-07-05T05:13:57.958124+00:00","updated_at":"2026-07-05T05:13:57.958124+00:00"}