{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CCMSJFOANBNPQ4MDVOBKLBVGWC","short_pith_number":"pith:CCMSJFOA","schema_version":"1.0","canonical_sha256":"10992495c0685af87183ab82a586a6b0aa284119af93d760769bad89556b1bfe","source":{"kind":"arxiv","id":"2505.18897","version":1},"attestation_state":"computed","paper":{"title":"Improving Ad matching via Cluster-Adaptive Keyword Expansion and Relevance tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Abraham Bagherjeiran, Anis Zaman, Dipanwita Saha, Hua Zou, Nadia Vase, Ning Chen, Xinxin Shu","submitted_at":"2025-05-24T23:02:19Z","abstract_excerpt":"In search advertising, keyword matching connects user queries with relevant ads. While token-based matching increases ad coverage, it can reduce relevance due to overly permissive semantic expansion. This work extends keyword reach through document-side semantic keyword expansion, using a language model to broaden token-level matching without altering queries. We propose a solution using a pre-trained siamese model to generate dense vector representations of ad keywords and identify semantically related variants through nearest neighbor search. To maintain precision, we introduce a cluster-bas"},"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":"2505.18897","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-05-24T23:02:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8d2b4aae7302d3a109dba1fb3e9fafd0f15e758fd1c2fec5c399940db2f2f93e","abstract_canon_sha256":"79559c1f6d5b36d64b845a9f3f1e69372392e91a22cd82f498108b797d2da238"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:21.547991Z","signature_b64":"l22bavy43ds+zJ3tgEsHg1kDYWFTak2HtCu1GYLzv0VkCbhkyXxnXZILvout93bXC3Ij/TOqFCef8JQSQJ04CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10992495c0685af87183ab82a586a6b0aa284119af93d760769bad89556b1bfe","last_reissued_at":"2026-07-05T11:09:21.547510Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:21.547510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Ad matching via Cluster-Adaptive Keyword Expansion and Relevance tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Abraham Bagherjeiran, Anis Zaman, Dipanwita Saha, Hua Zou, Nadia Vase, Ning Chen, Xinxin Shu","submitted_at":"2025-05-24T23:02:19Z","abstract_excerpt":"In search advertising, keyword matching connects user queries with relevant ads. While token-based matching increases ad coverage, it can reduce relevance due to overly permissive semantic expansion. This work extends keyword reach through document-side semantic keyword expansion, using a language model to broaden token-level matching without altering queries. We propose a solution using a pre-trained siamese model to generate dense vector representations of ad keywords and identify semantically related variants through nearest neighbor search. To maintain precision, we introduce a cluster-bas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18897","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/2505.18897/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":"2505.18897","created_at":"2026-07-05T11:09:21.547569+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18897v1","created_at":"2026-07-05T11:09:21.547569+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18897","created_at":"2026-07-05T11:09:21.547569+00:00"},{"alias_kind":"pith_short_12","alias_value":"CCMSJFOANBNP","created_at":"2026-07-05T11:09:21.547569+00:00"},{"alias_kind":"pith_short_16","alias_value":"CCMSJFOANBNPQ4MD","created_at":"2026-07-05T11:09:21.547569+00:00"},{"alias_kind":"pith_short_8","alias_value":"CCMSJFOA","created_at":"2026-07-05T11:09:21.547569+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.05570","citing_title":"LESER: Learning to Expand via Search Engine-feedback Reinforcement in e-Commerce","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CCMSJFOANBNPQ4MDVOBKLBVGWC","json":"https://pith.science/pith/CCMSJFOANBNPQ4MDVOBKLBVGWC.json","graph_json":"https://pith.science/api/pith-number/CCMSJFOANBNPQ4MDVOBKLBVGWC/graph.json","events_json":"https://pith.science/api/pith-number/CCMSJFOANBNPQ4MDVOBKLBVGWC/events.json","paper":"https://pith.science/paper/CCMSJFOA"},"agent_actions":{"view_html":"https://pith.science/pith/CCMSJFOANBNPQ4MDVOBKLBVGWC","download_json":"https://pith.science/pith/CCMSJFOANBNPQ4MDVOBKLBVGWC.json","view_paper":"https://pith.science/paper/CCMSJFOA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18897&json=true","fetch_graph":"https://pith.science/api/pith-number/CCMSJFOANBNPQ4MDVOBKLBVGWC/graph.json","fetch_events":"https://pith.science/api/pith-number/CCMSJFOANBNPQ4MDVOBKLBVGWC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CCMSJFOANBNPQ4MDVOBKLBVGWC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CCMSJFOANBNPQ4MDVOBKLBVGWC/action/storage_attestation","attest_author":"https://pith.science/pith/CCMSJFOANBNPQ4MDVOBKLBVGWC/action/author_attestation","sign_citation":"https://pith.science/pith/CCMSJFOANBNPQ4MDVOBKLBVGWC/action/citation_signature","submit_replication":"https://pith.science/pith/CCMSJFOANBNPQ4MDVOBKLBVGWC/action/replication_record"}},"created_at":"2026-07-05T11:09:21.547569+00:00","updated_at":"2026-07-05T11:09:21.547569+00:00"}