{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:RFYXQ4T35ADQTCTQNPSJZ3FEIC","short_pith_number":"pith:RFYXQ4T3","schema_version":"1.0","canonical_sha256":"897178727be807098a706be49ceca4409f93f4c043945ed26b62dfff674014e4","source":{"kind":"arxiv","id":"1811.12776","version":2},"attestation_state":"computed","paper":{"title":"Learning From Weights: A Cost-Sensitive Approach For Ad Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Nikit Begwani, Rahul Agrawal, Shrutendra Harsola","submitted_at":"2018-11-30T13:13:38Z","abstract_excerpt":"Retrieval models such as CLSM is trained on click-through data which treats each clicked query-document pair as equivalent. While training on click-through data is reasonable, this paper argues that it is sub-optimal because of its noisy and long-tail nature (especially for sponsored search). In this paper, we discuss the impact of incorporating or disregarding the long tail pairs in the training set. Also, we propose a weighing based strategy using which we can learn semantic representations for tail pairs without compromising the quality of retrieval. We conducted our experiments on Bing spo"},"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":"1811.12776","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-11-30T13:13:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"11e5d0ce67b67e8957ff97eca75048a3905134db17d7cf0cd169f40076a38436","abstract_canon_sha256":"99ed24d193fdf08dc42c5e88e4049d228c4688da05d795c48ea2093744161724"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:21.903889Z","signature_b64":"RCvgIz62nl9N3rnmhP/4yTjF749UCx1Z71/PmDfckULu+AIM/xxjacIDmvILwA2dobjpDJEB1bSvMlf9imG8DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"897178727be807098a706be49ceca4409f93f4c043945ed26b62dfff674014e4","last_reissued_at":"2026-05-17T23:59:21.903433Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:21.903433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning From Weights: A Cost-Sensitive Approach For Ad Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Nikit Begwani, Rahul Agrawal, Shrutendra Harsola","submitted_at":"2018-11-30T13:13:38Z","abstract_excerpt":"Retrieval models such as CLSM is trained on click-through data which treats each clicked query-document pair as equivalent. While training on click-through data is reasonable, this paper argues that it is sub-optimal because of its noisy and long-tail nature (especially for sponsored search). In this paper, we discuss the impact of incorporating or disregarding the long tail pairs in the training set. Also, we propose a weighing based strategy using which we can learn semantic representations for tail pairs without compromising the quality of retrieval. We conducted our experiments on Bing spo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.12776","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":""},"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":"1811.12776","created_at":"2026-05-17T23:59:21.903504+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.12776v2","created_at":"2026-05-17T23:59:21.903504+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.12776","created_at":"2026-05-17T23:59:21.903504+00:00"},{"alias_kind":"pith_short_12","alias_value":"RFYXQ4T35ADQ","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"RFYXQ4T35ADQTCTQ","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"RFYXQ4T3","created_at":"2026-05-18T12:32:50.500415+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/RFYXQ4T35ADQTCTQNPSJZ3FEIC","json":"https://pith.science/pith/RFYXQ4T35ADQTCTQNPSJZ3FEIC.json","graph_json":"https://pith.science/api/pith-number/RFYXQ4T35ADQTCTQNPSJZ3FEIC/graph.json","events_json":"https://pith.science/api/pith-number/RFYXQ4T35ADQTCTQNPSJZ3FEIC/events.json","paper":"https://pith.science/paper/RFYXQ4T3"},"agent_actions":{"view_html":"https://pith.science/pith/RFYXQ4T35ADQTCTQNPSJZ3FEIC","download_json":"https://pith.science/pith/RFYXQ4T35ADQTCTQNPSJZ3FEIC.json","view_paper":"https://pith.science/paper/RFYXQ4T3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.12776&json=true","fetch_graph":"https://pith.science/api/pith-number/RFYXQ4T35ADQTCTQNPSJZ3FEIC/graph.json","fetch_events":"https://pith.science/api/pith-number/RFYXQ4T35ADQTCTQNPSJZ3FEIC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RFYXQ4T35ADQTCTQNPSJZ3FEIC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RFYXQ4T35ADQTCTQNPSJZ3FEIC/action/storage_attestation","attest_author":"https://pith.science/pith/RFYXQ4T35ADQTCTQNPSJZ3FEIC/action/author_attestation","sign_citation":"https://pith.science/pith/RFYXQ4T35ADQTCTQNPSJZ3FEIC/action/citation_signature","submit_replication":"https://pith.science/pith/RFYXQ4T35ADQTCTQNPSJZ3FEIC/action/replication_record"}},"created_at":"2026-05-17T23:59:21.903504+00:00","updated_at":"2026-05-17T23:59:21.903504+00:00"}