{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XKGUN6ZP7U4YEHJCGGSKEJAYSO","short_pith_number":"pith:XKGUN6ZP","schema_version":"1.0","canonical_sha256":"ba8d46fb2ffd39821d2231a4a22418939281930fa4e4d187ff56ea2ee73a73c4","source":{"kind":"arxiv","id":"2302.09340","version":1},"attestation_state":"computed","paper":{"title":"Ensemble Ranking Model with Multiple Pretraining Strategies for Web Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jiafeng Guo, Keping Bi, Lulu Yu, Xiaojie Sun, Yiting Wang","submitted_at":"2023-02-18T14:14:50Z","abstract_excerpt":"An effective ranking model usually requires a large amount of training data to learn the relevance between documents and queries. User clicks are often used as training data since they can indicate relevance and are cheap to collect, but they contain substantial bias and noise. There has been some work on mitigating various types of bias in simulated user clicks to train effective learning-to-rank models based on multiple features. However, how to effectively use such methods on large-scale pre-trained models with real-world click data is unknown. To alleviate the data bias in the real world, "},"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":"2302.09340","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-02-18T14:14:50Z","cross_cats_sorted":[],"title_canon_sha256":"81ff81a0191c4cb5fdd33e06897f2bcd691b81846aa2a1f7953602a209bbf2ab","abstract_canon_sha256":"c9e813961d77aa92445d3a71e69e8cf649b9ef9c7bc56605046719ba157a8529"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:43:24.432802Z","signature_b64":"GdbeNPGbvdJpnFJkkYZYX6JbgBtaqsMgCbhC8nVkUQd3//AJ1xh+2HSiyKSRRQq5PbVobCFaSVpQQC406TrRBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba8d46fb2ffd39821d2231a4a22418939281930fa4e4d187ff56ea2ee73a73c4","last_reissued_at":"2026-07-05T05:43:24.432374Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:43:24.432374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ensemble Ranking Model with Multiple Pretraining Strategies for Web Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jiafeng Guo, Keping Bi, Lulu Yu, Xiaojie Sun, Yiting Wang","submitted_at":"2023-02-18T14:14:50Z","abstract_excerpt":"An effective ranking model usually requires a large amount of training data to learn the relevance between documents and queries. User clicks are often used as training data since they can indicate relevance and are cheap to collect, but they contain substantial bias and noise. There has been some work on mitigating various types of bias in simulated user clicks to train effective learning-to-rank models based on multiple features. However, how to effectively use such methods on large-scale pre-trained models with real-world click data is unknown. To alleviate the data bias in the real world, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.09340","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/2302.09340/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":"2302.09340","created_at":"2026-07-05T05:43:24.432428+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.09340v1","created_at":"2026-07-05T05:43:24.432428+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.09340","created_at":"2026-07-05T05:43:24.432428+00:00"},{"alias_kind":"pith_short_12","alias_value":"XKGUN6ZP7U4Y","created_at":"2026-07-05T05:43:24.432428+00:00"},{"alias_kind":"pith_short_16","alias_value":"XKGUN6ZP7U4YEHJC","created_at":"2026-07-05T05:43:24.432428+00:00"},{"alias_kind":"pith_short_8","alias_value":"XKGUN6ZP","created_at":"2026-07-05T05:43:24.432428+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/XKGUN6ZP7U4YEHJCGGSKEJAYSO","json":"https://pith.science/pith/XKGUN6ZP7U4YEHJCGGSKEJAYSO.json","graph_json":"https://pith.science/api/pith-number/XKGUN6ZP7U4YEHJCGGSKEJAYSO/graph.json","events_json":"https://pith.science/api/pith-number/XKGUN6ZP7U4YEHJCGGSKEJAYSO/events.json","paper":"https://pith.science/paper/XKGUN6ZP"},"agent_actions":{"view_html":"https://pith.science/pith/XKGUN6ZP7U4YEHJCGGSKEJAYSO","download_json":"https://pith.science/pith/XKGUN6ZP7U4YEHJCGGSKEJAYSO.json","view_paper":"https://pith.science/paper/XKGUN6ZP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.09340&json=true","fetch_graph":"https://pith.science/api/pith-number/XKGUN6ZP7U4YEHJCGGSKEJAYSO/graph.json","fetch_events":"https://pith.science/api/pith-number/XKGUN6ZP7U4YEHJCGGSKEJAYSO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XKGUN6ZP7U4YEHJCGGSKEJAYSO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XKGUN6ZP7U4YEHJCGGSKEJAYSO/action/storage_attestation","attest_author":"https://pith.science/pith/XKGUN6ZP7U4YEHJCGGSKEJAYSO/action/author_attestation","sign_citation":"https://pith.science/pith/XKGUN6ZP7U4YEHJCGGSKEJAYSO/action/citation_signature","submit_replication":"https://pith.science/pith/XKGUN6ZP7U4YEHJCGGSKEJAYSO/action/replication_record"}},"created_at":"2026-07-05T05:43:24.432428+00:00","updated_at":"2026-07-05T05:43:24.432428+00:00"}