{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NS5XDEHLDRBNKI472JMQHMUMKA","short_pith_number":"pith:NS5XDEHL","schema_version":"1.0","canonical_sha256":"6cbb7190eb1c42d5239fd25903b28c50198755df5ae8aa2390b082f98f3477c1","source":{"kind":"arxiv","id":"2506.06989","version":3},"attestation_state":"computed","paper":{"title":"A Control Function Framework for Mitigating Position Bias in Learning to Rank Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Elena Zheleva, Kathryn Vasilaky, Md Aminul Islam","submitted_at":"2025-06-08T04:10:14Z","abstract_excerpt":"Learning-to-rank (LTR) systems commonly depend on implicit feedback, such as user clicks, because it is easy to collect and can serve as a valuable signal of user preferences. However, directly optimizing ranking models using implicit feedback data often yields suboptimal performance because such data is inherently skewed by systematic biases. Among these biases, position bias is particularly pervasive: items ranked higher tend to receive disproportionately more interactions, regardless of their actual relevance. To address this, we introduce a novel two-stage framework based on control functi"},"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":"2506.06989","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-08T04:10:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bde59ed9780ae788b0c39b2634e478ea759dac3ee8c0bb8111300c21e879a5e6","abstract_canon_sha256":"6a6adf4e80a07f858d860e06e1d18e2d67dc95b5861b1fa44107ceed2289dff2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T02:18:16.042392Z","signature_b64":"uchbN4YUiN+R95nmt/EzhEbhai7NxwbZ5MlBtN038mwwxj1ZDEBEp+9tA4s5rPISHTH0lufvPFtd9g7APLVjAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cbb7190eb1c42d5239fd25903b28c50198755df5ae8aa2390b082f98f3477c1","last_reissued_at":"2026-08-11T02:18:16.040600Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T02:18:16.040600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Control Function Framework for Mitigating Position Bias in Learning to Rank Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Elena Zheleva, Kathryn Vasilaky, Md Aminul Islam","submitted_at":"2025-06-08T04:10:14Z","abstract_excerpt":"Learning-to-rank (LTR) systems commonly depend on implicit feedback, such as user clicks, because it is easy to collect and can serve as a valuable signal of user preferences. However, directly optimizing ranking models using implicit feedback data often yields suboptimal performance because such data is inherently skewed by systematic biases. Among these biases, position bias is particularly pervasive: items ranked higher tend to receive disproportionately more interactions, regardless of their actual relevance. To address this, we introduce a novel two-stage framework based on control functi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06989","kind":"arxiv","version":3},"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/2506.06989/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":"2506.06989","created_at":"2026-08-11T02:18:16.041299+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.06989v3","created_at":"2026-08-11T02:18:16.041299+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06989","created_at":"2026-08-11T02:18:16.041299+00:00"},{"alias_kind":"pith_short_12","alias_value":"NS5XDEHLDRBN","created_at":"2026-08-11T02:18:16.041299+00:00"},{"alias_kind":"pith_short_16","alias_value":"NS5XDEHLDRBNKI47","created_at":"2026-08-11T02:18:16.041299+00:00"},{"alias_kind":"pith_short_8","alias_value":"NS5XDEHL","created_at":"2026-08-11T02:18:16.041299+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.04072","citing_title":"CTR-Guided Generative Query Suggestion in Conversational Search","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NS5XDEHLDRBNKI472JMQHMUMKA","json":"https://pith.science/pith/NS5XDEHLDRBNKI472JMQHMUMKA.json","graph_json":"https://pith.science/api/pith-number/NS5XDEHLDRBNKI472JMQHMUMKA/graph.json","events_json":"https://pith.science/api/pith-number/NS5XDEHLDRBNKI472JMQHMUMKA/events.json","paper":"https://pith.science/paper/NS5XDEHL"},"agent_actions":{"view_html":"https://pith.science/pith/NS5XDEHLDRBNKI472JMQHMUMKA","download_json":"https://pith.science/pith/NS5XDEHLDRBNKI472JMQHMUMKA.json","view_paper":"https://pith.science/paper/NS5XDEHL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.06989&json=true","fetch_graph":"https://pith.science/api/pith-number/NS5XDEHLDRBNKI472JMQHMUMKA/graph.json","fetch_events":"https://pith.science/api/pith-number/NS5XDEHLDRBNKI472JMQHMUMKA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NS5XDEHLDRBNKI472JMQHMUMKA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NS5XDEHLDRBNKI472JMQHMUMKA/action/storage_attestation","attest_author":"https://pith.science/pith/NS5XDEHLDRBNKI472JMQHMUMKA/action/author_attestation","sign_citation":"https://pith.science/pith/NS5XDEHLDRBNKI472JMQHMUMKA/action/citation_signature","submit_replication":"https://pith.science/pith/NS5XDEHLDRBNKI472JMQHMUMKA/action/replication_record"}},"created_at":"2026-08-11T02:18:16.041299+00:00","updated_at":"2026-08-11T02:18:16.041299+00:00"}