{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:X5HBR6OUURZWSHRLWNBEDA5U3M","short_pith_number":"pith:X5HBR6OU","schema_version":"1.0","canonical_sha256":"bf4e18f9d4a473691e2bb3424183b4db01b96e8b6c66d6ea8d46ad2f2503ba14","source":{"kind":"arxiv","id":"2201.01534","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Online Learning to Rank with Unbiased Reward Shaping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Guido Zuccon, Shengyao Zhuang, Zhihao Qiao","submitted_at":"2022-01-05T10:43:25Z","abstract_excerpt":"Online learning to rank (OLTR) aims to learn a ranker directly from implicit feedback derived from users' interactions, such as clicks. Clicks however are a biased signal: specifically, top-ranked documents are likely to attract more clicks than documents down the ranking (position bias). In this paper, we propose a novel learning algorithm for OLTR that uses reinforcement learning to optimize rankers: Reinforcement Online Learning to Rank (ROLTR). In ROLTR, the gradients of the ranker are estimated based on the rewards assigned to clicked and unclicked documents. In order to de-bias the users"},"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":"2201.01534","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-01-05T10:43:25Z","cross_cats_sorted":[],"title_canon_sha256":"4c54f75287904e137ccd079dfab1f6bcff4e41315bc4e9842501188125e52d24","abstract_canon_sha256":"698e4e62348d2c2b133a5066d802b33ebe21f128052da3c8a78a1a2cee2a68d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:46:06.567370Z","signature_b64":"TCIEvDWIy91qbX3YP9QeBelFZ7NAiSBDZrDYM/Y1njWKfWrx4sRq2ohVgI6x1Wcp7VLJqBcVB4mY7De6O4PhBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf4e18f9d4a473691e2bb3424183b4db01b96e8b6c66d6ea8d46ad2f2503ba14","last_reissued_at":"2026-07-05T03:46:06.566943Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:46:06.566943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Online Learning to Rank with Unbiased Reward Shaping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Guido Zuccon, Shengyao Zhuang, Zhihao Qiao","submitted_at":"2022-01-05T10:43:25Z","abstract_excerpt":"Online learning to rank (OLTR) aims to learn a ranker directly from implicit feedback derived from users' interactions, such as clicks. Clicks however are a biased signal: specifically, top-ranked documents are likely to attract more clicks than documents down the ranking (position bias). In this paper, we propose a novel learning algorithm for OLTR that uses reinforcement learning to optimize rankers: Reinforcement Online Learning to Rank (ROLTR). In ROLTR, the gradients of the ranker are estimated based on the rewards assigned to clicked and unclicked documents. In order to de-bias the users"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.01534","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/2201.01534/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":"2201.01534","created_at":"2026-07-05T03:46:06.567002+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.01534v1","created_at":"2026-07-05T03:46:06.567002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.01534","created_at":"2026-07-05T03:46:06.567002+00:00"},{"alias_kind":"pith_short_12","alias_value":"X5HBR6OUURZW","created_at":"2026-07-05T03:46:06.567002+00:00"},{"alias_kind":"pith_short_16","alias_value":"X5HBR6OUURZWSHRL","created_at":"2026-07-05T03:46:06.567002+00:00"},{"alias_kind":"pith_short_8","alias_value":"X5HBR6OU","created_at":"2026-07-05T03:46:06.567002+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/X5HBR6OUURZWSHRLWNBEDA5U3M","json":"https://pith.science/pith/X5HBR6OUURZWSHRLWNBEDA5U3M.json","graph_json":"https://pith.science/api/pith-number/X5HBR6OUURZWSHRLWNBEDA5U3M/graph.json","events_json":"https://pith.science/api/pith-number/X5HBR6OUURZWSHRLWNBEDA5U3M/events.json","paper":"https://pith.science/paper/X5HBR6OU"},"agent_actions":{"view_html":"https://pith.science/pith/X5HBR6OUURZWSHRLWNBEDA5U3M","download_json":"https://pith.science/pith/X5HBR6OUURZWSHRLWNBEDA5U3M.json","view_paper":"https://pith.science/paper/X5HBR6OU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.01534&json=true","fetch_graph":"https://pith.science/api/pith-number/X5HBR6OUURZWSHRLWNBEDA5U3M/graph.json","fetch_events":"https://pith.science/api/pith-number/X5HBR6OUURZWSHRLWNBEDA5U3M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X5HBR6OUURZWSHRLWNBEDA5U3M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X5HBR6OUURZWSHRLWNBEDA5U3M/action/storage_attestation","attest_author":"https://pith.science/pith/X5HBR6OUURZWSHRLWNBEDA5U3M/action/author_attestation","sign_citation":"https://pith.science/pith/X5HBR6OUURZWSHRLWNBEDA5U3M/action/citation_signature","submit_replication":"https://pith.science/pith/X5HBR6OUURZWSHRLWNBEDA5U3M/action/replication_record"}},"created_at":"2026-07-05T03:46:06.567002+00:00","updated_at":"2026-07-05T03:46:06.567002+00:00"}