{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:X5HBR6OUURZWSHRLWNBEDA5U3M","short_pith_number":"pith:X5HBR6OU","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"},"canonical_sha256":"bf4e18f9d4a473691e2bb3424183b4db01b96e8b6c66d6ea8d46ad2f2503ba14","source":{"kind":"arxiv","id":"2201.01534","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.01534","created_at":"2026-07-05T03:46:06Z"},{"alias_kind":"arxiv_version","alias_value":"2201.01534v1","created_at":"2026-07-05T03:46:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.01534","created_at":"2026-07-05T03:46:06Z"},{"alias_kind":"pith_short_12","alias_value":"X5HBR6OUURZW","created_at":"2026-07-05T03:46:06Z"},{"alias_kind":"pith_short_16","alias_value":"X5HBR6OUURZWSHRL","created_at":"2026-07-05T03:46:06Z"},{"alias_kind":"pith_short_8","alias_value":"X5HBR6OU","created_at":"2026-07-05T03:46:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:X5HBR6OUURZWSHRLWNBEDA5U3M","target":"record","payload":{"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"},"canonical_sha256":"bf4e18f9d4a473691e2bb3424183b4db01b96e8b6c66d6ea8d46ad2f2503ba14","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"},"source_kind":"arxiv","source_id":"2201.01534","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:46:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r6dtf/9dzuf0Fh4fB9jePPkwEFLjwce+6ypEzE0AabcHp6UGpNxqjOaeEwsGtWRnj1aPLUaVN8b/UMjE6xWiCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:02:16.410740Z"},"content_sha256":"4e8f284e377710c73131840a7074c539ccf85c75c0ec124352eb5ee129b99603","schema_version":"1.0","event_id":"sha256:4e8f284e377710c73131840a7074c539ccf85c75c0ec124352eb5ee129b99603"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:X5HBR6OUURZWSHRLWNBEDA5U3M","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:46:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6/ClOYabLt2xucBljxbDlw76znqN62tlnQNGbRb7oIfp1yozA/TBrFTYAIwUxfA0dZlSZJA4rm80kgId5B5/DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:02:16.411122Z"},"content_sha256":"dd0342021757d15a37d55768160a198ff24714b10ce10fa156566358fd8c6775","schema_version":"1.0","event_id":"sha256:dd0342021757d15a37d55768160a198ff24714b10ce10fa156566358fd8c6775"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X5HBR6OUURZWSHRLWNBEDA5U3M/bundle.json","state_url":"https://pith.science/pith/X5HBR6OUURZWSHRLWNBEDA5U3M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X5HBR6OUURZWSHRLWNBEDA5U3M/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T03:02:16Z","links":{"resolver":"https://pith.science/pith/X5HBR6OUURZWSHRLWNBEDA5U3M","bundle":"https://pith.science/pith/X5HBR6OUURZWSHRLWNBEDA5U3M/bundle.json","state":"https://pith.science/pith/X5HBR6OUURZWSHRLWNBEDA5U3M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X5HBR6OUURZWSHRLWNBEDA5U3M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:X5HBR6OUURZWSHRLWNBEDA5U3M","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"698e4e62348d2c2b133a5066d802b33ebe21f128052da3c8a78a1a2cee2a68d9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-01-05T10:43:25Z","title_canon_sha256":"4c54f75287904e137ccd079dfab1f6bcff4e41315bc4e9842501188125e52d24"},"schema_version":"1.0","source":{"id":"2201.01534","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.01534","created_at":"2026-07-05T03:46:06Z"},{"alias_kind":"arxiv_version","alias_value":"2201.01534v1","created_at":"2026-07-05T03:46:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.01534","created_at":"2026-07-05T03:46:06Z"},{"alias_kind":"pith_short_12","alias_value":"X5HBR6OUURZW","created_at":"2026-07-05T03:46:06Z"},{"alias_kind":"pith_short_16","alias_value":"X5HBR6OUURZWSHRL","created_at":"2026-07-05T03:46:06Z"},{"alias_kind":"pith_short_8","alias_value":"X5HBR6OU","created_at":"2026-07-05T03:46:06Z"}],"graph_snapshots":[{"event_id":"sha256:dd0342021757d15a37d55768160a198ff24714b10ce10fa156566358fd8c6775","target":"graph","created_at":"2026-07-05T03:46:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2201.01534/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Guido Zuccon, Shengyao Zhuang, Zhihao Qiao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-01-05T10:43:25Z","title":"Reinforcement Online Learning to Rank with Unbiased Reward Shaping"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.01534","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4e8f284e377710c73131840a7074c539ccf85c75c0ec124352eb5ee129b99603","target":"record","created_at":"2026-07-05T03:46:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"698e4e62348d2c2b133a5066d802b33ebe21f128052da3c8a78a1a2cee2a68d9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-01-05T10:43:25Z","title_canon_sha256":"4c54f75287904e137ccd079dfab1f6bcff4e41315bc4e9842501188125e52d24"},"schema_version":"1.0","source":{"id":"2201.01534","kind":"arxiv","version":1}},"canonical_sha256":"bf4e18f9d4a473691e2bb3424183b4db01b96e8b6c66d6ea8d46ad2f2503ba14","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf4e18f9d4a473691e2bb3424183b4db01b96e8b6c66d6ea8d46ad2f2503ba14","first_computed_at":"2026-07-05T03:46:06.566943Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:46:06.566943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TCIEvDWIy91qbX3YP9QeBelFZ7NAiSBDZrDYM/Y1njWKfWrx4sRq2ohVgI6x1Wcp7VLJqBcVB4mY7De6O4PhBg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:46:06.567370Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.01534","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e8f284e377710c73131840a7074c539ccf85c75c0ec124352eb5ee129b99603","sha256:dd0342021757d15a37d55768160a198ff24714b10ce10fa156566358fd8c6775"],"state_sha256":"4bc63ceeeb0494a7b5e59f29496fd564f90a8f5f2afca8a564e01c2207b2ae62"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eq3mxodKCqfwRtF5En4Pk+tSiy+ltfiuVb8cfkMqKsDH5lxqX6Y0ArsYE7x0KumipRkZLykOmC1l+VX8RfwxAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T03:02:16.413542Z","bundle_sha256":"295cea4ad71bf48ee59aa0811e1eed6270eca7e6b5b9e253afc584e3ba65341e"}}