{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XG7ARARO5T3XHCWHZYBHDI7V6W","short_pith_number":"pith:XG7ARARO","canonical_record":{"source":{"id":"2607.18689","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T04:11:20Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"4d96ecb9c80e99b5c9a3134f47e7bf3e7d496b5f7e72b21ccca6ce9650bc8d3e","abstract_canon_sha256":"f91526569d4e9c766008d0fe0822ce2fc3d1ab636a836b228e0d12bbf9979e12"},"schema_version":"1.0"},"canonical_sha256":"b9be08822eecf7738ac7ce0271a3f5f58f1539172987c5db6fda07da81a2605f","source":{"kind":"arxiv","id":"2607.18689","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18689","created_at":"2026-07-22T01:23:06Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18689v1","created_at":"2026-07-22T01:23:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18689","created_at":"2026-07-22T01:23:06Z"},{"alias_kind":"pith_short_12","alias_value":"XG7ARARO5T3X","created_at":"2026-07-22T01:23:06Z"},{"alias_kind":"pith_short_16","alias_value":"XG7ARARO5T3XHCWH","created_at":"2026-07-22T01:23:06Z"},{"alias_kind":"pith_short_8","alias_value":"XG7ARARO","created_at":"2026-07-22T01:23:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XG7ARARO5T3XHCWHZYBHDI7V6W","target":"record","payload":{"canonical_record":{"source":{"id":"2607.18689","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T04:11:20Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"4d96ecb9c80e99b5c9a3134f47e7bf3e7d496b5f7e72b21ccca6ce9650bc8d3e","abstract_canon_sha256":"f91526569d4e9c766008d0fe0822ce2fc3d1ab636a836b228e0d12bbf9979e12"},"schema_version":"1.0"},"canonical_sha256":"b9be08822eecf7738ac7ce0271a3f5f58f1539172987c5db6fda07da81a2605f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T01:23:06.903595Z","signature_b64":"BR5Lm8tA1NoR90y91CvFZG/PNV3RkH9kI7/4njmMHdKVy+3GP7DtATFOL3u51aqaWKjjBkV42OMmfGXAGCtWCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9be08822eecf7738ac7ce0271a3f5f58f1539172987c5db6fda07da81a2605f","last_reissued_at":"2026-07-22T01:23:06.902753Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T01:23:06.902753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.18689","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":"2026-07-22T01:23:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v5SNjEg6GZTHCY81j8kENZEiGWTs9ugaXy/t4kH76tPhIE6jtjSh4lFie8OeZDRuOb/1r6NEcVOhpDrCr4zXCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:47:53.406493Z"},"content_sha256":"271d4bebdd6068e4948307fda6203f1b0b04fdc5d1961ab732d4b95977903d37","schema_version":"1.0","event_id":"sha256:271d4bebdd6068e4948307fda6203f1b0b04fdc5d1961ab732d4b95977903d37"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XG7ARARO5T3XHCWHZYBHDI7V6W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exposure-Based Reinforcement Learning to Rank","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Harrie Oosterhuis, Rolf Jagerman, Xuanhui Wang, Zhen Qin","submitted_at":"2026-07-21T04:11:20Z","abstract_excerpt":"Reinforcement learning (RL) methods for learning-to-rank (LTR) can optimize (almost) any ranking goal, e.g., from precision or discounted cumulative gain to fairness-of-exposure or ranking distillation. However, standard RL is ineffective and computationally costly due to the enormous action space in LTR settings. Existing methods reach computational efficiency through custom gradient computation algorithms, but they are very complex to implement and often clash with auto-differentiation. Consequently, existing RL for LTR is not attractive to many practitioners. We reconsider RL for LTR while "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18689","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/2607.18689/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":"2026-07-22T01:23:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9/+UTfeCuSP4jfYLu0SZFkeg8hUropwLSwI12+UVfdZz34ZLvThg9L+IRDZct7+5iNRUqpOheSOCGZp+r7AeAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:47:53.407021Z"},"content_sha256":"8a6cc937eda6490e6a60c8794e6b29e68cee098fba18fce4b609329e008f03c0","schema_version":"1.0","event_id":"sha256:8a6cc937eda6490e6a60c8794e6b29e68cee098fba18fce4b609329e008f03c0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XG7ARARO5T3XHCWHZYBHDI7V6W/bundle.json","state_url":"https://pith.science/pith/XG7ARARO5T3XHCWHZYBHDI7V6W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XG7ARARO5T3XHCWHZYBHDI7V6W/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":"2026-08-06T05:47:53Z","links":{"resolver":"https://pith.science/pith/XG7ARARO5T3XHCWHZYBHDI7V6W","bundle":"https://pith.science/pith/XG7ARARO5T3XHCWHZYBHDI7V6W/bundle.json","state":"https://pith.science/pith/XG7ARARO5T3XHCWHZYBHDI7V6W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XG7ARARO5T3XHCWHZYBHDI7V6W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XG7ARARO5T3XHCWHZYBHDI7V6W","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":"f91526569d4e9c766008d0fe0822ce2fc3d1ab636a836b228e0d12bbf9979e12","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T04:11:20Z","title_canon_sha256":"4d96ecb9c80e99b5c9a3134f47e7bf3e7d496b5f7e72b21ccca6ce9650bc8d3e"},"schema_version":"1.0","source":{"id":"2607.18689","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18689","created_at":"2026-07-22T01:23:06Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18689v1","created_at":"2026-07-22T01:23:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18689","created_at":"2026-07-22T01:23:06Z"},{"alias_kind":"pith_short_12","alias_value":"XG7ARARO5T3X","created_at":"2026-07-22T01:23:06Z"},{"alias_kind":"pith_short_16","alias_value":"XG7ARARO5T3XHCWH","created_at":"2026-07-22T01:23:06Z"},{"alias_kind":"pith_short_8","alias_value":"XG7ARARO","created_at":"2026-07-22T01:23:06Z"}],"graph_snapshots":[{"event_id":"sha256:8a6cc937eda6490e6a60c8794e6b29e68cee098fba18fce4b609329e008f03c0","target":"graph","created_at":"2026-07-22T01:23:06Z","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/2607.18689/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) methods for learning-to-rank (LTR) can optimize (almost) any ranking goal, e.g., from precision or discounted cumulative gain to fairness-of-exposure or ranking distillation. However, standard RL is ineffective and computationally costly due to the enormous action space in LTR settings. Existing methods reach computational efficiency through custom gradient computation algorithms, but they are very complex to implement and often clash with auto-differentiation. Consequently, existing RL for LTR is not attractive to many practitioners. We reconsider RL for LTR while ","authors_text":"Harrie Oosterhuis, Rolf Jagerman, Xuanhui Wang, Zhen Qin","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T04:11:20Z","title":"Exposure-Based Reinforcement Learning to Rank"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18689","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":"sha256:271d4bebdd6068e4948307fda6203f1b0b04fdc5d1961ab732d4b95977903d37","target":"record","created_at":"2026-07-22T01:23:06Z","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":"f91526569d4e9c766008d0fe0822ce2fc3d1ab636a836b228e0d12bbf9979e12","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T04:11:20Z","title_canon_sha256":"4d96ecb9c80e99b5c9a3134f47e7bf3e7d496b5f7e72b21ccca6ce9650bc8d3e"},"schema_version":"1.0","source":{"id":"2607.18689","kind":"arxiv","version":1}},"canonical_sha256":"b9be08822eecf7738ac7ce0271a3f5f58f1539172987c5db6fda07da81a2605f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b9be08822eecf7738ac7ce0271a3f5f58f1539172987c5db6fda07da81a2605f","first_computed_at":"2026-07-22T01:23:06.902753Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-22T01:23:06.902753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BR5Lm8tA1NoR90y91CvFZG/PNV3RkH9kI7/4njmMHdKVy+3GP7DtATFOL3u51aqaWKjjBkV42OMmfGXAGCtWCA==","signature_status":"signed_v1","signed_at":"2026-07-22T01:23:06.903595Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.18689","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:271d4bebdd6068e4948307fda6203f1b0b04fdc5d1961ab732d4b95977903d37","sha256:8a6cc937eda6490e6a60c8794e6b29e68cee098fba18fce4b609329e008f03c0"],"state_sha256":"491bfa7972f75ba8250968082eb6721ab6f2f7b07be12f6dab45788116a5cd08"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W78Az1m+rK6PW0TrgX5R5iaAT0IokTQ33Q/1zQ3chwMVeTQnxg/2HRXG4FPuDB0rkk5XlckLpwzp4tcNN2FFAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:47:53.412645Z","bundle_sha256":"33f015d3bab993748f0c52dc18c1b5e712ae840dbdec812972a72ce71b90d971"}}