{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HCALVUB6TJTY2TYM33SYX42EGB","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":"9d63fba42945f189b69326f7d6fc241cacbeea61be2f02c9624d280f94546068","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-28T04:13:47Z","title_canon_sha256":"49768f9aeefcd05310079413195e0ef8e4848427c7c28f85487b69bb9387ea18"},"schema_version":"1.0","source":{"id":"2607.25268","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.25268","created_at":"2026-07-29T00:25:11Z"},{"alias_kind":"arxiv_version","alias_value":"2607.25268v1","created_at":"2026-07-29T00:25:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.25268","created_at":"2026-07-29T00:25:11Z"},{"alias_kind":"pith_short_12","alias_value":"HCALVUB6TJTY","created_at":"2026-07-29T00:25:11Z"},{"alias_kind":"pith_short_16","alias_value":"HCALVUB6TJTY2TYM","created_at":"2026-07-29T00:25:11Z"},{"alias_kind":"pith_short_8","alias_value":"HCALVUB6","created_at":"2026-07-29T00:25:11Z"}],"graph_snapshots":[{"event_id":"sha256:50fc4947ebf388485c002153a0a3da21dab5f383372cd45c5261bf237fca9d81","target":"graph","created_at":"2026-07-29T00:25:11Z","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/2607.25268/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Ranking is a fundamental component of modern information access systems. Reinforcement learning (RL) provides a flexible framework for directly optimizing coarse-grained feedback and system-level objectives defined over the complete ranking list. However, existing RL-based ranking methods typically treat each sampled permutation as an atomic output and evaluate it primarily through a scalar reward, overlooking the structural relationships among different ranking lists. Consequently, permutations with similar rewards but substantially different permutation patterns may receive comparable optimi","authors_text":"Min Zhang, Qingyao Ai, Weihang Su, Yiqun Liu, Yiteng Tu, Zitao Su","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-28T04:13:47Z","title":"Structure-aware Relative Policy Optimization for Ranking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.25268","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":"sha256:1e8c57b56c93776f9ca0012f7b7474b8bd06ae3105df59d3f68c916b0a867237","target":"record","created_at":"2026-07-29T00:25:11Z","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":"9d63fba42945f189b69326f7d6fc241cacbeea61be2f02c9624d280f94546068","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-28T04:13:47Z","title_canon_sha256":"49768f9aeefcd05310079413195e0ef8e4848427c7c28f85487b69bb9387ea18"},"schema_version":"1.0","source":{"id":"2607.25268","kind":"arxiv","version":1}},"canonical_sha256":"3880bad03e9a678d4f0cdee58bf3443070d9d1bc3b10dbfa8c16e264851681ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3880bad03e9a678d4f0cdee58bf3443070d9d1bc3b10dbfa8c16e264851681ab","first_computed_at":"2026-07-29T00:25:11.911267Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-29T00:25:11.911267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b8xTUw6Vr7f/Evh1R1gS4WrO5k1d7henUeiwgjkTBjpU3rOsw/3ByqGqTn2Uy/FJ4STACoFx+yFetClzoIOjCA==","signature_status":"signed_v1","signed_at":"2026-07-29T00:25:11.912105Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.25268","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e8c57b56c93776f9ca0012f7b7474b8bd06ae3105df59d3f68c916b0a867237","sha256:50fc4947ebf388485c002153a0a3da21dab5f383372cd45c5261bf237fca9d81"],"state_sha256":"d36780aa3916c933d357544267fbf4bafc6809d4160929c25f24beb975905b4a"}