{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DMYZIDMHSZX7VGA3RRPDDVVIRN","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":"8af8bf445927ffef654f5ae3e49aff2d9445c87057dc5a475506d5f30b2f40a0","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T12:34:15Z","title_canon_sha256":"ada7f497879153bd9912be16ca1eae2314fd6feb81b7023afd32f9840c3f8498"},"schema_version":"1.0","source":{"id":"2606.06096","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.06096","created_at":"2026-06-05T01:15:33Z"},{"alias_kind":"arxiv_version","alias_value":"2606.06096v1","created_at":"2026-06-05T01:15:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06096","created_at":"2026-06-05T01:15:33Z"},{"alias_kind":"pith_short_12","alias_value":"DMYZIDMHSZX7","created_at":"2026-06-05T01:15:33Z"},{"alias_kind":"pith_short_16","alias_value":"DMYZIDMHSZX7VGA3","created_at":"2026-06-05T01:15:33Z"},{"alias_kind":"pith_short_8","alias_value":"DMYZIDMH","created_at":"2026-06-05T01:15:33Z"}],"graph_snapshots":[{"event_id":"sha256:286926d1b16e2a19c5769c3b3f9489cdbf0e072dcffbdeeba628f6e0fc8af7be","target":"graph","created_at":"2026-06-05T01:15:33Z","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/2606.06096/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Policy-gradient methods usually optimize expected return, but many real world applications care about distributional properties of returns: tail risk, outlier robustness, or best-of-K discovery. We introduce OrderGrad, a family of likelihood-ratio and reparameterization gradient estimators for order-statistic objectives. OrderGrad optimizes finite-sample L-statistics, i.e., weighted averages of sorted rewards or costs, recovering objectives such as VaR, CVaR, trimmed means, medians, and top-m/best-of-K criteria by changing only the rank weights. For any fixed sample size and rank-weight vector","authors_text":"Kohsei Matsutani, Paavo Parmas, Shota Takashiro, Soichiro Nishimori, Takeshi Kojima, Yongmin Kim, Yusuke Iwasawa, Yutaka Matsuo","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T12:34:15Z","title":"OrderGrad: Optimizing Beyond the Mean with Order-Statistic Policy Gradient Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06096","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:eb7e8649c51afaaa8e5088d15ed0f01236891ba265b0aa6f08b87d010bd10bd8","target":"record","created_at":"2026-06-05T01:15:33Z","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":"8af8bf445927ffef654f5ae3e49aff2d9445c87057dc5a475506d5f30b2f40a0","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T12:34:15Z","title_canon_sha256":"ada7f497879153bd9912be16ca1eae2314fd6feb81b7023afd32f9840c3f8498"},"schema_version":"1.0","source":{"id":"2606.06096","kind":"arxiv","version":1}},"canonical_sha256":"1b31940d87966ffa981b8c5e31d6a88b4e8908e7181e993f3d13d91a708b29e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b31940d87966ffa981b8c5e31d6a88b4e8908e7181e993f3d13d91a708b29e8","first_computed_at":"2026-06-05T01:15:33.194206Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:33.194206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"asDLvYmZa4RVXtW6zdb4sJzWZuRe6UoIBbq93Vt5hSRn/RNXiaEp8v76TPbeugfSQ+2Xs6O+GicDyR72feokCQ==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:33.194942Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.06096","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb7e8649c51afaaa8e5088d15ed0f01236891ba265b0aa6f08b87d010bd10bd8","sha256:286926d1b16e2a19c5769c3b3f9489cdbf0e072dcffbdeeba628f6e0fc8af7be"],"state_sha256":"44c8fb4a5fd4e560e23e12a68f6cb964a81455e069625df9bcc0770c5ed5606d"}