{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IVHD2WKQ7FHMZACR7JNOGIWFDK","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":"a8f015ebe488313aac6ab21a0fca3f0d4eeeba2b824c257a28724cf54677afa5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-02T03:25:26Z","title_canon_sha256":"2fe19874f31f64bfb97ec7e8fb6e71782d998ad8f904ca2d5a7386610efbe238"},"schema_version":"1.0","source":{"id":"2508.01174","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.01174","created_at":"2026-07-05T11:47:34Z"},{"alias_kind":"arxiv_version","alias_value":"2508.01174v1","created_at":"2026-07-05T11:47:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01174","created_at":"2026-07-05T11:47:34Z"},{"alias_kind":"pith_short_12","alias_value":"IVHD2WKQ7FHM","created_at":"2026-07-05T11:47:34Z"},{"alias_kind":"pith_short_16","alias_value":"IVHD2WKQ7FHMZACR","created_at":"2026-07-05T11:47:34Z"},{"alias_kind":"pith_short_8","alias_value":"IVHD2WKQ","created_at":"2026-07-05T11:47:34Z"}],"graph_snapshots":[{"event_id":"sha256:003591d7e75793e36e60f187ae30cddd8404983e1d80e92e65039c311a48da59","target":"graph","created_at":"2026-07-05T11:47:34Z","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/2508.01174/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current large language model post-training optimizes a risk-neutral objective that maximizes expected reward, yet evaluation relies heavily on risk-seeking metrics like Pass@k (at least one success in k trials) and Max@k (maximum reward across k responses). This mismatch in risk preferences can inevitably lead to suboptimal performance. To bridge this gap, we propose Risk-Seeking Policy Optimization (RSPO), a novel method that directly targets Pass@k and Max@k during training. A key challenge in optimizing these metrics is the \"hitchhiking\" problem: low-reward responses are inadvertently reinf","authors_text":"Haipeng Sun, Hong Dingqian, Hongfei Jiang, Hui Xiong, Junwei Bao, Kaichen Zhang, Shenghao Gao, Yang Song, Yuzhong Hong","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-02T03:25:26Z","title":"RSPO: Risk-Seeking Policy Optimization for Pass@k and Max@k Metrics in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01174","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":"sha256:62d72e3391ae7e5da2ad15e69a96a3180594f59413040475e64d5bfc4dcd7e83","target":"record","created_at":"2026-07-05T11:47:34Z","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":"a8f015ebe488313aac6ab21a0fca3f0d4eeeba2b824c257a28724cf54677afa5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-02T03:25:26Z","title_canon_sha256":"2fe19874f31f64bfb97ec7e8fb6e71782d998ad8f904ca2d5a7386610efbe238"},"schema_version":"1.0","source":{"id":"2508.01174","kind":"arxiv","version":1}},"canonical_sha256":"454e3d5950f94ecc8051fa5ae322c51a898c715e7ce145adebae4d5ae55608dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"454e3d5950f94ecc8051fa5ae322c51a898c715e7ce145adebae4d5ae55608dc","first_computed_at":"2026-07-05T11:47:34.244372Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:47:34.244372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qpvh66XpAoehAFPD71yyJ7oawDwJH12puMsPMNmxRBTAQi286frwCKfVAKY4ax2JAx5CDop6mLK31SzXVrtQCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:47:34.244809Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.01174","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62d72e3391ae7e5da2ad15e69a96a3180594f59413040475e64d5bfc4dcd7e83","sha256:003591d7e75793e36e60f187ae30cddd8404983e1d80e92e65039c311a48da59"],"state_sha256":"c1d5cba55fabdf5aa154fed74e3a6195fec2610735a2fcefeb08023dd3f6e339"}