{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TIWRX7BTCFURL7PW573LTH4P4Z","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":"4ec49d561b89fbf40f89fdfe3c5f1fa2d6c62eca4335bca041152819f59c39ff","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-21T07:26:36Z","title_canon_sha256":"90d89e7ce72416ed6a2ad23373530035cb46361592633dbe9c0556e84fac5da3"},"schema_version":"1.0","source":{"id":"2505.15201","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.15201","created_at":"2026-06-11T01:09:13Z"},{"alias_kind":"arxiv_version","alias_value":"2505.15201v5","created_at":"2026-06-11T01:09:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15201","created_at":"2026-06-11T01:09:13Z"},{"alias_kind":"pith_short_12","alias_value":"TIWRX7BTCFUR","created_at":"2026-06-11T01:09:13Z"},{"alias_kind":"pith_short_16","alias_value":"TIWRX7BTCFURL7PW","created_at":"2026-06-11T01:09:13Z"},{"alias_kind":"pith_short_8","alias_value":"TIWRX7BT","created_at":"2026-06-11T01:09:13Z"}],"graph_snapshots":[{"event_id":"sha256:466ae6bf43651a854e23fb388d3c13b0751da8a49dd95bfd7c2eb7457d19ed2c","target":"graph","created_at":"2026-06-11T01:09:13Z","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/2505.15201/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) algorithms sample multiple n>1 solution attempts for each problem and reward them independently. This optimizes for pass@1 performance and prioritizes the strength of isolated samples at the expense of the diversity and collective utility of sets of samples. This under-utilizes the sampling capacity, limiting exploration and eventual improvement on harder examples. As a fix, we propose Pass-at-k Policy Optimization (PKPO), a transformation on the final rewards which leads to direct optimization of pass@k performance, thus optimizing for sets of samples that maximize","authors_text":"Christian Walder, Deep Karkhanis","cross_cats":["cs.AI","cs.CL","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-21T07:26:36Z","title":"Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15201","kind":"arxiv","version":5},"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:f98233e8ff0814d00d58717549200eb0a5dda648c6dd4ea876aa0c327d69cd2a","target":"record","created_at":"2026-06-11T01:09:13Z","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":"4ec49d561b89fbf40f89fdfe3c5f1fa2d6c62eca4335bca041152819f59c39ff","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-21T07:26:36Z","title_canon_sha256":"90d89e7ce72416ed6a2ad23373530035cb46361592633dbe9c0556e84fac5da3"},"schema_version":"1.0","source":{"id":"2505.15201","kind":"arxiv","version":5}},"canonical_sha256":"9a2d1bfc33116915fdf6eff6b99f8fe67f254b191e3a8108d2f3b262b38b8bb7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a2d1bfc33116915fdf6eff6b99f8fe67f254b191e3a8108d2f3b262b38b8bb7","first_computed_at":"2026-06-11T01:09:13.385182Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:09:13.385182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zV07tIsMKHhR1c8UhhTHkD2bK5e4ErQ9Eeven/4jq45fw3sLDaxQX270EnVsuTbDfPRE/l04AJDZxMvH2yqkCQ==","signature_status":"signed_v1","signed_at":"2026-06-11T01:09:13.385898Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.15201","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f98233e8ff0814d00d58717549200eb0a5dda648c6dd4ea876aa0c327d69cd2a","sha256:466ae6bf43651a854e23fb388d3c13b0751da8a49dd95bfd7c2eb7457d19ed2c"],"state_sha256":"71e0802fe6113eda1c9a2a024ca277827fa04e9abfedb5814c750d52b8c59c30"}