{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TIWRX7BTCFURL7PW573LTH4P4Z","short_pith_number":"pith:TIWRX7BT","canonical_record":{"source":{"id":"2505.15201","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-21T07:26:36Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"90d89e7ce72416ed6a2ad23373530035cb46361592633dbe9c0556e84fac5da3","abstract_canon_sha256":"4ec49d561b89fbf40f89fdfe3c5f1fa2d6c62eca4335bca041152819f59c39ff"},"schema_version":"1.0"},"canonical_sha256":"9a2d1bfc33116915fdf6eff6b99f8fe67f254b191e3a8108d2f3b262b38b8bb7","source":{"kind":"arxiv","id":"2505.15201","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TIWRX7BTCFURL7PW573LTH4P4Z","target":"record","payload":{"canonical_record":{"source":{"id":"2505.15201","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-21T07:26:36Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"90d89e7ce72416ed6a2ad23373530035cb46361592633dbe9c0556e84fac5da3","abstract_canon_sha256":"4ec49d561b89fbf40f89fdfe3c5f1fa2d6c62eca4335bca041152819f59c39ff"},"schema_version":"1.0"},"canonical_sha256":"9a2d1bfc33116915fdf6eff6b99f8fe67f254b191e3a8108d2f3b262b38b8bb7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:09:13.385898Z","signature_b64":"zV07tIsMKHhR1c8UhhTHkD2bK5e4ErQ9Eeven/4jq45fw3sLDaxQX270EnVsuTbDfPRE/l04AJDZxMvH2yqkCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a2d1bfc33116915fdf6eff6b99f8fe67f254b191e3a8108d2f3b262b38b8bb7","last_reissued_at":"2026-06-11T01:09:13.385182Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:09:13.385182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.15201","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-11T01:09:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2eritFTte8v+bpTDqqY/Hvx1zykHwZ0ANTFsNtVNq9NYeXO+aXVg7JL4itJUzV4Ce35X7g6ir4uJK8ZjsO6fCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T00:43:39.714876Z"},"content_sha256":"f98233e8ff0814d00d58717549200eb0a5dda648c6dd4ea876aa0c327d69cd2a","schema_version":"1.0","event_id":"sha256:f98233e8ff0814d00d58717549200eb0a5dda648c6dd4ea876aa0c327d69cd2a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TIWRX7BTCFURL7PW573LTH4P4Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christian Walder, Deep Karkhanis","submitted_at":"2025-05-21T07:26:36Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15201","kind":"arxiv","version":5},"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/2505.15201/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":"2026-06-11T01:09:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u3BgkKMS8N49B2iXDKiKU3xKwOgZwGmGzM/5VQOCoToNQPVqnsiRrcceqFXubvc0KYP3k+E4USuo1OfrpEG9Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T00:43:39.715492Z"},"content_sha256":"466ae6bf43651a854e23fb388d3c13b0751da8a49dd95bfd7c2eb7457d19ed2c","schema_version":"1.0","event_id":"sha256:466ae6bf43651a854e23fb388d3c13b0751da8a49dd95bfd7c2eb7457d19ed2c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TIWRX7BTCFURL7PW573LTH4P4Z/bundle.json","state_url":"https://pith.science/pith/TIWRX7BTCFURL7PW573LTH4P4Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TIWRX7BTCFURL7PW573LTH4P4Z/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":"2026-07-01T00:43:39Z","links":{"resolver":"https://pith.science/pith/TIWRX7BTCFURL7PW573LTH4P4Z","bundle":"https://pith.science/pith/TIWRX7BTCFURL7PW573LTH4P4Z/bundle.json","state":"https://pith.science/pith/TIWRX7BTCFURL7PW573LTH4P4Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TIWRX7BTCFURL7PW573LTH4P4Z/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u1LAf2OYZbJXvvJxL2AtHoZj9Ycknfsx4rdenxjgsIdRrLPoiMhG//PvFyL5W329RQJZrf5sqJMhSUGWzS+yBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-01T00:43:39.718453Z","bundle_sha256":"4ea8a9591f195f38e4e1ce8146b4192ef82e5f61d99e8ac86d7f7457db4e8ffd"}}