{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:Y2U5NYVN4EKXZONIBXZ54TTMBH","short_pith_number":"pith:Y2U5NYVN","canonical_record":{"source":{"id":"2503.23829","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-31T08:22:49Z","cross_cats_sorted":[],"title_canon_sha256":"b2d59fffc3d2b4b9866e4ed14c455763266ab281591c507d802a5c399c537f56","abstract_canon_sha256":"ce205d715eee78df98d3cc04f2f4f6f9bbea23f1173f7b9eb925540abd4e5473"},"schema_version":"1.0"},"canonical_sha256":"c6a9d6e2ade1157cb9a80df3de4e6c09f73ca6055127bfd264a6ce57288cb4fe","source":{"kind":"arxiv","id":"2503.23829","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.23829","created_at":"2026-07-05T10:42:46Z"},{"alias_kind":"arxiv_version","alias_value":"2503.23829v2","created_at":"2026-07-05T10:42:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23829","created_at":"2026-07-05T10:42:46Z"},{"alias_kind":"pith_short_12","alias_value":"Y2U5NYVN4EKX","created_at":"2026-07-05T10:42:46Z"},{"alias_kind":"pith_short_16","alias_value":"Y2U5NYVN4EKXZONI","created_at":"2026-07-05T10:42:46Z"},{"alias_kind":"pith_short_8","alias_value":"Y2U5NYVN","created_at":"2026-07-05T10:42:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:Y2U5NYVN4EKXZONIBXZ54TTMBH","target":"record","payload":{"canonical_record":{"source":{"id":"2503.23829","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-31T08:22:49Z","cross_cats_sorted":[],"title_canon_sha256":"b2d59fffc3d2b4b9866e4ed14c455763266ab281591c507d802a5c399c537f56","abstract_canon_sha256":"ce205d715eee78df98d3cc04f2f4f6f9bbea23f1173f7b9eb925540abd4e5473"},"schema_version":"1.0"},"canonical_sha256":"c6a9d6e2ade1157cb9a80df3de4e6c09f73ca6055127bfd264a6ce57288cb4fe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:46.087755Z","signature_b64":"L8Yy82mXbT8r/qqtpARzIjbyzTnc9VsProWZtH57y20caQZP5wwjsFXl6EZv2QfLkk9pZBgA5Nuk9I8fmY7GCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6a9d6e2ade1157cb9a80df3de4e6c09f73ca6055127bfd264a6ce57288cb4fe","last_reissued_at":"2026-07-05T10:42:46.087253Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:46.087253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.23829","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:42:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QiFXumbMwJOZ8eingJgHr0WFQj11SJo7bMQxnGaSNAM3MZqKsYOmAljrssxNSNxS/ud4sPE7y7d3k97WPXaOBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:46:30.659422Z"},"content_sha256":"57a5191ac5a12cbeda5995074eb9e89e59bbb5a89f793ee0dc224a7f70d674d6","schema_version":"1.0","event_id":"sha256:57a5191ac5a12cbeda5995074eb9e89e59bbb5a89f793ee0dc224a7f70d674d6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:Y2U5NYVN4EKXZONIBXZ54TTMBH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dian Yu, Dong Yu, Haitao Mi, Juntao Li, Linfeng Song, Min Zhang, Yi Su, Zhaopeng Tu","submitted_at":"2025-03-31T08:22:49Z","abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) has demonstrated significant success in enhancing mathematical reasoning and coding performance of large language models (LLMs), especially when structured reference answers are accessible for verification. However, its extension to broader, less structured domains remains unexplored. In this work, we investigate the effectiveness and scalability of RLVR across diverse real-world domains including medicine, chemistry, psychology, economics, and education, where structured reference answers are typically unavailable. We reveal that binary ve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23829","kind":"arxiv","version":2},"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/2503.23829/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":"2026-07-05T10:42:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lh8D6Kbo4xiVhxqAZGmLWBM9+0wYkgJAj0GemcU85Od42pQMf1dWJkvWr0DrKMztyR2iEHirloLrNf8uBxGlDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:46:30.660321Z"},"content_sha256":"26b19ef4ae4ed505291f57fd5f394865c63b87f3bbb8a010c1b579dbda963ab8","schema_version":"1.0","event_id":"sha256:26b19ef4ae4ed505291f57fd5f394865c63b87f3bbb8a010c1b579dbda963ab8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y2U5NYVN4EKXZONIBXZ54TTMBH/bundle.json","state_url":"https://pith.science/pith/Y2U5NYVN4EKXZONIBXZ54TTMBH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y2U5NYVN4EKXZONIBXZ54TTMBH/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":"2026-08-04T05:46:30Z","links":{"resolver":"https://pith.science/pith/Y2U5NYVN4EKXZONIBXZ54TTMBH","bundle":"https://pith.science/pith/Y2U5NYVN4EKXZONIBXZ54TTMBH/bundle.json","state":"https://pith.science/pith/Y2U5NYVN4EKXZONIBXZ54TTMBH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y2U5NYVN4EKXZONIBXZ54TTMBH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Y2U5NYVN4EKXZONIBXZ54TTMBH","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":"ce205d715eee78df98d3cc04f2f4f6f9bbea23f1173f7b9eb925540abd4e5473","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-31T08:22:49Z","title_canon_sha256":"b2d59fffc3d2b4b9866e4ed14c455763266ab281591c507d802a5c399c537f56"},"schema_version":"1.0","source":{"id":"2503.23829","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.23829","created_at":"2026-07-05T10:42:46Z"},{"alias_kind":"arxiv_version","alias_value":"2503.23829v2","created_at":"2026-07-05T10:42:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23829","created_at":"2026-07-05T10:42:46Z"},{"alias_kind":"pith_short_12","alias_value":"Y2U5NYVN4EKX","created_at":"2026-07-05T10:42:46Z"},{"alias_kind":"pith_short_16","alias_value":"Y2U5NYVN4EKXZONI","created_at":"2026-07-05T10:42:46Z"},{"alias_kind":"pith_short_8","alias_value":"Y2U5NYVN","created_at":"2026-07-05T10:42:46Z"}],"graph_snapshots":[{"event_id":"sha256:26b19ef4ae4ed505291f57fd5f394865c63b87f3bbb8a010c1b579dbda963ab8","target":"graph","created_at":"2026-07-05T10:42:46Z","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/2503.23829/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) has demonstrated significant success in enhancing mathematical reasoning and coding performance of large language models (LLMs), especially when structured reference answers are accessible for verification. However, its extension to broader, less structured domains remains unexplored. In this work, we investigate the effectiveness and scalability of RLVR across diverse real-world domains including medicine, chemistry, psychology, economics, and education, where structured reference answers are typically unavailable. We reveal that binary ve","authors_text":"Dian Yu, Dong Yu, Haitao Mi, Juntao Li, Linfeng Song, Min Zhang, Yi Su, Zhaopeng Tu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-31T08:22:49Z","title":"Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23829","kind":"arxiv","version":2},"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":"sha256:57a5191ac5a12cbeda5995074eb9e89e59bbb5a89f793ee0dc224a7f70d674d6","target":"record","created_at":"2026-07-05T10:42:46Z","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":"ce205d715eee78df98d3cc04f2f4f6f9bbea23f1173f7b9eb925540abd4e5473","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-31T08:22:49Z","title_canon_sha256":"b2d59fffc3d2b4b9866e4ed14c455763266ab281591c507d802a5c399c537f56"},"schema_version":"1.0","source":{"id":"2503.23829","kind":"arxiv","version":2}},"canonical_sha256":"c6a9d6e2ade1157cb9a80df3de4e6c09f73ca6055127bfd264a6ce57288cb4fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6a9d6e2ade1157cb9a80df3de4e6c09f73ca6055127bfd264a6ce57288cb4fe","first_computed_at":"2026-07-05T10:42:46.087253Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:42:46.087253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L8Yy82mXbT8r/qqtpARzIjbyzTnc9VsProWZtH57y20caQZP5wwjsFXl6EZv2QfLkk9pZBgA5Nuk9I8fmY7GCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:42:46.087755Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.23829","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57a5191ac5a12cbeda5995074eb9e89e59bbb5a89f793ee0dc224a7f70d674d6","sha256:26b19ef4ae4ed505291f57fd5f394865c63b87f3bbb8a010c1b579dbda963ab8"],"state_sha256":"a3d901eded14c019f382a751ff4c016a6245d7fac05d6f946e8930094c1e826a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QXwoUoGpQXwsXt9BsmDcB3bMG+qoy0+ZUIYXpUeDqhMNLy3nfxJkjIhUf4I646vYmetlx9TVTSSKkDVkB/L4Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T05:46:30.666097Z","bundle_sha256":"cbef77e6c6dc1afdcd3318208f7b45bbe29eb096e6a7b64802ab8518a7b538df"}}