{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2VIV47NJXTHS7DVXWFRWSRBTFP","short_pith_number":"pith:2VIV47NJ","canonical_record":{"source":{"id":"2506.18254","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-23T02:56:36Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"2a17d9a66fb4493818deda806861f729af3dce26117e57f222ee02b2ece62f12","abstract_canon_sha256":"3cd638ae934970c58da4a26d05593f878910d397c08668756d45325974f096dd"},"schema_version":"1.0"},"canonical_sha256":"d5515e7da9bccf2f8eb7b1636944332bd23dcfff886deb5c78faa6624a821ab4","source":{"kind":"arxiv","id":"2506.18254","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.18254","created_at":"2026-07-05T11:25:47Z"},{"alias_kind":"arxiv_version","alias_value":"2506.18254v1","created_at":"2026-07-05T11:25:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18254","created_at":"2026-07-05T11:25:47Z"},{"alias_kind":"pith_short_12","alias_value":"2VIV47NJXTHS","created_at":"2026-07-05T11:25:47Z"},{"alias_kind":"pith_short_16","alias_value":"2VIV47NJXTHS7DVX","created_at":"2026-07-05T11:25:47Z"},{"alias_kind":"pith_short_8","alias_value":"2VIV47NJ","created_at":"2026-07-05T11:25:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2VIV47NJXTHS7DVXWFRWSRBTFP","target":"record","payload":{"canonical_record":{"source":{"id":"2506.18254","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-23T02:56:36Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"2a17d9a66fb4493818deda806861f729af3dce26117e57f222ee02b2ece62f12","abstract_canon_sha256":"3cd638ae934970c58da4a26d05593f878910d397c08668756d45325974f096dd"},"schema_version":"1.0"},"canonical_sha256":"d5515e7da9bccf2f8eb7b1636944332bd23dcfff886deb5c78faa6624a821ab4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:47.026370Z","signature_b64":"Si/MyBhQfDfQKR11LP/Y1kyEvkOAtGyFa36euPSeDA9GIWoMv6f4Xc4mTxNvDPfOtYOWnRL0QptdBlDbzlORDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5515e7da9bccf2f8eb7b1636944332bd23dcfff886deb5c78faa6624a821ab4","last_reissued_at":"2026-07-05T11:25:47.025910Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:47.025910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.18254","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:25:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Iv4LFBh4/UEkfuNxrdplLfmUfxMiB/wXRRap1Fgj/7kqcgiPPYqwknqHEFEeMPCGeRQZZWclqZEy8EtAyZ2dBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T09:06:24.514955Z"},"content_sha256":"28ea303efb45d0737cced777879ee9ad2dd0177338bd63f6ee3aaa46961b72f0","schema_version":"1.0","event_id":"sha256:28ea303efb45d0737cced777879ee9ad2dd0177338bd63f6ee3aaa46961b72f0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2VIV47NJXTHS7DVXWFRWSRBTFP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RLPR: Extrapolating RLVR to General Domains without Verifiers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Bo Ji, Ganqu Cui, Lifan Yuan, Maosong Sun, Ning Ding, Shouli Wang, Shu Yao, Tat-Seng Chua, Tianyu Yu, Yuan Yao, Zefan Wang, Zhiyuan Liu","submitted_at":"2025-06-23T02:56:36Z","abstract_excerpt":"Reinforcement Learning with Verifiable Rewards (RLVR) demonstrates promising potential in advancing the reasoning capabilities of LLMs. However, its success remains largely confined to mathematical and code domains. This primary limitation stems from the heavy reliance on domain-specific verifiers, which results in prohibitive complexity and limited scalability. To address the challenge, our key observation is that LLM's intrinsic probability of generating a correct free-form answer directly indicates its own evaluation of the reasoning reward (i.e., how well the reasoning process leads to the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18254","kind":"arxiv","version":1},"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/2506.18254/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":"2026-07-05T11:25:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tid7OBi2v1VAafAf11r/LHP5pdjeftUMpyp/fidX4ox2Sz14Ea2IglaG7Az793DPehK2Fh3Eoi72j8CCib5sCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T09:06:24.515521Z"},"content_sha256":"eda32ccd78c236e604aed8acba2b6c404c44344a7a348abd3093c0aaa8ed9136","schema_version":"1.0","event_id":"sha256:eda32ccd78c236e604aed8acba2b6c404c44344a7a348abd3093c0aaa8ed9136"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2VIV47NJXTHS7DVXWFRWSRBTFP/bundle.json","state_url":"https://pith.science/pith/2VIV47NJXTHS7DVXWFRWSRBTFP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2VIV47NJXTHS7DVXWFRWSRBTFP/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":"2026-08-03T09:06:24Z","links":{"resolver":"https://pith.science/pith/2VIV47NJXTHS7DVXWFRWSRBTFP","bundle":"https://pith.science/pith/2VIV47NJXTHS7DVXWFRWSRBTFP/bundle.json","state":"https://pith.science/pith/2VIV47NJXTHS7DVXWFRWSRBTFP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2VIV47NJXTHS7DVXWFRWSRBTFP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2VIV47NJXTHS7DVXWFRWSRBTFP","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":"3cd638ae934970c58da4a26d05593f878910d397c08668756d45325974f096dd","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-23T02:56:36Z","title_canon_sha256":"2a17d9a66fb4493818deda806861f729af3dce26117e57f222ee02b2ece62f12"},"schema_version":"1.0","source":{"id":"2506.18254","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.18254","created_at":"2026-07-05T11:25:47Z"},{"alias_kind":"arxiv_version","alias_value":"2506.18254v1","created_at":"2026-07-05T11:25:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18254","created_at":"2026-07-05T11:25:47Z"},{"alias_kind":"pith_short_12","alias_value":"2VIV47NJXTHS","created_at":"2026-07-05T11:25:47Z"},{"alias_kind":"pith_short_16","alias_value":"2VIV47NJXTHS7DVX","created_at":"2026-07-05T11:25:47Z"},{"alias_kind":"pith_short_8","alias_value":"2VIV47NJ","created_at":"2026-07-05T11:25:47Z"}],"graph_snapshots":[{"event_id":"sha256:eda32ccd78c236e604aed8acba2b6c404c44344a7a348abd3093c0aaa8ed9136","target":"graph","created_at":"2026-07-05T11:25:47Z","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/2506.18254/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning with Verifiable Rewards (RLVR) demonstrates promising potential in advancing the reasoning capabilities of LLMs. However, its success remains largely confined to mathematical and code domains. This primary limitation stems from the heavy reliance on domain-specific verifiers, which results in prohibitive complexity and limited scalability. To address the challenge, our key observation is that LLM's intrinsic probability of generating a correct free-form answer directly indicates its own evaluation of the reasoning reward (i.e., how well the reasoning process leads to the","authors_text":"Bo Ji, Ganqu Cui, Lifan Yuan, Maosong Sun, Ning Ding, Shouli Wang, Shu Yao, Tat-Seng Chua, Tianyu Yu, Yuan Yao, Zefan Wang, Zhiyuan Liu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-23T02:56:36Z","title":"RLPR: Extrapolating RLVR to General Domains without Verifiers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18254","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":"sha256:28ea303efb45d0737cced777879ee9ad2dd0177338bd63f6ee3aaa46961b72f0","target":"record","created_at":"2026-07-05T11:25:47Z","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":"3cd638ae934970c58da4a26d05593f878910d397c08668756d45325974f096dd","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-23T02:56:36Z","title_canon_sha256":"2a17d9a66fb4493818deda806861f729af3dce26117e57f222ee02b2ece62f12"},"schema_version":"1.0","source":{"id":"2506.18254","kind":"arxiv","version":1}},"canonical_sha256":"d5515e7da9bccf2f8eb7b1636944332bd23dcfff886deb5c78faa6624a821ab4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d5515e7da9bccf2f8eb7b1636944332bd23dcfff886deb5c78faa6624a821ab4","first_computed_at":"2026-07-05T11:25:47.025910Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:47.025910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Si/MyBhQfDfQKR11LP/Y1kyEvkOAtGyFa36euPSeDA9GIWoMv6f4Xc4mTxNvDPfOtYOWnRL0QptdBlDbzlORDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:47.026370Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.18254","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28ea303efb45d0737cced777879ee9ad2dd0177338bd63f6ee3aaa46961b72f0","sha256:eda32ccd78c236e604aed8acba2b6c404c44344a7a348abd3093c0aaa8ed9136"],"state_sha256":"1249befde5fb61867a799bc8086eb6edaad913a795e221906ee80f9c246dbaa1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X1ihz9fCpKBc0OyoVsjteRuUO5O+wRbfjgy8ZYft0BFJFEhoTQb0u2CP/2a5mTsktrf9a1jMbu0fodbdVOGRBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T09:06:24.522133Z","bundle_sha256":"749dcd32593a5335e3ffa8a4edde287cf07fd2a54ba565d732d2aa9083863439"}}