{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PIFO2Z2SQJHT3W5Z7BLZY6WHHE","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":"676ae3e81a4b0603b47a35d9e4a1ca6a8e4ab3a14efae500f17eb9289a98e3db","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-14T03:45:24Z","title_canon_sha256":"d34f58071fc1f87ab61a23d699cfd83c8c66fac604aa7a016937ebeb3a93315c"},"schema_version":"1.0","source":{"id":"2507.09884","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.09884","created_at":"2026-07-05T11:43:33Z"},{"alias_kind":"arxiv_version","alias_value":"2507.09884v3","created_at":"2026-07-05T11:43:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09884","created_at":"2026-07-05T11:43:33Z"},{"alias_kind":"pith_short_12","alias_value":"PIFO2Z2SQJHT","created_at":"2026-07-05T11:43:33Z"},{"alias_kind":"pith_short_16","alias_value":"PIFO2Z2SQJHT3W5Z","created_at":"2026-07-05T11:43:33Z"},{"alias_kind":"pith_short_8","alias_value":"PIFO2Z2S","created_at":"2026-07-05T11:43:33Z"}],"graph_snapshots":[{"event_id":"sha256:ab9dc46d05d1485066bc4ec0676a0251663082b003bd3a5200e8fcc6ec91083b","target":"graph","created_at":"2026-07-05T11:43:33Z","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/2507.09884/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) increasingly rely on reinforcement learning (RL) to enhance their reasoning capabilities through feedback. A critical challenge is verifying the consistency of model-generated responses and reference answers, since these responses are often lengthy, diverse, and nuanced. Rule-based verifiers struggle with complexity, prompting the use of model-based verifiers. However, specialized verifiers lack flexibility, while general LLM judges can be inconsistent. Existing research primarily focuses on building better verifiers, yet a systematic evaluation of different types ","authors_text":"Shiyu Hu, Wentao Zhang, Xuchen Li, Xuzhao Li, Yongzhen Guo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-14T03:45:24Z","title":"VerifyBench: A Systematic Benchmark for Evaluating Reasoning Verifiers Across Domains"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09884","kind":"arxiv","version":3},"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":"sha256:7340bc069741bee3830cef6a335db78e1e77fd44240314a27dc7c66e01ee65b9","target":"record","created_at":"2026-07-05T11:43:33Z","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":"676ae3e81a4b0603b47a35d9e4a1ca6a8e4ab3a14efae500f17eb9289a98e3db","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-14T03:45:24Z","title_canon_sha256":"d34f58071fc1f87ab61a23d699cfd83c8c66fac604aa7a016937ebeb3a93315c"},"schema_version":"1.0","source":{"id":"2507.09884","kind":"arxiv","version":3}},"canonical_sha256":"7a0aed6752824f3ddbb9f8579c7ac73929bd7a4eab9cfbdfcf2292ed0dcace5e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a0aed6752824f3ddbb9f8579c7ac73929bd7a4eab9cfbdfcf2292ed0dcace5e","first_computed_at":"2026-07-05T11:43:33.571579Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:33.571579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Dv+VtXsMWgkOrQYXdwltcgjOOrQ76AYfehlsvyn/7LANIlZQRPjdVN2t0nOrCcYYgHvW0dbld8bIBaG/jWBrBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:33.571976Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.09884","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7340bc069741bee3830cef6a335db78e1e77fd44240314a27dc7c66e01ee65b9","sha256:ab9dc46d05d1485066bc4ec0676a0251663082b003bd3a5200e8fcc6ec91083b"],"state_sha256":"d7c2d0fe503ec3ed16530af919e359895542a11525f6fae7354e0520f895049d"}