{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2JEXCPFC5XJPE4LYBW4TNS4ZFF","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":"a5dff8782148ee06b2cd7389d0bd841f8a66d7e267103ab653a332d943444cbb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-07T17:57:09Z","title_canon_sha256":"6b73dd8af29ab8316024629bc1637021eb3ad5729ad07f23223c23754d231977"},"schema_version":"1.0","source":{"id":"2508.05618","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.05618","created_at":"2026-07-05T11:50:22Z"},{"alias_kind":"arxiv_version","alias_value":"2508.05618v1","created_at":"2026-07-05T11:50:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.05618","created_at":"2026-07-05T11:50:22Z"},{"alias_kind":"pith_short_12","alias_value":"2JEXCPFC5XJP","created_at":"2026-07-05T11:50:22Z"},{"alias_kind":"pith_short_16","alias_value":"2JEXCPFC5XJPE4LY","created_at":"2026-07-05T11:50:22Z"},{"alias_kind":"pith_short_8","alias_value":"2JEXCPFC","created_at":"2026-07-05T11:50:22Z"}],"graph_snapshots":[{"event_id":"sha256:5644b02403c54a63739f736ab015cc3629111478137606a89acdba2a43c36b56","target":"graph","created_at":"2026-07-05T11:50:22Z","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/2508.05618/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reasoning Large Language Models (R-LLMs) have significantly advanced complex reasoning tasks but often struggle with factuality, generating substantially more hallucinations than their non-reasoning counterparts on long-form factuality benchmarks. However, extending online Reinforcement Learning (RL), a key component in recent R-LLM advancements, to the long-form factuality setting poses several unique challenges due to the lack of reliable verification methods. Previous work has utilized automatic factuality evaluation frameworks such as FActScore to curate preference data in the offline RL s","authors_text":"Barlas O\\u{g}uz, Gargi Ghosh, Ilia Kulikov, Jason Weston, Rulin Shao, Vincent-Pierre Berges, Wen-tau Yih, Xilun Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-07T17:57:09Z","title":"Learning to Reason for Factuality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.05618","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:e1d2060eab53240ea6fa0cbf925f8c068ab9bd535eef21b14246ac8510c864d4","target":"record","created_at":"2026-07-05T11:50:22Z","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":"a5dff8782148ee06b2cd7389d0bd841f8a66d7e267103ab653a332d943444cbb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-07T17:57:09Z","title_canon_sha256":"6b73dd8af29ab8316024629bc1637021eb3ad5729ad07f23223c23754d231977"},"schema_version":"1.0","source":{"id":"2508.05618","kind":"arxiv","version":1}},"canonical_sha256":"d249713ca2edd2f271780db936cb99297c9514d130f39745452b9af6f9be0fec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d249713ca2edd2f271780db936cb99297c9514d130f39745452b9af6f9be0fec","first_computed_at":"2026-07-05T11:50:22.634599Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:50:22.634599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JF5RvGz2cqlenyQhJY2hNpxDfPPDuyihXwA15+1iL+cklnpH0NJa9XBWQL6TqGrLVpCAlw4S1tW0ixGGCFb7AA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:50:22.635192Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.05618","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1d2060eab53240ea6fa0cbf925f8c068ab9bd535eef21b14246ac8510c864d4","sha256:5644b02403c54a63739f736ab015cc3629111478137606a89acdba2a43c36b56"],"state_sha256":"f8e6b85197debf7f9a50f8028f006ad117500fad6e9e64a48d010175b7c87df6"}