{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4H7LDMYF2HZSJ35LMFQ2KYRJDN","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":"7ffc631c84742bc6c0104b99ae447e4145d4c693466fad332a6ef096e4a56279","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-27T17:56:27Z","title_canon_sha256":"58c1b0e670a17182215c7c346655631d450a494274814fcd36231bd1e737466c"},"schema_version":"1.0","source":{"id":"2505.21493","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21493","created_at":"2026-07-05T11:10:42Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21493v1","created_at":"2026-07-05T11:10:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21493","created_at":"2026-07-05T11:10:42Z"},{"alias_kind":"pith_short_12","alias_value":"4H7LDMYF2HZS","created_at":"2026-07-05T11:10:42Z"},{"alias_kind":"pith_short_16","alias_value":"4H7LDMYF2HZSJ35L","created_at":"2026-07-05T11:10:42Z"},{"alias_kind":"pith_short_8","alias_value":"4H7LDMYF","created_at":"2026-07-05T11:10:42Z"}],"graph_snapshots":[{"event_id":"sha256:c8a88d3eb5ad52b0f96397c5cc2517c04d795a98cf4c46e00e621401fe931fc2","target":"graph","created_at":"2026-07-05T11:10:42Z","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/2505.21493/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent paradigm shift towards training large language models (LLMs) using DeepSeek-R1-Zero-style reinforcement learning (RL) on verifiable rewards has led to impressive advancements in code and mathematical reasoning. However, this methodology is limited to tasks where rule-based answer verification is possible and does not naturally extend to real-world domains such as chemistry, healthcare, engineering, law, biology, business, and economics. Current practical workarounds use an additional LLM as a model-based verifier; however, this introduces issues such as reliance on a strong verifier","authors_text":"Anya Sims, Chao Du, Chongxuan Li, Haonan Wang, Liang Wang, Min Lin, Tianyu Pang, Xiangxin Zhou, Zichen Liu","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-27T17:56:27Z","title":"Reinforcing General Reasoning without Verifiers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21493","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:faa43dfd42e6be0fead6c3f654c7e164948f60ba9b114778614b4acda928e50b","target":"record","created_at":"2026-07-05T11:10:42Z","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":"7ffc631c84742bc6c0104b99ae447e4145d4c693466fad332a6ef096e4a56279","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-27T17:56:27Z","title_canon_sha256":"58c1b0e670a17182215c7c346655631d450a494274814fcd36231bd1e737466c"},"schema_version":"1.0","source":{"id":"2505.21493","kind":"arxiv","version":1}},"canonical_sha256":"e1feb1b305d1f324efab6161a562291b5c59ee1990d406d0e9075b555e9d5599","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e1feb1b305d1f324efab6161a562291b5c59ee1990d406d0e9075b555e9d5599","first_computed_at":"2026-07-05T11:10:42.750401Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:42.750401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NvyzoJleLxDwAb/+hCGi2TYPeoLP0YSCjuTd6Nu/NgWDqIEdphgFEKxUcCOxCj+jVcrtorjodOQu44GNYsUTDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:42.750895Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.21493","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:faa43dfd42e6be0fead6c3f654c7e164948f60ba9b114778614b4acda928e50b","sha256:c8a88d3eb5ad52b0f96397c5cc2517c04d795a98cf4c46e00e621401fe931fc2"],"state_sha256":"db7c323c026da080111500b2e6c220da475194d63f22ec98450b1d696e1a8141"}