{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UKG6RHDKYB2RW5DM46JYUJJOJY","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":"5ff7906b3ad95cc74a426adf7fe2bdd41f4c6072115d27f32de087925eda792d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T18:20:32Z","title_canon_sha256":"96fececb83b2c09d5e577a25bf258e9ad9db9ae2c2fd629627ffcb4c619a4958"},"schema_version":"1.0","source":{"id":"2605.30451","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30451","created_at":"2026-06-01T01:02:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30451v1","created_at":"2026-06-01T01:02:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30451","created_at":"2026-06-01T01:02:55Z"},{"alias_kind":"pith_short_12","alias_value":"UKG6RHDKYB2R","created_at":"2026-06-01T01:02:55Z"},{"alias_kind":"pith_short_16","alias_value":"UKG6RHDKYB2RW5DM","created_at":"2026-06-01T01:02:55Z"},{"alias_kind":"pith_short_8","alias_value":"UKG6RHDK","created_at":"2026-06-01T01:02:55Z"}],"graph_snapshots":[{"event_id":"sha256:f3e9aa0136efb412cbc140f655d0d25bb5b5ac51de76da00cf5a4224f8b4a281","target":"graph","created_at":"2026-06-01T01:02:55Z","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/2605.30451/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Group Relative Policy Optimization (GRPO) is an effective recipe for training reasoning models with verifier-based outcome rewards, but its supervision is sparse: when all sampled trajectories for a prompt receive the same verifier reward, the group-relative advantage collapses to zero and learning stalls. Outcome-only rewards also provide no step-level credit assignment, limiting exploration and making it harder to learn robust reasoning. We present VeriGate (Verifier-Gated Step-Level GRPO), a verifier-gated extension of GRPO that addresses these limitations with three design choices. First, ","authors_text":"Aakriti Agrawal, Furong Huang, Minghui Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T18:20:32Z","title":"VeriGate: Verifier-Gated Step-Level Supervision for GRPO"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30451","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":"sha256:6b69de2a3309e81d4c8d2a498214ba773c47275eca49e391b112926419406209","target":"record","created_at":"2026-06-01T01:02:55Z","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":"5ff7906b3ad95cc74a426adf7fe2bdd41f4c6072115d27f32de087925eda792d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T18:20:32Z","title_canon_sha256":"96fececb83b2c09d5e577a25bf258e9ad9db9ae2c2fd629627ffcb4c619a4958"},"schema_version":"1.0","source":{"id":"2605.30451","kind":"arxiv","version":1}},"canonical_sha256":"a28de89c6ac0751b746ce7938a252e4e1b13e25daccbf909d83ebc80ae680adb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a28de89c6ac0751b746ce7938a252e4e1b13e25daccbf909d83ebc80ae680adb","first_computed_at":"2026-06-01T01:02:55.004571Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:02:55.004571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/le32pXuEz3ptWRHIfWf7GSwIZYOxWa+X9EDY3kRlRpwDvjOOppSBCoAbeizutOTyPdWnrkr7HOSIiacfQv8DQ==","signature_status":"signed_v1","signed_at":"2026-06-01T01:02:55.005643Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30451","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b69de2a3309e81d4c8d2a498214ba773c47275eca49e391b112926419406209","sha256:f3e9aa0136efb412cbc140f655d0d25bb5b5ac51de76da00cf5a4224f8b4a281"],"state_sha256":"f708b4cc697023c74826cb84ea0ab626c06deb54669bb47eefb923e411152ac4"}