{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EOLWVEHWQBFTQV3CPZV65YTJF3","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":"a7a70a008dd9b48a096c43139cb5eb4d58e7d496a3623bbebc1858a83a211315","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-11-29T04:47:14Z","title_canon_sha256":"db7e47ddfe2ccdf167877168c2d7bbab475c45ba152833aa53e990f963d85dc4"},"schema_version":"1.0","source":{"id":"2512.00319","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.00319","created_at":"2026-07-20T00:18:16Z"},{"alias_kind":"arxiv_version","alias_value":"2512.00319v3","created_at":"2026-07-20T00:18:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.00319","created_at":"2026-07-20T00:18:16Z"},{"alias_kind":"pith_short_12","alias_value":"EOLWVEHWQBFT","created_at":"2026-07-20T00:18:16Z"},{"alias_kind":"pith_short_16","alias_value":"EOLWVEHWQBFTQV3C","created_at":"2026-07-20T00:18:16Z"},{"alias_kind":"pith_short_8","alias_value":"EOLWVEHW","created_at":"2026-07-20T00:18:16Z"}],"graph_snapshots":[{"event_id":"sha256:6db0c8e0b936dae4eeb7b569843afcd324a418dab0b58b1764d9f914eeea72f7","target":"graph","created_at":"2026-07-20T00:18:16Z","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/2512.00319/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Structure Gap between probabilistic LLM generation and deterministic schema requirements hinders automated workflows. We propose RL-Struct, a lightweight framework using Gradient Regularized Policy Optimization (GRPO) with a hierarchical reward function to align LLMs with structural constraints. This approach eliminates the critic network, reducing peak VRAM by 38% compared to PPO. On complex JSON tasks, RL-Struct achieves 89.7% structural accuracy and 92.1% validity, significantly outperforming SFT and zero-shot baselines. We also report an emergent curriculum--a self-organized learning p","authors_text":"Ruike Hu, Shulei Wu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-11-29T04:47:14Z","title":"RL-Struct: A Lightweight Reinforcement Learning Framework for Reliable Structured Output in LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.00319","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":"sha256:40a9c843fb7744c59bf5b15657305721b8854b94e52b8bdaefaeda90d23a2bd6","target":"record","created_at":"2026-07-20T00:18:16Z","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":"a7a70a008dd9b48a096c43139cb5eb4d58e7d496a3623bbebc1858a83a211315","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-11-29T04:47:14Z","title_canon_sha256":"db7e47ddfe2ccdf167877168c2d7bbab475c45ba152833aa53e990f963d85dc4"},"schema_version":"1.0","source":{"id":"2512.00319","kind":"arxiv","version":3}},"canonical_sha256":"23976a90f6804b3857627e6beee2692ec55bc58d84e77df5cf40ae5ee9ef0594","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23976a90f6804b3857627e6beee2692ec55bc58d84e77df5cf40ae5ee9ef0594","first_computed_at":"2026-07-20T00:18:16.190441Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-20T00:18:16.190441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+EKU93VnD3V/JIFA2x4xWmDMXdTmBMO0MnQ/4xZ7sw/lMBGellqnhy5zLqVWx7ANjlwCSyqamSSyyd93/aLhCQ==","signature_status":"signed_v1","signed_at":"2026-07-20T00:18:16.191430Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.00319","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40a9c843fb7744c59bf5b15657305721b8854b94e52b8bdaefaeda90d23a2bd6","sha256:6db0c8e0b936dae4eeb7b569843afcd324a418dab0b58b1764d9f914eeea72f7"],"state_sha256":"01c32de8b71cfaf873a914e84d1e529313295987d4756f6d72bd601c8db15359"}