{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:42DMKMMTVC5IDHGSVRIGVUU2OV","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":"1c42b27c243a6336c2aa8df9ea907d0e1465ad555f898f379b39a81dd641f7f0","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-11T08:28:47Z","title_canon_sha256":"745f526e6d20977595262bba3861899911ab12e9b873b32d14a953621f7f99fc"},"schema_version":"1.0","source":{"id":"2508.07750","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.07750","created_at":"2026-07-05T11:51:51Z"},{"alias_kind":"arxiv_version","alias_value":"2508.07750v1","created_at":"2026-07-05T11:51:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07750","created_at":"2026-07-05T11:51:51Z"},{"alias_kind":"pith_short_12","alias_value":"42DMKMMTVC5I","created_at":"2026-07-05T11:51:51Z"},{"alias_kind":"pith_short_16","alias_value":"42DMKMMTVC5IDHGS","created_at":"2026-07-05T11:51:51Z"},{"alias_kind":"pith_short_8","alias_value":"42DMKMMT","created_at":"2026-07-05T11:51:51Z"}],"graph_snapshots":[{"event_id":"sha256:4f7a1134071fb71dd0e49d5b1734c625f4d1cfdaf38be00f6f4202dd98390dba","target":"graph","created_at":"2026-07-05T11:51:51Z","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/2508.07750/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Alignment methodologies have emerged as a critical pathway for enhancing language model alignment capabilities. While SFT (supervised fine-tuning) accelerates convergence through direct token-level loss intervention, its efficacy is constrained by offline policy trajectory. In contrast, RL(reinforcement learning) facilitates exploratory policy optimization, but suffers from low sample efficiency and stringent dependency on high-quality base models. To address these dual challenges, we propose GRAO (Group Relative Alignment Optimization), a unified framework that synergizes the respective stren","authors_text":"Cheng Wei, Chunxiao Guo, Haowen Wang, Jiadi Jiang, Jian Wang, Jiaxin Liang, Ji Li, Jingyuan Deng, Jinjie Gu, Lei Fan, Peng Wei, Shuowen Zhang, Xudong Han, Yun Yue, Zhiling Ye","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-11T08:28:47Z","title":"Learning to Align, Aligning to Learn: A Unified Approach for Self-Optimized Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07750","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:d015af0e01252412e4a8482724b2df15343d59f3221c75ebc7309a47c2a19cb1","target":"record","created_at":"2026-07-05T11:51:51Z","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":"1c42b27c243a6336c2aa8df9ea907d0e1465ad555f898f379b39a81dd641f7f0","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-11T08:28:47Z","title_canon_sha256":"745f526e6d20977595262bba3861899911ab12e9b873b32d14a953621f7f99fc"},"schema_version":"1.0","source":{"id":"2508.07750","kind":"arxiv","version":1}},"canonical_sha256":"e686c53193a8ba819cd2ac506ad29a754cd71bb60d3093142235a6e57a6bd124","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e686c53193a8ba819cd2ac506ad29a754cd71bb60d3093142235a6e57a6bd124","first_computed_at":"2026-07-05T11:51:51.602798Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:51:51.602798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NboXR/0qtpWEnPhAt1iNt78o4veYqhRe1p4S7MCpFOYzTRA1xrrT4GInmifzEhh+nlRoQHOUMkT9Wn6KplexAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:51:51.603251Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.07750","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d015af0e01252412e4a8482724b2df15343d59f3221c75ebc7309a47c2a19cb1","sha256:4f7a1134071fb71dd0e49d5b1734c625f4d1cfdaf38be00f6f4202dd98390dba"],"state_sha256":"a31c14fcfc71a1a153aecada585a469540bd5f3a6059876965d107ee3a12961c"}