{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RQY4AMNL4FKBQJ5K3MDEHL4HVB","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":"8c5814c8d7d1a827557008382bcfd5260a4717f064b65cc4ffb9b750df4e9df4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-11T04:20:45Z","title_canon_sha256":"f342c3c3f1f390397aec318a27654ba6b667368d9d1aefb381190088a788aa89"},"schema_version":"1.0","source":{"id":"2603.10395","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.10395","created_at":"2026-06-09T02:07:23Z"},{"alias_kind":"arxiv_version","alias_value":"2603.10395v2","created_at":"2026-06-09T02:07:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.10395","created_at":"2026-06-09T02:07:23Z"},{"alias_kind":"pith_short_12","alias_value":"RQY4AMNL4FKB","created_at":"2026-06-09T02:07:23Z"},{"alias_kind":"pith_short_16","alias_value":"RQY4AMNL4FKBQJ5K","created_at":"2026-06-09T02:07:23Z"},{"alias_kind":"pith_short_8","alias_value":"RQY4AMNL","created_at":"2026-06-09T02:07:23Z"}],"graph_snapshots":[{"event_id":"sha256:cea97c4881fba926442c5e416a80c19f10f9444dd93b21c362c003680d891f98","target":"graph","created_at":"2026-06-09T02:07:23Z","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/2603.10395/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Graph generation is a fundamental task with broad applications, such as drug discovery. Recently, discrete flow matching-based graph generation, \\aka, graph flow model (GFM), has emerged due to its superior performance and flexible sampling. However, effectively aligning GFMs with complex human preferences or task-specific objectives remains a significant challenge. In this paper, we propose Graph-GRPO, an online reinforcement learning (RL) framework for training GFMs under verifiable rewards. Our method makes two key contributions: (1) We derive an analytical expression for the transition pro","authors_text":"Baoheng Zhu, Delvin Ce Zhang, Deyu Bo, Xiao Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-11T04:20:45Z","title":"Graph-GRPO: Training Graph Flow Models with Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.10395","kind":"arxiv","version":2},"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:ff6f24522a4a07644a6253eb0f2b0f51627d39a5f831fe43c17717bae0cf49b3","target":"record","created_at":"2026-06-09T02:07:23Z","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":"8c5814c8d7d1a827557008382bcfd5260a4717f064b65cc4ffb9b750df4e9df4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-11T04:20:45Z","title_canon_sha256":"f342c3c3f1f390397aec318a27654ba6b667368d9d1aefb381190088a788aa89"},"schema_version":"1.0","source":{"id":"2603.10395","kind":"arxiv","version":2}},"canonical_sha256":"8c31c031abe1541827aadb0643af87a872e90cabce9323cdc749895c610c3956","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c31c031abe1541827aadb0643af87a872e90cabce9323cdc749895c610c3956","first_computed_at":"2026-06-09T02:07:23.586365Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:07:23.586365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Pmwt+E/k6Vs0jOPSApsFi1Cy7e+I3V6FGof2MCPGETsAkfwam54AUrlE5edop445PMAmcxmjUZqcK2z5+iJPCQ==","signature_status":"signed_v1","signed_at":"2026-06-09T02:07:23.587358Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.10395","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff6f24522a4a07644a6253eb0f2b0f51627d39a5f831fe43c17717bae0cf49b3","sha256:cea97c4881fba926442c5e416a80c19f10f9444dd93b21c362c003680d891f98"],"state_sha256":"fa9e797381a7abb80cb91a6a4942a91a1a8d5ab60859534e7453b5ebf3abe8db"}