{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:RQY4AMNL4FKBQJ5K3MDEHL4HVB","short_pith_number":"pith:RQY4AMNL","canonical_record":{"source":{"id":"2603.10395","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-11T04:20:45Z","cross_cats_sorted":[],"title_canon_sha256":"f342c3c3f1f390397aec318a27654ba6b667368d9d1aefb381190088a788aa89","abstract_canon_sha256":"8c5814c8d7d1a827557008382bcfd5260a4717f064b65cc4ffb9b750df4e9df4"},"schema_version":"1.0"},"canonical_sha256":"8c31c031abe1541827aadb0643af87a872e90cabce9323cdc749895c610c3956","source":{"kind":"arxiv","id":"2603.10395","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:RQY4AMNL4FKBQJ5K3MDEHL4HVB","target":"record","payload":{"canonical_record":{"source":{"id":"2603.10395","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-11T04:20:45Z","cross_cats_sorted":[],"title_canon_sha256":"f342c3c3f1f390397aec318a27654ba6b667368d9d1aefb381190088a788aa89","abstract_canon_sha256":"8c5814c8d7d1a827557008382bcfd5260a4717f064b65cc4ffb9b750df4e9df4"},"schema_version":"1.0"},"canonical_sha256":"8c31c031abe1541827aadb0643af87a872e90cabce9323cdc749895c610c3956","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:23.587358Z","signature_b64":"Pmwt+E/k6Vs0jOPSApsFi1Cy7e+I3V6FGof2MCPGETsAkfwam54AUrlE5edop445PMAmcxmjUZqcK2z5+iJPCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c31c031abe1541827aadb0643af87a872e90cabce9323cdc749895c610c3956","last_reissued_at":"2026-06-09T02:07:23.586365Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:23.586365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2603.10395","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T02:07:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gWTOySXbDnuNdEuLST6lbkSOUkUj59tXa7w4K0bsJkqcaIxonx5wPH03QOXe8sF322bSwkvAk9gG9dQovY8MAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T02:46:29.577899Z"},"content_sha256":"ff6f24522a4a07644a6253eb0f2b0f51627d39a5f831fe43c17717bae0cf49b3","schema_version":"1.0","event_id":"sha256:ff6f24522a4a07644a6253eb0f2b0f51627d39a5f831fe43c17717bae0cf49b3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:RQY4AMNL4FKBQJ5K3MDEHL4HVB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Graph-GRPO: Training Graph Flow Models with Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Baoheng Zhu, Delvin Ce Zhang, Deyu Bo, Xiao Wang","submitted_at":"2026-03-11T04:20:45Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.10395","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.10395/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T02:07:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d/WA6zL7q/L7dthGHpBOlbYu1cUa7NNRQ6NCFQpxclo/bd1n2uIpqCEDZP7icw+zApb39W5jDir0nZrf+StEBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T02:46:29.578665Z"},"content_sha256":"cea97c4881fba926442c5e416a80c19f10f9444dd93b21c362c003680d891f98","schema_version":"1.0","event_id":"sha256:cea97c4881fba926442c5e416a80c19f10f9444dd93b21c362c003680d891f98"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RQY4AMNL4FKBQJ5K3MDEHL4HVB/bundle.json","state_url":"https://pith.science/pith/RQY4AMNL4FKBQJ5K3MDEHL4HVB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RQY4AMNL4FKBQJ5K3MDEHL4HVB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-10T02:46:29Z","links":{"resolver":"https://pith.science/pith/RQY4AMNL4FKBQJ5K3MDEHL4HVB","bundle":"https://pith.science/pith/RQY4AMNL4FKBQJ5K3MDEHL4HVB/bundle.json","state":"https://pith.science/pith/RQY4AMNL4FKBQJ5K3MDEHL4HVB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RQY4AMNL4FKBQJ5K3MDEHL4HVB/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vn2XbHtGVUQX42T2AxfGljdtD7QKm8Q+xagQy67nc1A3SfmStMunoimhjdMXoBtgGKBPDzWKKkXc4bk+aaE1BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T02:46:29.583227Z","bundle_sha256":"84e3bb76f3ee10830b5209874be391e2c2f6b26b704a3ea772e00251895d21e8"}}