{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IHWBTJQLYQ5LLAKUTPYBBLTZMS","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":"b51f7d386f07cd6cd104d35d034911283598db6dbdb16a13faa5c1e74eed7eed","cross_cats_sorted":["cs.CR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-16T09:46:10Z","title_canon_sha256":"7e80fd5f24db0df89d4a76c1d59d91b2b36d9004c458b188b113f38c9ef0e342"},"schema_version":"1.0","source":{"id":"2505.11049","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11049","created_at":"2026-07-05T11:04:09Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11049v1","created_at":"2026-07-05T11:04:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11049","created_at":"2026-07-05T11:04:09Z"},{"alias_kind":"pith_short_12","alias_value":"IHWBTJQLYQ5L","created_at":"2026-07-05T11:04:09Z"},{"alias_kind":"pith_short_16","alias_value":"IHWBTJQLYQ5LLAKU","created_at":"2026-07-05T11:04:09Z"},{"alias_kind":"pith_short_8","alias_value":"IHWBTJQL","created_at":"2026-07-05T11:04:09Z"}],"graph_snapshots":[{"event_id":"sha256:e2a9fd5ee6f94be40a3379ec4b8994682e65964296317dd7d6ee4ebc9858552d","target":"graph","created_at":"2026-07-05T11:04:09Z","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/2505.11049/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To enhance the safety of VLMs, this paper introduces a novel reasoning-based VLM guard model dubbed GuardReasoner-VL. The core idea is to incentivize the guard model to deliberatively reason before making moderation decisions via online RL. First, we construct GuardReasoner-VLTrain, a reasoning corpus with 123K samples and 631K reasoning steps, spanning text, image, and text-image inputs. Then, based on it, we cold-start our model's reasoning ability via SFT. In addition, we further enhance reasoning regarding moderation through online RL. Concretely, to enhance diversity and difficulty of sam","authors_text":"Bryan Hooi, Cheng Wang, Hongcheng Gao, Jiaheng Zhang, Junfeng Fang, Kun Wang, Mingzhe Du, Shengfang Zhai, Tri Cao, Xinfeng Li, Yue Liu, Yulin Chen","cross_cats":["cs.CR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-16T09:46:10Z","title":"GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11049","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":"sha256:23c484e151a3f0aa3d3185e65e090ab62b58e35e8afdf311f5acfa3be6ca7008","target":"record","created_at":"2026-07-05T11:04:09Z","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":"b51f7d386f07cd6cd104d35d034911283598db6dbdb16a13faa5c1e74eed7eed","cross_cats_sorted":["cs.CR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-16T09:46:10Z","title_canon_sha256":"7e80fd5f24db0df89d4a76c1d59d91b2b36d9004c458b188b113f38c9ef0e342"},"schema_version":"1.0","source":{"id":"2505.11049","kind":"arxiv","version":1}},"canonical_sha256":"41ec19a60bc43ab581549bf010ae79649c734678bc7140d4e8e1325924de5dc0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"41ec19a60bc43ab581549bf010ae79649c734678bc7140d4e8e1325924de5dc0","first_computed_at":"2026-07-05T11:04:09.918383Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:09.918383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S1uCgkB9n7WOKx5lyLs6KcO9QUIdpQgpku6sKxGcC1ijCoVk8GoNOVapvrWU6Y5L1y2XCoqZtx+1t0ekcRqPAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:09.918911Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.11049","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23c484e151a3f0aa3d3185e65e090ab62b58e35e8afdf311f5acfa3be6ca7008","sha256:e2a9fd5ee6f94be40a3379ec4b8994682e65964296317dd7d6ee4ebc9858552d"],"state_sha256":"d8917715774a388cec332d2eb068ccb25ef879fd59254c4ec580a97b883c6316"}