{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZRV3FT7LC42Z5XUDGFCPCQTREL","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":"dd2768e8ab5815053e5d2fb05d2d70d1b88398fc9d3bf53f6d54e634b7cef4d2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-28T17:59:46Z","title_canon_sha256":"12b97e4db7568a5fb50a6d54f57353962e96a21e1fda4b4c6f0e57683d65f31f"},"schema_version":"1.0","source":{"id":"2508.21066","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.21066","created_at":"2026-07-05T12:01:16Z"},{"alias_kind":"arxiv_version","alias_value":"2508.21066v1","created_at":"2026-07-05T12:01:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21066","created_at":"2026-07-05T12:01:16Z"},{"alias_kind":"pith_short_12","alias_value":"ZRV3FT7LC42Z","created_at":"2026-07-05T12:01:16Z"},{"alias_kind":"pith_short_16","alias_value":"ZRV3FT7LC42Z5XUD","created_at":"2026-07-05T12:01:16Z"},{"alias_kind":"pith_short_8","alias_value":"ZRV3FT7L","created_at":"2026-07-05T12:01:16Z"}],"graph_snapshots":[{"event_id":"sha256:8b32181990846b903bdd50181127b5556d12406a8cdea2912134df68ac4dea34","target":"graph","created_at":"2026-07-05T12:01:16Z","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/2508.21066/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce OneReward, a unified reinforcement learning framework that enhances the model's generative capabilities across multiple tasks under different evaluation criteria using only \\textit{One Reward} model. By employing a single vision-language model (VLM) as the generative reward model, which can distinguish the winner and loser for a given task and a given evaluation criterion, it can be effectively applied to multi-task generation models, particularly in contexts with varied data and diverse task objectives. We utilize OneReward for mask-guided image generation, which c","authors_text":"Jie Wu, Shiyin Wang, Xinglong Wu, Xionghui Wang, Yitong Wang, Yuan Gong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-28T17:59:46Z","title":"OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21066","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:b260295505fe03593e4b9e01753e24b082027a09a3ff2b8a5c41556a3321017f","target":"record","created_at":"2026-07-05T12:01:16Z","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":"dd2768e8ab5815053e5d2fb05d2d70d1b88398fc9d3bf53f6d54e634b7cef4d2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-28T17:59:46Z","title_canon_sha256":"12b97e4db7568a5fb50a6d54f57353962e96a21e1fda4b4c6f0e57683d65f31f"},"schema_version":"1.0","source":{"id":"2508.21066","kind":"arxiv","version":1}},"canonical_sha256":"cc6bb2cfeb17359ede833144f1427122fb07650844fbc8c360eedccc09a9cd0d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc6bb2cfeb17359ede833144f1427122fb07650844fbc8c360eedccc09a9cd0d","first_computed_at":"2026-07-05T12:01:16.140775Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:01:16.140775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nIhIo4kPvOex24c/GSilj/co742rT8dgV7gaEQARjc6+at6CE7aadzP7W3GHuN0tLeAk9fqx0R0HmO42rVPnDg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:01:16.141279Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.21066","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b260295505fe03593e4b9e01753e24b082027a09a3ff2b8a5c41556a3321017f","sha256:8b32181990846b903bdd50181127b5556d12406a8cdea2912134df68ac4dea34"],"state_sha256":"01a1f4ddbad5ba7224bef2a7e6c69437de36081619e3f822a630c0166031c41e"}