{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GBVNWFAL2CL7PKMQ6DO6LXMZZ4","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":"213b5a291c43c3c40f454b3782d54ca8ae57b66e12d4973b862854de426c5400","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-14T17:56:11Z","title_canon_sha256":"ae0e875545db6b427e3e5aee6d12a604d37b35e5baf8886340b8b56145329309"},"schema_version":"1.0","source":{"id":"2510.12784","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.12784","created_at":"2026-06-30T01:17:27Z"},{"alias_kind":"arxiv_version","alias_value":"2510.12784v2","created_at":"2026-06-30T01:17:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.12784","created_at":"2026-06-30T01:17:27Z"},{"alias_kind":"pith_short_12","alias_value":"GBVNWFAL2CL7","created_at":"2026-06-30T01:17:27Z"},{"alias_kind":"pith_short_16","alias_value":"GBVNWFAL2CL7PKMQ","created_at":"2026-06-30T01:17:27Z"},{"alias_kind":"pith_short_8","alias_value":"GBVNWFAL","created_at":"2026-06-30T01:17:27Z"}],"graph_snapshots":[{"event_id":"sha256:9265afdb88cda0da7fb31bda165a111cb5ae91342c1bb57a90c5f0de0c21a6dd","target":"graph","created_at":"2026-06-30T01:17:27Z","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/2510.12784/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, remarkable progress has been made in Unified Multimodal Models (UMMs), which integrate vision-language generation and understanding capabilities within a single framework. However, a model's strong visual understanding often fails to transfer to visual generation: it may correctly judge prompt-image alignment while failing to generate a faithful image from the same prompt. This raises a compelling question: Can a model improve itself by using its understanding module to reward its generation module? We introduce SRUM, a self-rewarding post-training framework directly applicable to ex","authors_text":"Aoxue Li, Chengqi Duan, Jiaqi Liao, Shenghua Gao, Weiyang Jin, Xihui Liu, Yuwei Niu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-14T17:56:11Z","title":"SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.12784","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":"sha256:962987f26768c78d7d59c6588a84c6c759b72a0a47e5e2b849b1b6b923d43acd","target":"record","created_at":"2026-06-30T01:17:27Z","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":"213b5a291c43c3c40f454b3782d54ca8ae57b66e12d4973b862854de426c5400","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-14T17:56:11Z","title_canon_sha256":"ae0e875545db6b427e3e5aee6d12a604d37b35e5baf8886340b8b56145329309"},"schema_version":"1.0","source":{"id":"2510.12784","kind":"arxiv","version":2}},"canonical_sha256":"306adb140bd097f7a990f0dde5dd99cf01bb1882a671f15791f6b7c7553d0776","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"306adb140bd097f7a990f0dde5dd99cf01bb1882a671f15791f6b7c7553d0776","first_computed_at":"2026-06-30T01:17:27.753064Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:17:27.753064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8PiUlzdiL4P6Y60qX4UFg5AiR24FYDcodST0EW1eW4a9vCiSrEek/nl0OxSkch9DCRkOdELDmqRicoP/oN9GCg==","signature_status":"signed_v1","signed_at":"2026-06-30T01:17:27.753689Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.12784","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:962987f26768c78d7d59c6588a84c6c759b72a0a47e5e2b849b1b6b923d43acd","sha256:9265afdb88cda0da7fb31bda165a111cb5ae91342c1bb57a90c5f0de0c21a6dd"],"state_sha256":"44903a5047952eea787454f4b7625aa4ebf5652779bcf5de8edaa349d474cebb"}