{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YINVLGZLH23ZIWV5OU5VHDGWCY","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":"f6fdfc510d60f43c481ec38a085b53db554f791e136652ec99d47b48e757c935","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-09T17:38:45Z","title_canon_sha256":"eacee94a89536a9fbeef33e25e6967703dd9e8bc78390f0821bead640bdb875c"},"schema_version":"1.0","source":{"id":"2506.07963","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07963","created_at":"2026-07-05T12:06:48Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07963v3","created_at":"2026-07-05T12:06:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07963","created_at":"2026-07-05T12:06:48Z"},{"alias_kind":"pith_short_12","alias_value":"YINVLGZLH23Z","created_at":"2026-07-05T12:06:48Z"},{"alias_kind":"pith_short_16","alias_value":"YINVLGZLH23ZIWV5","created_at":"2026-07-05T12:06:48Z"},{"alias_kind":"pith_short_8","alias_value":"YINVLGZL","created_at":"2026-07-05T12:06:48Z"}],"graph_snapshots":[{"event_id":"sha256:ef74fbaff15e2a13cdd7fc33c69c52cd2fe267f521950efd6b107c6aef76e517","target":"graph","created_at":"2026-07-05T12:06:48Z","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/2506.07963/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Building upon large language models (LLMs), recent large multimodal models (LMMs) unify cross-model understanding and generation into a single framework. However, LMMs still struggle to achieve accurate vision-language alignment, prone to generating text responses contradicting the visual input or failing to follow the text-to-image prompts. Current solutions require external supervision (e.g., human feedback or reward models) and only address unidirectional tasks-either understanding or generation. In this work, based on the observation that understanding and generation are naturally inverse ","authors_text":"Guanzhong Wang, Ji-Rong Wen, Jixiang Hong, Rui Yan, Yi Liu, Yiran Zhang","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-09T17:38:45Z","title":"SUDER: Self-Improving Unified Large Multimodal Models for Understanding and Generation with Dual Self-Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07963","kind":"arxiv","version":3},"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:a111227314ee7eb422b5046b55b4a3bc8ccaf1b953ea60533e24cd6688272734","target":"record","created_at":"2026-07-05T12:06:48Z","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":"f6fdfc510d60f43c481ec38a085b53db554f791e136652ec99d47b48e757c935","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-09T17:38:45Z","title_canon_sha256":"eacee94a89536a9fbeef33e25e6967703dd9e8bc78390f0821bead640bdb875c"},"schema_version":"1.0","source":{"id":"2506.07963","kind":"arxiv","version":3}},"canonical_sha256":"c21b559b2b3eb7945abd753b538cd6162b1ed288a23b808241c116a5ebefb194","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c21b559b2b3eb7945abd753b538cd6162b1ed288a23b808241c116a5ebefb194","first_computed_at":"2026-07-05T12:06:48.372861Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:06:48.372861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gFSf/z+bxrBhbzJZk4GR1W0KqMFBxbrEzpojzbMBPeONdhMvmPGm6C6hxJc0+xnHJQ6Ptyg6MHnIes4kouLODQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:06:48.373351Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07963","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a111227314ee7eb422b5046b55b4a3bc8ccaf1b953ea60533e24cd6688272734","sha256:ef74fbaff15e2a13cdd7fc33c69c52cd2fe267f521950efd6b107c6aef76e517"],"state_sha256":"e3ba06a18f08a0ef7b8524a730c1862ad0be73b7faf3f991578d6789a7af52b5"}