{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UFWQ743Z3HECLPP2CHG3HMOVWB","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":"db7caecbc2b9c7bd75823f04ccc077b5eefefa61edef795df96a42b1d6dace18","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-19T08:53:01Z","title_canon_sha256":"9f06d4f6761d2c1cda5b38748eb2e312536c5fcf24fdac622558f8f597d2c30e"},"schema_version":"1.0","source":{"id":"2607.17140","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.17140","created_at":"2026-07-21T01:21:17Z"},{"alias_kind":"arxiv_version","alias_value":"2607.17140v1","created_at":"2026-07-21T01:21:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17140","created_at":"2026-07-21T01:21:17Z"},{"alias_kind":"pith_short_12","alias_value":"UFWQ743Z3HEC","created_at":"2026-07-21T01:21:17Z"},{"alias_kind":"pith_short_16","alias_value":"UFWQ743Z3HECLPP2","created_at":"2026-07-21T01:21:17Z"},{"alias_kind":"pith_short_8","alias_value":"UFWQ743Z","created_at":"2026-07-21T01:21:17Z"}],"graph_snapshots":[{"event_id":"sha256:588260a06fa1694f842cb0887e48745f8053b735702d3d4d5e08c51895a583e4","target":"graph","created_at":"2026-07-21T01:21:17Z","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/2607.17140/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unified multimodal models (UMMs) aim to integrate visual understanding and generation within a single architecture, but architectural unification alone does not ensure semantic consistency. A model may describe the intended target correctly while generating an inconsistent edit. This exposes an understanding-generation alignment gap: linguistic and visual outputs live in different spaces, yet should be governed by the same target semantics. We study this gap in image editing, where an instruction defines a target state that can be both described and visually realized. Given a source image and ","authors_text":"Hao Fang, Hongjun Wang, Peixian Chen, Rui Ma, Tongyuan Bai, Weibo Gu, Wei Liu, Xing Sun, Ye Wang, Zuwei Long","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-19T08:53:01Z","title":"STBridge: Shared-Target Alignment for Bridging Understanding and Generation in UMMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17140","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:dd9fe617ff21785663a3ea3ad75afab081bfe0859d2bfb7e2098e21d5ca4a21b","target":"record","created_at":"2026-07-21T01:21:17Z","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":"db7caecbc2b9c7bd75823f04ccc077b5eefefa61edef795df96a42b1d6dace18","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-19T08:53:01Z","title_canon_sha256":"9f06d4f6761d2c1cda5b38748eb2e312536c5fcf24fdac622558f8f597d2c30e"},"schema_version":"1.0","source":{"id":"2607.17140","kind":"arxiv","version":1}},"canonical_sha256":"a16d0ff379d9c825bdfa11cdb3b1d5b04818e1da4ed72d8403959def0eb2fa95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a16d0ff379d9c825bdfa11cdb3b1d5b04818e1da4ed72d8403959def0eb2fa95","first_computed_at":"2026-07-21T01:21:17.754286Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T01:21:17.754286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z4MmID/V15HC6Cl93FJAL5XOsrIUQRWInW6GXb2FdDPiy/RAby0WfPdJPxEtvWdY36ErB7umlw4msoQSOLsdCg==","signature_status":"signed_v1","signed_at":"2026-07-21T01:21:17.755182Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.17140","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd9fe617ff21785663a3ea3ad75afab081bfe0859d2bfb7e2098e21d5ca4a21b","sha256:588260a06fa1694f842cb0887e48745f8053b735702d3d4d5e08c51895a583e4"],"state_sha256":"0ab71575277b71ff84dcaf3682df66f7fef559ee331c1581deee02c6d0f5010b"}