{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UFWQ743Z3HECLPP2CHG3HMOVWB","short_pith_number":"pith:UFWQ743Z","schema_version":"1.0","canonical_sha256":"a16d0ff379d9c825bdfa11cdb3b1d5b04818e1da4ed72d8403959def0eb2fa95","source":{"kind":"arxiv","id":"2607.17140","version":1},"attestation_state":"computed","paper":{"title":"STBridge: Shared-Target Alignment for Bridging Understanding and Generation in UMMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Fang, Hongjun Wang, Peixian Chen, Rui Ma, Tongyuan Bai, Weibo Gu, Wei Liu, Xing Sun, Ye Wang, Zuwei Long","submitted_at":"2026-07-19T08:53:01Z","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.17140","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-19T08:53:01Z","cross_cats_sorted":[],"title_canon_sha256":"9f06d4f6761d2c1cda5b38748eb2e312536c5fcf24fdac622558f8f597d2c30e","abstract_canon_sha256":"db7caecbc2b9c7bd75823f04ccc077b5eefefa61edef795df96a42b1d6dace18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T01:21:17.755182Z","signature_b64":"Z4MmID/V15HC6Cl93FJAL5XOsrIUQRWInW6GXb2FdDPiy/RAby0WfPdJPxEtvWdY36ErB7umlw4msoQSOLsdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a16d0ff379d9c825bdfa11cdb3b1d5b04818e1da4ed72d8403959def0eb2fa95","last_reissued_at":"2026-07-21T01:21:17.754286Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T01:21:17.754286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STBridge: Shared-Target Alignment for Bridging Understanding and Generation in UMMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Fang, Hongjun Wang, Peixian Chen, Rui Ma, Tongyuan Bai, Weibo Gu, Wei Liu, Xing Sun, Ye Wang, Zuwei Long","submitted_at":"2026-07-19T08:53:01Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17140","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.17140/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.17140","created_at":"2026-07-21T01:21:17.754746+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.17140v1","created_at":"2026-07-21T01:21:17.754746+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17140","created_at":"2026-07-21T01:21:17.754746+00:00"},{"alias_kind":"pith_short_12","alias_value":"UFWQ743Z3HEC","created_at":"2026-07-21T01:21:17.754746+00:00"},{"alias_kind":"pith_short_16","alias_value":"UFWQ743Z3HECLPP2","created_at":"2026-07-21T01:21:17.754746+00:00"},{"alias_kind":"pith_short_8","alias_value":"UFWQ743Z","created_at":"2026-07-21T01:21:17.754746+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UFWQ743Z3HECLPP2CHG3HMOVWB","json":"https://pith.science/pith/UFWQ743Z3HECLPP2CHG3HMOVWB.json","graph_json":"https://pith.science/api/pith-number/UFWQ743Z3HECLPP2CHG3HMOVWB/graph.json","events_json":"https://pith.science/api/pith-number/UFWQ743Z3HECLPP2CHG3HMOVWB/events.json","paper":"https://pith.science/paper/UFWQ743Z"},"agent_actions":{"view_html":"https://pith.science/pith/UFWQ743Z3HECLPP2CHG3HMOVWB","download_json":"https://pith.science/pith/UFWQ743Z3HECLPP2CHG3HMOVWB.json","view_paper":"https://pith.science/paper/UFWQ743Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.17140&json=true","fetch_graph":"https://pith.science/api/pith-number/UFWQ743Z3HECLPP2CHG3HMOVWB/graph.json","fetch_events":"https://pith.science/api/pith-number/UFWQ743Z3HECLPP2CHG3HMOVWB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UFWQ743Z3HECLPP2CHG3HMOVWB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UFWQ743Z3HECLPP2CHG3HMOVWB/action/storage_attestation","attest_author":"https://pith.science/pith/UFWQ743Z3HECLPP2CHG3HMOVWB/action/author_attestation","sign_citation":"https://pith.science/pith/UFWQ743Z3HECLPP2CHG3HMOVWB/action/citation_signature","submit_replication":"https://pith.science/pith/UFWQ743Z3HECLPP2CHG3HMOVWB/action/replication_record"}},"created_at":"2026-07-21T01:21:17.754746+00:00","updated_at":"2026-07-21T01:21:17.754746+00:00"}