{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TWGXJNF6X7OYTFFFFVY4R7OLE2","short_pith_number":"pith:TWGXJNF6","schema_version":"1.0","canonical_sha256":"9d8d74b4bebfdd8994a52d71c8fdcb268e77d5e4f3a108bfd8caad99914383ed","source":{"kind":"arxiv","id":"2608.11907","version":1},"attestation_state":"computed","paper":{"title":"Do You See What You Draw? A Semantic Closed-Loop Framework for Holistic Evaluation of Unified Multimodal Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hao Zhang, Jianqiang Huang, Jiaxin Qi, Zhijiang Tang","submitted_at":"2026-08-12T10:35:52Z","abstract_excerpt":"As Large Vision-Language Models increasingly aim to integrate visual generation and understanding within a single parameter space, evaluating such structural unification in a cohesive manner remains a critical challenge. Current evaluation protocols predominantly treat generative and discriminative capabilities as separate tasks, leaving a gap in system-level evaluation for unified multimodal models (UMMs). In this work, we propose Self-Generative-Understanding (SGU), a novel, annotation-free evaluation framework that probes the integrated capabilities of unified models through a semantic clos"},"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":"2608.11907","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-12T10:35:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bc8d8ef779115af0d3e3f9c479081743747bd3e05483ebf7b03914eb8a7a3d88","abstract_canon_sha256":"bf8fca63cf549453597155b7be8d69edc784b07028c192714f52262339a45264"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-13T01:28:53.298982Z","signature_b64":"D9MNdLU8kJbQzEBqU2feHYlnbhQ4HUA+e4Ni1ON2x5H8F4VEG7Z9/72MQceTa58AV/aNoAA4HNwzZ8qbVktnAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d8d74b4bebfdd8994a52d71c8fdcb268e77d5e4f3a108bfd8caad99914383ed","last_reissued_at":"2026-08-13T01:28:53.296713Z","signature_status":"signed_v1","first_computed_at":"2026-08-13T01:28:53.296713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do You See What You Draw? A Semantic Closed-Loop Framework for Holistic Evaluation of Unified Multimodal Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hao Zhang, Jianqiang Huang, Jiaxin Qi, Zhijiang Tang","submitted_at":"2026-08-12T10:35:52Z","abstract_excerpt":"As Large Vision-Language Models increasingly aim to integrate visual generation and understanding within a single parameter space, evaluating such structural unification in a cohesive manner remains a critical challenge. Current evaluation protocols predominantly treat generative and discriminative capabilities as separate tasks, leaving a gap in system-level evaluation for unified multimodal models (UMMs). In this work, we propose Self-Generative-Understanding (SGU), a novel, annotation-free evaluation framework that probes the integrated capabilities of unified models through a semantic clos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11907","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/2608.11907/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":"2608.11907","created_at":"2026-08-13T01:28:53.297869+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.11907v1","created_at":"2026-08-13T01:28:53.297869+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11907","created_at":"2026-08-13T01:28:53.297869+00:00"},{"alias_kind":"pith_short_12","alias_value":"TWGXJNF6X7OY","created_at":"2026-08-13T01:28:53.297869+00:00"},{"alias_kind":"pith_short_16","alias_value":"TWGXJNF6X7OYTFFF","created_at":"2026-08-13T01:28:53.297869+00:00"},{"alias_kind":"pith_short_8","alias_value":"TWGXJNF6","created_at":"2026-08-13T01:28:53.297869+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/TWGXJNF6X7OYTFFFFVY4R7OLE2","json":"https://pith.science/pith/TWGXJNF6X7OYTFFFFVY4R7OLE2.json","graph_json":"https://pith.science/api/pith-number/TWGXJNF6X7OYTFFFFVY4R7OLE2/graph.json","events_json":"https://pith.science/api/pith-number/TWGXJNF6X7OYTFFFFVY4R7OLE2/events.json","paper":"https://pith.science/paper/TWGXJNF6"},"agent_actions":{"view_html":"https://pith.science/pith/TWGXJNF6X7OYTFFFFVY4R7OLE2","download_json":"https://pith.science/pith/TWGXJNF6X7OYTFFFFVY4R7OLE2.json","view_paper":"https://pith.science/paper/TWGXJNF6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.11907&json=true","fetch_graph":"https://pith.science/api/pith-number/TWGXJNF6X7OYTFFFFVY4R7OLE2/graph.json","fetch_events":"https://pith.science/api/pith-number/TWGXJNF6X7OYTFFFFVY4R7OLE2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TWGXJNF6X7OYTFFFFVY4R7OLE2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TWGXJNF6X7OYTFFFFVY4R7OLE2/action/storage_attestation","attest_author":"https://pith.science/pith/TWGXJNF6X7OYTFFFFVY4R7OLE2/action/author_attestation","sign_citation":"https://pith.science/pith/TWGXJNF6X7OYTFFFFVY4R7OLE2/action/citation_signature","submit_replication":"https://pith.science/pith/TWGXJNF6X7OYTFFFFVY4R7OLE2/action/replication_record"}},"created_at":"2026-08-13T01:28:53.297869+00:00","updated_at":"2026-08-13T01:28:53.297869+00:00"}