{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PBJBLDXMCLHRYXQQ2KHUOLSHVY","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":"8a20bd59cf05a59847ae4319fd40a4deb8809cef0f3b632563dec225ee179db3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-11T08:46:49Z","title_canon_sha256":"3063eac84004025a25fcba03f362ed68adffb5760ef51f3b79332aac26a11e8c"},"schema_version":"1.0","source":{"id":"2504.08358","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.08358","created_at":"2026-07-05T10:47:47Z"},{"alias_kind":"arxiv_version","alias_value":"2504.08358v1","created_at":"2026-07-05T10:47:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.08358","created_at":"2026-07-05T10:47:47Z"},{"alias_kind":"pith_short_12","alias_value":"PBJBLDXMCLHR","created_at":"2026-07-05T10:47:47Z"},{"alias_kind":"pith_short_16","alias_value":"PBJBLDXMCLHRYXQQ","created_at":"2026-07-05T10:47:47Z"},{"alias_kind":"pith_short_8","alias_value":"PBJBLDXM","created_at":"2026-07-05T10:47:47Z"}],"graph_snapshots":[{"event_id":"sha256:347cb174bb1a4e4124f4a2b7aa43df711c8eaea9e5ba209aee37f5834984e6fc","target":"graph","created_at":"2026-07-05T10:47:47Z","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/2504.08358/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent breakthroughs in large multimodal models (LMMs) have significantly advanced both text-to-image (T2I) generation and image-to-text (I2T) interpretation. However, many generated images still suffer from issues related to perceptual quality and text-image alignment. Given the high cost and inefficiency of manual evaluation, an automatic metric that aligns with human preferences is desirable. To this end, we present EvalMi-50K, a comprehensive dataset and benchmark for evaluating large-multimodal image generation, which features (i) comprehensive tasks, encompassing 2,100 extensive prompts ","authors_text":"Guangtao Zhai, Huiyu Duan, Jiarui Wang, Juntong Wang, Xiongkuo Min, Yu Zhao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-11T08:46:49Z","title":"LMM4LMM: Benchmarking and Evaluating Large-multimodal Image Generation with LMMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.08358","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":"sha256:2ec208f9acb034a379d00cc8975bc58ae69824695d960e300ff6eb0cb34fdf50","target":"record","created_at":"2026-07-05T10:47:47Z","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":"8a20bd59cf05a59847ae4319fd40a4deb8809cef0f3b632563dec225ee179db3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-11T08:46:49Z","title_canon_sha256":"3063eac84004025a25fcba03f362ed68adffb5760ef51f3b79332aac26a11e8c"},"schema_version":"1.0","source":{"id":"2504.08358","kind":"arxiv","version":1}},"canonical_sha256":"7852158eec12cf1c5e10d28f472e47ae04020206f2008de8feb54e1101439d81","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7852158eec12cf1c5e10d28f472e47ae04020206f2008de8feb54e1101439d81","first_computed_at":"2026-07-05T10:47:47.610741Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:47:47.610741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YjP/HaELFzdDulvDmWv+RxyvOvigRyjDHIbVaw+7VE7hSejGzIVKoULf9iGxxj1nRPqnthf1DjW6OUSHaTgnCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:47:47.611191Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.08358","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ec208f9acb034a379d00cc8975bc58ae69824695d960e300ff6eb0cb34fdf50","sha256:347cb174bb1a4e4124f4a2b7aa43df711c8eaea9e5ba209aee37f5834984e6fc"],"state_sha256":"86b0a7660243c5838a5bc103205ae4a6b95e9a8e5252f03250a78e3a78010cbb"}