{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EXWV4OXTJXSJE6FK4L2B2V4YNF","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":"71973ddbf9b7eb9e447e1f221c5c03f7b4676771f683cf167d78f9704eae9599","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-16T12:21:49Z","title_canon_sha256":"ec1c11db88212a2008d8ea78d737a2f47d84ef41a78c1f673d6396e57db87cca"},"schema_version":"1.0","source":{"id":"2504.12018","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.12018","created_at":"2026-07-05T10:50:01Z"},{"alias_kind":"arxiv_version","alias_value":"2504.12018v1","created_at":"2026-07-05T10:50:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12018","created_at":"2026-07-05T10:50:01Z"},{"alias_kind":"pith_short_12","alias_value":"EXWV4OXTJXSJ","created_at":"2026-07-05T10:50:01Z"},{"alias_kind":"pith_short_16","alias_value":"EXWV4OXTJXSJE6FK","created_at":"2026-07-05T10:50:01Z"},{"alias_kind":"pith_short_8","alias_value":"EXWV4OXT","created_at":"2026-07-05T10:50:01Z"}],"graph_snapshots":[{"event_id":"sha256:2faf3f57f51a396bfd98841c22c9eb10366f2ec1b5e05d737f517ee13938d8c5","target":"graph","created_at":"2026-07-05T10:50:01Z","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/2504.12018/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the rapid advancement of text-to-image (T2I) generation models, assessing the semantic alignment between generated images and text descriptions has become a significant research challenge. Current methods, including those based on Visual Question Answering (VQA), still struggle with fine-grained assessments and precise quantification of image-text alignment. This paper presents an improved evaluation method named Instruction-augmented Multimodal Alignment for Image-Text and Element Matching (iMatch), which evaluates image-text semantic alignment by fine-tuning multimodal large language mo","authors_text":"Fan Xia, Fengyun Rao, Jianhui Sun, Jing Lyu, Junda Lu, Liangchao Yao, Tianyi Wang, Xinli Yue, Yuetang Deng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-16T12:21:49Z","title":"Instruction-augmented Multimodal Alignment for Image-Text and Element Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12018","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":"sha256:75703adac8c960ba71d3e836cc38536dde6c8935847ee166106adbceae9b4d7a","target":"record","created_at":"2026-07-05T10:50:01Z","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":"71973ddbf9b7eb9e447e1f221c5c03f7b4676771f683cf167d78f9704eae9599","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-16T12:21:49Z","title_canon_sha256":"ec1c11db88212a2008d8ea78d737a2f47d84ef41a78c1f673d6396e57db87cca"},"schema_version":"1.0","source":{"id":"2504.12018","kind":"arxiv","version":1}},"canonical_sha256":"25ed5e3af34de49278aae2f41d579869537905cfc1b40cb123a52d04ec5b7bd2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25ed5e3af34de49278aae2f41d579869537905cfc1b40cb123a52d04ec5b7bd2","first_computed_at":"2026-07-05T10:50:01.465061Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:50:01.465061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4VSt4nMaTuJdfdhjqCXEmtQseJ8+zOyzhlrfP6r+4njmr1res6sbZlf5/9AvKAjuiPjB7cUowmRx1KRA5WifBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:50:01.465546Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.12018","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75703adac8c960ba71d3e836cc38536dde6c8935847ee166106adbceae9b4d7a","sha256:2faf3f57f51a396bfd98841c22c9eb10366f2ec1b5e05d737f517ee13938d8c5"],"state_sha256":"eb652a61db95988afa4a436728461d52b3ba45c7e2f8d539ed81fc3ca469abc3"}