{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:276DMUK55H54GYKT4MPJSVXPFZ","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":"069f293147bc31364e5b293bf9bf35cc363645e1abfd7fdac33d18ac574c8844","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-10-13T02:32:07Z","title_canon_sha256":"dee1ffa2278edf7ea577f76c39316a9c829d3e1753975940e14260d09f3d5bae"},"schema_version":"1.0","source":{"id":"2510.10921","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.10921","created_at":"2026-05-26T02:03:58Z"},{"alias_kind":"arxiv_version","alias_value":"2510.10921v3","created_at":"2026-05-26T02:03:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.10921","created_at":"2026-05-26T02:03:58Z"},{"alias_kind":"pith_short_12","alias_value":"276DMUK55H54","created_at":"2026-05-26T02:03:58Z"},{"alias_kind":"pith_short_16","alias_value":"276DMUK55H54GYKT","created_at":"2026-05-26T02:03:58Z"},{"alias_kind":"pith_short_8","alias_value":"276DMUK5","created_at":"2026-05-26T02:03:58Z"}],"graph_snapshots":[{"event_id":"sha256:7e81db0cd97ddb39896452d74cd4ef5aaede96eeb9cf42f22d639d8b0ccac410","target":"graph","created_at":"2026-05-26T02:03:58Z","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/2510.10921/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-grained vision-language understanding requires precise alignment between visual content and linguistic descriptions, a capability that remains limited in current models, particularly in non-English settings. While models like CLIP perform well on global alignment, they often struggle to capture fine-grained details in object attributes, spatial relations, and linguistic expressions, with limited support for bilingual comprehension. To address these challenges, we introduce FG-CLIP 2, a bilingual vision-language model designed to advance fine-grained alignment for both English and Chinese.","authors_text":"Bin Wang, Chunyu Xie, Dawei Leng, Dawei Liang, Fanjing Kong, Ji Ao, Jincheng Li, Yuhui Yin","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-10-13T02:32:07Z","title":"FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.10921","kind":"arxiv","version":3},"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:ed1871fc7b9ef70a3da45def781a51b701c796a6027aba8885f4bb6dbf68dfef","target":"record","created_at":"2026-05-26T02:03:58Z","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":"069f293147bc31364e5b293bf9bf35cc363645e1abfd7fdac33d18ac574c8844","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-10-13T02:32:07Z","title_canon_sha256":"dee1ffa2278edf7ea577f76c39316a9c829d3e1753975940e14260d09f3d5bae"},"schema_version":"1.0","source":{"id":"2510.10921","kind":"arxiv","version":3}},"canonical_sha256":"d7fc36515de9fbc36153e31e9956ef2e78db7244aa35dbf782ae7bc428825ff2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7fc36515de9fbc36153e31e9956ef2e78db7244aa35dbf782ae7bc428825ff2","first_computed_at":"2026-05-26T02:03:58.026691Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:03:58.026691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7IHBOkoVXAYsUNbVEgampw6hkQ4j2eU/8R4K6B8QDl5xo+5eRvhyX/R/uMrrGseIzjzEYFxtIeFP0R9VEMyrCw==","signature_status":"signed_v1","signed_at":"2026-05-26T02:03:58.027570Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.10921","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed1871fc7b9ef70a3da45def781a51b701c796a6027aba8885f4bb6dbf68dfef","sha256:7e81db0cd97ddb39896452d74cd4ef5aaede96eeb9cf42f22d639d8b0ccac410"],"state_sha256":"330041aab46b89580394faa4e5a18e9a442982b8c64775dbeb32ec7554c20b4f"}