{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SYCFQ3R2JR3TXFUOO25ILWCIVS","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":"095e3fede78e2ecfb69e8cc4400784b2fed13189c27931a3c6504c0d650899d0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-08T09:06:53Z","title_canon_sha256":"c958546b5e03d473346c4843418cc12fd5c685e49d122bf2496346919385c3a7"},"schema_version":"1.0","source":{"id":"2505.05071","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.05071","created_at":"2026-07-05T11:06:31Z"},{"alias_kind":"arxiv_version","alias_value":"2505.05071v3","created_at":"2026-07-05T11:06:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05071","created_at":"2026-07-05T11:06:31Z"},{"alias_kind":"pith_short_12","alias_value":"SYCFQ3R2JR3T","created_at":"2026-07-05T11:06:31Z"},{"alias_kind":"pith_short_16","alias_value":"SYCFQ3R2JR3TXFUO","created_at":"2026-07-05T11:06:31Z"},{"alias_kind":"pith_short_8","alias_value":"SYCFQ3R2","created_at":"2026-07-05T11:06:31Z"}],"graph_snapshots":[{"event_id":"sha256:78afc4e063a802dd553446813d7bbb62cff535f7dce29b64e1204ef35ae8b129","target":"graph","created_at":"2026-07-05T11:06:31Z","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/2505.05071/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) excels in multimodal tasks such as image-text retrieval and zero-shot classification but struggles with fine-grained understanding due to its focus on coarse-grained short captions. To address this, we propose Fine-Grained CLIP (FG-CLIP), which enhances fine-grained understanding through three key innovations. First, we leverage large multimodal models to generate 1.6 billion long caption-image pairs for capturing global-level semantic details. Second, a high-quality dataset is constructed with 12 million images and 40 million region-specific boun","authors_text":"Bin Wang, Chunyu Xie, Dawei Leng, Dawei Liang, Fanjing Kong, Gengshen Zhang, Jincheng Li, Yuhui Yin","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-08T09:06:53Z","title":"FG-CLIP: Fine-Grained Visual and Textual Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05071","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":"sha256:48996cc3999cc7fe577f4431694dc38aeb0d76f5aaebd67f4b2c24fd1207623b","target":"record","created_at":"2026-07-05T11:06:31Z","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":"095e3fede78e2ecfb69e8cc4400784b2fed13189c27931a3c6504c0d650899d0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-08T09:06:53Z","title_canon_sha256":"c958546b5e03d473346c4843418cc12fd5c685e49d122bf2496346919385c3a7"},"schema_version":"1.0","source":{"id":"2505.05071","kind":"arxiv","version":3}},"canonical_sha256":"9604586e3a4c773b968e76ba85d848ac867ea90b14ead57150c35e8ae0b35b36","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9604586e3a4c773b968e76ba85d848ac867ea90b14ead57150c35e8ae0b35b36","first_computed_at":"2026-07-05T11:06:31.822508Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:31.822508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BtyHSuJoPxiMXTjGvq+feKd8zQgoVs4dvk4CcjdqJUXDQVttnQ7H1GgdRHQ9C4+/LsiH5hhsDkYf7yeBApYlAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:31.822975Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.05071","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:48996cc3999cc7fe577f4431694dc38aeb0d76f5aaebd67f4b2c24fd1207623b","sha256:78afc4e063a802dd553446813d7bbb62cff535f7dce29b64e1204ef35ae8b129"],"state_sha256":"80f8a75f2a4d6f115b8a59314afa4986ff4dd29cb7441a5275a0468be9c1e5fa"}