{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TOTNLUMDTFK554456UBACKQLIN","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":"8d1b0a655afd8f2a0e25812ddbbe1a4a8fc4023b20fdf3aa34f31c7c65cd4554","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-13T10:39:31Z","title_canon_sha256":"409958c09b001d4b6bdaccaea9a202978f9fe3ce0eab29a89c26997773b2a009"},"schema_version":"1.0","source":{"id":"2412.10029","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10029","created_at":"2026-07-05T09:48:45Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10029v1","created_at":"2026-07-05T09:48:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10029","created_at":"2026-07-05T09:48:45Z"},{"alias_kind":"pith_short_12","alias_value":"TOTNLUMDTFK5","created_at":"2026-07-05T09:48:45Z"},{"alias_kind":"pith_short_16","alias_value":"TOTNLUMDTFK55445","created_at":"2026-07-05T09:48:45Z"},{"alias_kind":"pith_short_8","alias_value":"TOTNLUMD","created_at":"2026-07-05T09:48:45Z"}],"graph_snapshots":[{"event_id":"sha256:35ce6e05adc53b3d9d031823036e4742f4080faf201714a1386422b38f2944a6","target":"graph","created_at":"2026-07-05T09:48:45Z","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/2412.10029/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing Vision-Language Pretraining (VLP) methods have achieved remarkable improvements across a variety of vision-language tasks, confirming their effectiveness in capturing coarse-grained semantic correlations. However, their capability for fine-grained understanding, which is critical for many nuanced vision-language applications, remains limited. Prevailing VLP models often overlook the intricate distinctions in expressing different modal features and typically depend on the similarity of holistic features for cross-modal interactions. Moreover, these models directly align and integrate f","authors_text":"Dehong Gao, Jinxia Zhang, Lei Yi, Libin Yang, Linbo Jin, Xiaoyan Cai, Yeyuan Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-13T10:39:31Z","title":"Enhancing Fine-Grained Vision-Language Pretraining with Negative Augmented Samples"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10029","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":"sha256:7064e91e794dbe4a4d6f7b3715e561c3b9cb4f98f3395587329ba9474512b2a0","target":"record","created_at":"2026-07-05T09:48:45Z","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":"8d1b0a655afd8f2a0e25812ddbbe1a4a8fc4023b20fdf3aa34f31c7c65cd4554","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-13T10:39:31Z","title_canon_sha256":"409958c09b001d4b6bdaccaea9a202978f9fe3ce0eab29a89c26997773b2a009"},"schema_version":"1.0","source":{"id":"2412.10029","kind":"arxiv","version":1}},"canonical_sha256":"9ba6d5d1839955def39df502012a0b4374458bb79016dbacca7b7a913837cdae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ba6d5d1839955def39df502012a0b4374458bb79016dbacca7b7a913837cdae","first_computed_at":"2026-07-05T09:48:45.993481Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:48:45.993481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ilu/06bjRmDgGaoC87VfwcdCEHOm+CCM8K7B8Ra5zWhRP7shOc0xxQ5+7vGZwG8Wr2vUZvTsXPj6ZG7FVylcCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:48:45.993920Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.10029","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7064e91e794dbe4a4d6f7b3715e561c3b9cb4f98f3395587329ba9474512b2a0","sha256:35ce6e05adc53b3d9d031823036e4742f4080faf201714a1386422b38f2944a6"],"state_sha256":"236fafaf6ba23b098ef7d0c8b509c514075f9c28bb6246f6c03e701e12cbef1d"}