{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TOTNLUMDTFK554456UBACKQLIN","short_pith_number":"pith:TOTNLUMD","schema_version":"1.0","canonical_sha256":"9ba6d5d1839955def39df502012a0b4374458bb79016dbacca7b7a913837cdae","source":{"kind":"arxiv","id":"2412.10029","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Fine-Grained Vision-Language Pretraining with Negative Augmented Samples","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dehong Gao, Jinxia Zhang, Lei Yi, Libin Yang, Linbo Jin, Xiaoyan Cai, Yeyuan Wang","submitted_at":"2024-12-13T10:39:31Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.10029","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-13T10:39:31Z","cross_cats_sorted":[],"title_canon_sha256":"409958c09b001d4b6bdaccaea9a202978f9fe3ce0eab29a89c26997773b2a009","abstract_canon_sha256":"8d1b0a655afd8f2a0e25812ddbbe1a4a8fc4023b20fdf3aa34f31c7c65cd4554"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:45.993920Z","signature_b64":"Ilu/06bjRmDgGaoC87VfwcdCEHOm+CCM8K7B8Ra5zWhRP7shOc0xxQ5+7vGZwG8Wr2vUZvTsXPj6ZG7FVylcCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ba6d5d1839955def39df502012a0b4374458bb79016dbacca7b7a913837cdae","last_reissued_at":"2026-07-05T09:48:45.993481Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:45.993481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Fine-Grained Vision-Language Pretraining with Negative Augmented Samples","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dehong Gao, Jinxia Zhang, Lei Yi, Libin Yang, Linbo Jin, Xiaoyan Cai, Yeyuan Wang","submitted_at":"2024-12-13T10:39:31Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10029","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.10029/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.10029","created_at":"2026-07-05T09:48:45.993545+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.10029v1","created_at":"2026-07-05T09:48:45.993545+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10029","created_at":"2026-07-05T09:48:45.993545+00:00"},{"alias_kind":"pith_short_12","alias_value":"TOTNLUMDTFK5","created_at":"2026-07-05T09:48:45.993545+00:00"},{"alias_kind":"pith_short_16","alias_value":"TOTNLUMDTFK55445","created_at":"2026-07-05T09:48:45.993545+00:00"},{"alias_kind":"pith_short_8","alias_value":"TOTNLUMD","created_at":"2026-07-05T09:48:45.993545+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TOTNLUMDTFK554456UBACKQLIN","json":"https://pith.science/pith/TOTNLUMDTFK554456UBACKQLIN.json","graph_json":"https://pith.science/api/pith-number/TOTNLUMDTFK554456UBACKQLIN/graph.json","events_json":"https://pith.science/api/pith-number/TOTNLUMDTFK554456UBACKQLIN/events.json","paper":"https://pith.science/paper/TOTNLUMD"},"agent_actions":{"view_html":"https://pith.science/pith/TOTNLUMDTFK554456UBACKQLIN","download_json":"https://pith.science/pith/TOTNLUMDTFK554456UBACKQLIN.json","view_paper":"https://pith.science/paper/TOTNLUMD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.10029&json=true","fetch_graph":"https://pith.science/api/pith-number/TOTNLUMDTFK554456UBACKQLIN/graph.json","fetch_events":"https://pith.science/api/pith-number/TOTNLUMDTFK554456UBACKQLIN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TOTNLUMDTFK554456UBACKQLIN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TOTNLUMDTFK554456UBACKQLIN/action/storage_attestation","attest_author":"https://pith.science/pith/TOTNLUMDTFK554456UBACKQLIN/action/author_attestation","sign_citation":"https://pith.science/pith/TOTNLUMDTFK554456UBACKQLIN/action/citation_signature","submit_replication":"https://pith.science/pith/TOTNLUMDTFK554456UBACKQLIN/action/replication_record"}},"created_at":"2026-07-05T09:48:45.993545+00:00","updated_at":"2026-07-05T09:48:45.993545+00:00"}