{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VTAUUDRMGNA4PQGTVCA2GVUMX4","short_pith_number":"pith:VTAUUDRM","schema_version":"1.0","canonical_sha256":"acc14a0e2c3341c7c0d3a881a3568cbf047979157d9c94e12aead271ab2a52c7","source":{"kind":"arxiv","id":"2409.09582","version":2},"attestation_state":"computed","paper":{"title":"NEVLP: Noise-Robust Framework for Efficient Vision-Language Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hang Zhang, Lun Wang, Yiyi Tao, Zhuoyue Wang","submitted_at":"2024-09-15T01:54:17Z","abstract_excerpt":"The success of Vision Language Models (VLMs) on various vision-language tasks heavily relies on pre-training with large scale web-crawled datasets. However, the noisy and incomplete nature of web data makes dataset scale crucial for performance, rendering end-to-end training increasingly prohibitive. In this paper, we propose NEVLP, a noise-robust framework for efficient vision-language pre-training that requires less pre-training data. Specifically, we bridge the modality gap between a frozen image encoder and a large language model with a transformer and introduce two innovative learning str"},"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":"2409.09582","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-15T01:54:17Z","cross_cats_sorted":[],"title_canon_sha256":"bf783f3a2c25b83c05d8de93ee7291dd2bd64e46aa5879b9f6609a613ca789d7","abstract_canon_sha256":"093438db1c5569f0aabebdb16f4332cec8515969657e5d509f18ab5a2f0593bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:50.313328Z","signature_b64":"4U1fYoPOzwgFMZadYGwknHFmRIA01ZJGXsBVakpbbAe9Yl1d00U4K0poY4THVLA9elgGUSo9i7FJzzu+0JWcDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acc14a0e2c3341c7c0d3a881a3568cbf047979157d9c94e12aead271ab2a52c7","last_reissued_at":"2026-07-05T09:10:50.312852Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:50.312852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NEVLP: Noise-Robust Framework for Efficient Vision-Language Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hang Zhang, Lun Wang, Yiyi Tao, Zhuoyue Wang","submitted_at":"2024-09-15T01:54:17Z","abstract_excerpt":"The success of Vision Language Models (VLMs) on various vision-language tasks heavily relies on pre-training with large scale web-crawled datasets. However, the noisy and incomplete nature of web data makes dataset scale crucial for performance, rendering end-to-end training increasingly prohibitive. In this paper, we propose NEVLP, a noise-robust framework for efficient vision-language pre-training that requires less pre-training data. Specifically, we bridge the modality gap between a frozen image encoder and a large language model with a transformer and introduce two innovative learning str"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09582","kind":"arxiv","version":2},"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/2409.09582/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":"2409.09582","created_at":"2026-07-05T09:10:50.312908+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.09582v2","created_at":"2026-07-05T09:10:50.312908+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09582","created_at":"2026-07-05T09:10:50.312908+00:00"},{"alias_kind":"pith_short_12","alias_value":"VTAUUDRMGNA4","created_at":"2026-07-05T09:10:50.312908+00:00"},{"alias_kind":"pith_short_16","alias_value":"VTAUUDRMGNA4PQGT","created_at":"2026-07-05T09:10:50.312908+00:00"},{"alias_kind":"pith_short_8","alias_value":"VTAUUDRM","created_at":"2026-07-05T09:10:50.312908+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.17774","citing_title":"Human-AI Co-Creation: A Framework for Collaborative Design in Intelligent Systems","ref_index":2024,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VTAUUDRMGNA4PQGTVCA2GVUMX4","json":"https://pith.science/pith/VTAUUDRMGNA4PQGTVCA2GVUMX4.json","graph_json":"https://pith.science/api/pith-number/VTAUUDRMGNA4PQGTVCA2GVUMX4/graph.json","events_json":"https://pith.science/api/pith-number/VTAUUDRMGNA4PQGTVCA2GVUMX4/events.json","paper":"https://pith.science/paper/VTAUUDRM"},"agent_actions":{"view_html":"https://pith.science/pith/VTAUUDRMGNA4PQGTVCA2GVUMX4","download_json":"https://pith.science/pith/VTAUUDRMGNA4PQGTVCA2GVUMX4.json","view_paper":"https://pith.science/paper/VTAUUDRM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.09582&json=true","fetch_graph":"https://pith.science/api/pith-number/VTAUUDRMGNA4PQGTVCA2GVUMX4/graph.json","fetch_events":"https://pith.science/api/pith-number/VTAUUDRMGNA4PQGTVCA2GVUMX4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VTAUUDRMGNA4PQGTVCA2GVUMX4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VTAUUDRMGNA4PQGTVCA2GVUMX4/action/storage_attestation","attest_author":"https://pith.science/pith/VTAUUDRMGNA4PQGTVCA2GVUMX4/action/author_attestation","sign_citation":"https://pith.science/pith/VTAUUDRMGNA4PQGTVCA2GVUMX4/action/citation_signature","submit_replication":"https://pith.science/pith/VTAUUDRMGNA4PQGTVCA2GVUMX4/action/replication_record"}},"created_at":"2026-07-05T09:10:50.312908+00:00","updated_at":"2026-07-05T09:10:50.312908+00:00"}