{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VTAUUDRMGNA4PQGTVCA2GVUMX4","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":"093438db1c5569f0aabebdb16f4332cec8515969657e5d509f18ab5a2f0593bb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-15T01:54:17Z","title_canon_sha256":"bf783f3a2c25b83c05d8de93ee7291dd2bd64e46aa5879b9f6609a613ca789d7"},"schema_version":"1.0","source":{"id":"2409.09582","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.09582","created_at":"2026-07-05T09:10:50Z"},{"alias_kind":"arxiv_version","alias_value":"2409.09582v2","created_at":"2026-07-05T09:10:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09582","created_at":"2026-07-05T09:10:50Z"},{"alias_kind":"pith_short_12","alias_value":"VTAUUDRMGNA4","created_at":"2026-07-05T09:10:50Z"},{"alias_kind":"pith_short_16","alias_value":"VTAUUDRMGNA4PQGT","created_at":"2026-07-05T09:10:50Z"},{"alias_kind":"pith_short_8","alias_value":"VTAUUDRM","created_at":"2026-07-05T09:10:50Z"}],"graph_snapshots":[{"event_id":"sha256:09da648e01928d7b5bef24d91aa47a352b9b10382165cc1864ead0c50ab59451","target":"graph","created_at":"2026-07-05T09:10:50Z","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/2409.09582/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hang Zhang, Lun Wang, Yiyi Tao, Zhuoyue Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-15T01:54:17Z","title":"NEVLP: Noise-Robust Framework for Efficient Vision-Language Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09582","kind":"arxiv","version":2},"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":"sha256:6b1e522a5b61310e8abc488f9ba019bc7aa87ae84c433c8bd5f319aceeec1ced","target":"record","created_at":"2026-07-05T09:10:50Z","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":"093438db1c5569f0aabebdb16f4332cec8515969657e5d509f18ab5a2f0593bb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-15T01:54:17Z","title_canon_sha256":"bf783f3a2c25b83c05d8de93ee7291dd2bd64e46aa5879b9f6609a613ca789d7"},"schema_version":"1.0","source":{"id":"2409.09582","kind":"arxiv","version":2}},"canonical_sha256":"acc14a0e2c3341c7c0d3a881a3568cbf047979157d9c94e12aead271ab2a52c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"acc14a0e2c3341c7c0d3a881a3568cbf047979157d9c94e12aead271ab2a52c7","first_computed_at":"2026-07-05T09:10:50.312852Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:10:50.312852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4U1fYoPOzwgFMZadYGwknHFmRIA01ZJGXsBVakpbbAe9Yl1d00U4K0poY4THVLA9elgGUSo9i7FJzzu+0JWcDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:10:50.313328Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.09582","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b1e522a5b61310e8abc488f9ba019bc7aa87ae84c433c8bd5f319aceeec1ced","sha256:09da648e01928d7b5bef24d91aa47a352b9b10382165cc1864ead0c50ab59451"],"state_sha256":"477c7d28aa1296c49548f7a267ced5c59e033c52ca96f7d6d167ed544f916373"}