{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7Z34D7HMZQ2BWNDJ2B5BUFJBYJ","short_pith_number":"pith:7Z34D7HM","schema_version":"1.0","canonical_sha256":"fe77c1fceccc341b3469d07a1a1521c24f5b2e22c477c97d20fce8211d0e8070","source":{"kind":"arxiv","id":"2606.08063","version":1},"attestation_state":"computed","paper":{"title":"Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jianmin Chen, Jiaqi Tang, Mengjie Zhao, Qifeng Chen, Qingfa Xiao, Runtao Liu, Wei Wei, Xiangyu Wu, Youyang Zhai","submitted_at":"2026-06-06T08:58:12Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have demonstrated remarkable success in visual understanding, yet their performance degrades significantly under real-world visual corruptions. While existing robustness enhancement approaches exist, they are limited: black-box feature alignment lacks interpretability, and white-box text-based reasoning cannot restore lost pixel-level details. This work investigates a fundamental research question: Can MLLMs recover corrupted visual content by themselves? To address this, we propose Robust-U1, a novel framework that equips MLLMs with explicit visual sel"},"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":"2606.08063","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-06T08:58:12Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"d0999641abad1677c9dbfa9f789157e64037b47531e227c3088430e66f4fd117","abstract_canon_sha256":"7e054c591b1ee89bec4153ad9647739dc13eafefd31e0ad8610dab6d689c0774"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:25.035701Z","signature_b64":"rUHySfU0Phap8tCbbhUlCGmP11hjDbz4+ZybiI8SDWPXwSSc7KmW/HIW3gj/ryK7LwO0oTCXR5htQ6P0Es+fDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe77c1fceccc341b3469d07a1a1521c24f5b2e22c477c97d20fce8211d0e8070","last_reissued_at":"2026-06-09T01:05:25.035255Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:25.035255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jianmin Chen, Jiaqi Tang, Mengjie Zhao, Qifeng Chen, Qingfa Xiao, Runtao Liu, Wei Wei, Xiangyu Wu, Youyang Zhai","submitted_at":"2026-06-06T08:58:12Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have demonstrated remarkable success in visual understanding, yet their performance degrades significantly under real-world visual corruptions. While existing robustness enhancement approaches exist, they are limited: black-box feature alignment lacks interpretability, and white-box text-based reasoning cannot restore lost pixel-level details. This work investigates a fundamental research question: Can MLLMs recover corrupted visual content by themselves? To address this, we propose Robust-U1, a novel framework that equips MLLMs with explicit visual sel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08063","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/2606.08063/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":"2606.08063","created_at":"2026-06-09T01:05:25.035331+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08063v1","created_at":"2026-06-09T01:05:25.035331+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08063","created_at":"2026-06-09T01:05:25.035331+00:00"},{"alias_kind":"pith_short_12","alias_value":"7Z34D7HMZQ2B","created_at":"2026-06-09T01:05:25.035331+00:00"},{"alias_kind":"pith_short_16","alias_value":"7Z34D7HMZQ2BWNDJ","created_at":"2026-06-09T01:05:25.035331+00:00"},{"alias_kind":"pith_short_8","alias_value":"7Z34D7HM","created_at":"2026-06-09T01:05:25.035331+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/7Z34D7HMZQ2BWNDJ2B5BUFJBYJ","json":"https://pith.science/pith/7Z34D7HMZQ2BWNDJ2B5BUFJBYJ.json","graph_json":"https://pith.science/api/pith-number/7Z34D7HMZQ2BWNDJ2B5BUFJBYJ/graph.json","events_json":"https://pith.science/api/pith-number/7Z34D7HMZQ2BWNDJ2B5BUFJBYJ/events.json","paper":"https://pith.science/paper/7Z34D7HM"},"agent_actions":{"view_html":"https://pith.science/pith/7Z34D7HMZQ2BWNDJ2B5BUFJBYJ","download_json":"https://pith.science/pith/7Z34D7HMZQ2BWNDJ2B5BUFJBYJ.json","view_paper":"https://pith.science/paper/7Z34D7HM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08063&json=true","fetch_graph":"https://pith.science/api/pith-number/7Z34D7HMZQ2BWNDJ2B5BUFJBYJ/graph.json","fetch_events":"https://pith.science/api/pith-number/7Z34D7HMZQ2BWNDJ2B5BUFJBYJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7Z34D7HMZQ2BWNDJ2B5BUFJBYJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7Z34D7HMZQ2BWNDJ2B5BUFJBYJ/action/storage_attestation","attest_author":"https://pith.science/pith/7Z34D7HMZQ2BWNDJ2B5BUFJBYJ/action/author_attestation","sign_citation":"https://pith.science/pith/7Z34D7HMZQ2BWNDJ2B5BUFJBYJ/action/citation_signature","submit_replication":"https://pith.science/pith/7Z34D7HMZQ2BWNDJ2B5BUFJBYJ/action/replication_record"}},"created_at":"2026-06-09T01:05:25.035331+00:00","updated_at":"2026-06-09T01:05:25.035331+00:00"}