{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7Z34D7HMZQ2BWNDJ2B5BUFJBYJ","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":"7e054c591b1ee89bec4153ad9647739dc13eafefd31e0ad8610dab6d689c0774","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-06T08:58:12Z","title_canon_sha256":"d0999641abad1677c9dbfa9f789157e64037b47531e227c3088430e66f4fd117"},"schema_version":"1.0","source":{"id":"2606.08063","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08063","created_at":"2026-06-09T01:05:25Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08063v1","created_at":"2026-06-09T01:05:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08063","created_at":"2026-06-09T01:05:25Z"},{"alias_kind":"pith_short_12","alias_value":"7Z34D7HMZQ2B","created_at":"2026-06-09T01:05:25Z"},{"alias_kind":"pith_short_16","alias_value":"7Z34D7HMZQ2BWNDJ","created_at":"2026-06-09T01:05:25Z"},{"alias_kind":"pith_short_8","alias_value":"7Z34D7HM","created_at":"2026-06-09T01:05:25Z"}],"graph_snapshots":[{"event_id":"sha256:8b1b14beda1defbe57a65ad9b084a51aca20495abc46bfe25fec5c89609d0276","target":"graph","created_at":"2026-06-09T01:05:25Z","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/2606.08063/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jianmin Chen, Jiaqi Tang, Mengjie Zhao, Qifeng Chen, Qingfa Xiao, Runtao Liu, Wei Wei, Xiangyu Wu, Youyang Zhai","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-06T08:58:12Z","title":"Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08063","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:fb4271ac1c4fe0e784fb48dd4b9dbc5c01b345ff8aa24631292c3535629d9235","target":"record","created_at":"2026-06-09T01:05:25Z","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":"7e054c591b1ee89bec4153ad9647739dc13eafefd31e0ad8610dab6d689c0774","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-06T08:58:12Z","title_canon_sha256":"d0999641abad1677c9dbfa9f789157e64037b47531e227c3088430e66f4fd117"},"schema_version":"1.0","source":{"id":"2606.08063","kind":"arxiv","version":1}},"canonical_sha256":"fe77c1fceccc341b3469d07a1a1521c24f5b2e22c477c97d20fce8211d0e8070","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe77c1fceccc341b3469d07a1a1521c24f5b2e22c477c97d20fce8211d0e8070","first_computed_at":"2026-06-09T01:05:25.035255Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:25.035255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rUHySfU0Phap8tCbbhUlCGmP11hjDbz4+ZybiI8SDWPXwSSc7KmW/HIW3gj/ryK7LwO0oTCXR5htQ6P0Es+fDA==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:25.035701Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08063","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb4271ac1c4fe0e784fb48dd4b9dbc5c01b345ff8aa24631292c3535629d9235","sha256:8b1b14beda1defbe57a65ad9b084a51aca20495abc46bfe25fec5c89609d0276"],"state_sha256":"ccef215789196bfcafd96af4f0ae69536ac138f9412f6fe54a5f9e630eddd86d"}