{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TG24B66X2VCX5YT4AMIJ6OTZ7Z","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":"2a01dbb2df993427266b5033743fe0e981d61a6d523d51b8b42f0a52edbc877e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-26T12:49:34Z","title_canon_sha256":"b3aef26d50994657a2a8d3a430ca7bc260c0c0e83d666659275be4eacdf91921"},"schema_version":"1.0","source":{"id":"2606.00105","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.00105","created_at":"2026-06-02T00:03:15Z"},{"alias_kind":"arxiv_version","alias_value":"2606.00105v1","created_at":"2026-06-02T00:03:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00105","created_at":"2026-06-02T00:03:15Z"},{"alias_kind":"pith_short_12","alias_value":"TG24B66X2VCX","created_at":"2026-06-02T00:03:15Z"},{"alias_kind":"pith_short_16","alias_value":"TG24B66X2VCX5YT4","created_at":"2026-06-02T00:03:15Z"},{"alias_kind":"pith_short_8","alias_value":"TG24B66X","created_at":"2026-06-02T00:03:15Z"}],"graph_snapshots":[{"event_id":"sha256:b1328eed932f52dc17a1bf1058417337f9955ceec3120c7502c2a801dc3f4058","target":"graph","created_at":"2026-06-02T00:03:15Z","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/2606.00105/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have achieved remarkable progress on vision-language tasks, but they may also memorize and expose sensitive or restricted knowledge, raising concerns about privacy and broader safety risks. Machine Unlearning (MU) provides a promising way to remove targeted undesirable knowledge from trained models without retraining from scratch while preserving general model utility. Nevertheless, effective unlearning in MLLMs remains particularly challenging. Existing training-based methods often struggle to balance unlearning effectiveness and model utility. In cont","authors_text":"Chenyu Wang, Junkai Chen, Junxiang You, Ruiqi Liu, Shu Wu, Yuhao He","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-26T12:49:34Z","title":"Visual-Noise Guided In-Context Distillation for Multimodal Large Language Model Unlearning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00105","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":"sha256:72af4326b39b6c85d713b9df4068cc6917f128a7ec2e44f6ff7afefdc155be84","target":"record","created_at":"2026-06-02T00:03:15Z","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":"2a01dbb2df993427266b5033743fe0e981d61a6d523d51b8b42f0a52edbc877e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-26T12:49:34Z","title_canon_sha256":"b3aef26d50994657a2a8d3a430ca7bc260c0c0e83d666659275be4eacdf91921"},"schema_version":"1.0","source":{"id":"2606.00105","kind":"arxiv","version":1}},"canonical_sha256":"99b5c0fbd7d5457ee27c03109f3a79fe6ad40d43019daf425fe1125e70d197d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"99b5c0fbd7d5457ee27c03109f3a79fe6ad40d43019daf425fe1125e70d197d5","first_computed_at":"2026-06-02T00:03:15.193406Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T00:03:15.193406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U7Ia5VDO+4RbjVSIG+rERtfbNyBz+9nW7fB1hzpUGzG008r/glKb+pfgW9x3SLuIG0W3PPvczz0ClFlk7xiWBA==","signature_status":"signed_v1","signed_at":"2026-06-02T00:03:15.193961Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.00105","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72af4326b39b6c85d713b9df4068cc6917f128a7ec2e44f6ff7afefdc155be84","sha256:b1328eed932f52dc17a1bf1058417337f9955ceec3120c7502c2a801dc3f4058"],"state_sha256":"a2b15bbb2d6ebc3ccb6d56f01cae2a464cf70ceb4e86a7c6f4cf836d3589f618"}