{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:P7JA5REZLSS5UVXEB4SDK6GF22","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":"9aff33f986572f441d16010fca5841ced4e8b1b609b6880a045deb4420d5087e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T01:24:30Z","title_canon_sha256":"e14f9aad6040f8845ffe4d3ff6f797f6bb6b1ce0c939f220a7c06f108bd6dfd0"},"schema_version":"1.0","source":{"id":"2606.03005","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03005","created_at":"2026-06-03T01:05:29Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03005v1","created_at":"2026-06-03T01:05:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03005","created_at":"2026-06-03T01:05:29Z"},{"alias_kind":"pith_short_12","alias_value":"P7JA5REZLSS5","created_at":"2026-06-03T01:05:29Z"},{"alias_kind":"pith_short_16","alias_value":"P7JA5REZLSS5UVXE","created_at":"2026-06-03T01:05:29Z"},{"alias_kind":"pith_short_8","alias_value":"P7JA5REZ","created_at":"2026-06-03T01:05:29Z"}],"graph_snapshots":[{"event_id":"sha256:cf4bfa448f0db073f0122cd343b64816f4e89d8bf02193761f731666feb694c5","target":"graph","created_at":"2026-06-03T01:05:29Z","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/2606.03005/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite rapid progress, multimodal large language models (MLLMs) still fail on tasks that humans solve effortlessly, such as navigating a grid maze from a screenshot or selecting the correct puzzle piece. Rather than retraining the model, we ask a complementary question: how much capability can be elicited from a frozen MLLM purely by improving the execution scaffold around it? We introduce MUSE, a multimodal unified structured execution harness that wraps any off-the-shelf MLLM with composable modules for task representation, visual processing, perception tool use, structured parsing, determi","authors_text":"Hailing Wang, Jianglin Lu, Mingyuan Zhang, Qihua Dong, Xu Ma, Yizhou Wang, Yun Fu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T01:24:30Z","title":"MUSE: A Unified Agentic Harness for MLLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03005","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:b0240ab7f7d5c4413a2dd2f4bfefe005c68e99f12abe25f7232b7296e7710419","target":"record","created_at":"2026-06-03T01:05:29Z","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":"9aff33f986572f441d16010fca5841ced4e8b1b609b6880a045deb4420d5087e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T01:24:30Z","title_canon_sha256":"e14f9aad6040f8845ffe4d3ff6f797f6bb6b1ce0c939f220a7c06f108bd6dfd0"},"schema_version":"1.0","source":{"id":"2606.03005","kind":"arxiv","version":1}},"canonical_sha256":"7fd20ec4995ca5da56e40f243578c5d6b3b52acfcef72ce5f8c8830987e7fe02","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7fd20ec4995ca5da56e40f243578c5d6b3b52acfcef72ce5f8c8830987e7fe02","first_computed_at":"2026-06-03T01:05:29.068153Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:29.068153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qbO3+ypcWVRRnCCrjtrj0Zk+ITseT3NEgLp312sCgye3qdJhIm/owTl+35zXeCEJlpa+vZYTzYPkYciz2re+BA==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:29.068595Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03005","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b0240ab7f7d5c4413a2dd2f4bfefe005c68e99f12abe25f7232b7296e7710419","sha256:cf4bfa448f0db073f0122cd343b64816f4e89d8bf02193761f731666feb694c5"],"state_sha256":"e89253db56d4f7681629f2e1e9a1049309f27ce718dc96c8dbb4a25c53a63a05"}