{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KV53F7MN5WBB6XSXZRP452KLLC","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":"eb856fe7d08f30df23db5b89b3bab178c980355357f0438b02283e160437f352","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-27T13:24:35Z","title_canon_sha256":"deaf5e5940dc78855a7b7e8c29386f27d354b02f8a2daa28efe51e6cceee3d3c"},"schema_version":"1.0","source":{"id":"2607.24407","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24407","created_at":"2026-07-28T02:24:01Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24407v1","created_at":"2026-07-28T02:24:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24407","created_at":"2026-07-28T02:24:01Z"},{"alias_kind":"pith_short_12","alias_value":"KV53F7MN5WBB","created_at":"2026-07-28T02:24:01Z"},{"alias_kind":"pith_short_16","alias_value":"KV53F7MN5WBB6XSX","created_at":"2026-07-28T02:24:01Z"},{"alias_kind":"pith_short_8","alias_value":"KV53F7MN","created_at":"2026-07-28T02:24:01Z"}],"graph_snapshots":[{"event_id":"sha256:c0da8af7f299477721f110232f346fb36e01950c2ffbc0492ea2bcea63dc0280","target":"graph","created_at":"2026-07-28T02:24:01Z","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/2607.24407/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models have made great progress in grounding tasks, yet existing methods still struggle to unify precise localization and complex reasoning. For one thing, text-based methods rely on coordinates or index prediction, severely limiting the perceptual capabilities of the model for dense visual objects. Meanwhile, latent token-based methods employ special tokens without inherent spatial references and use a decoding mechanism that lacks thinking steps, weakening high-level reasoning capabilities. Consequently, developing a unified framework that excels in both perception ","authors_text":"Han Fang, Hao Li, Hao Sun, Hongbo Sun, Jinglin Xu, Jingmin Xin, Kongming Liang, Tianyi Ding, Tianyi Gao, Xiaodong Dong, Xin Wei, Ye Yuan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-27T13:24:35Z","title":"Mixture-of-Thought-Tokens: Unifying Perception and Reasoning for Free-form Multimodal Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24407","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":"sha256:87ad84d5e455c28f3fd04b6f6684f6c1d3c5d78be706c5d7a7595cef6199f9a1","target":"record","created_at":"2026-07-28T02:24:01Z","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":"eb856fe7d08f30df23db5b89b3bab178c980355357f0438b02283e160437f352","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-27T13:24:35Z","title_canon_sha256":"deaf5e5940dc78855a7b7e8c29386f27d354b02f8a2daa28efe51e6cceee3d3c"},"schema_version":"1.0","source":{"id":"2607.24407","kind":"arxiv","version":1}},"canonical_sha256":"557bb2fd8ded821f5e57cc5fcee94b588af57dd60f66cecc5bd4e8f82e7c8c06","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"557bb2fd8ded821f5e57cc5fcee94b588af57dd60f66cecc5bd4e8f82e7c8c06","first_computed_at":"2026-07-28T02:24:01.871313Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T02:24:01.871313Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BdBmDTvy9YpayI5/XcE+V9fxSApbSoYbSaoTyX+t9qJHnq02ofGWK21BqkpK45RVAnWXt2qhM+4nPsmKeee5Aw==","signature_status":"signed_v1","signed_at":"2026-07-28T02:24:01.872430Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.24407","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:87ad84d5e455c28f3fd04b6f6684f6c1d3c5d78be706c5d7a7595cef6199f9a1","sha256:c0da8af7f299477721f110232f346fb36e01950c2ffbc0492ea2bcea63dc0280"],"state_sha256":"7074712783bab091955d392339f1c88dcb89a4e60465374d3122851d776d9502"}