{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KV53F7MN5WBB6XSXZRP452KLLC","short_pith_number":"pith:KV53F7MN","schema_version":"1.0","canonical_sha256":"557bb2fd8ded821f5e57cc5fcee94b588af57dd60f66cecc5bd4e8f82e7c8c06","source":{"kind":"arxiv","id":"2607.24407","version":1},"attestation_state":"computed","paper":{"title":"Mixture-of-Thought-Tokens: Unifying Perception and Reasoning for Free-form Multimodal Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","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","submitted_at":"2026-07-27T13:24:35Z","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 "},"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":"2607.24407","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-27T13:24:35Z","cross_cats_sorted":[],"title_canon_sha256":"deaf5e5940dc78855a7b7e8c29386f27d354b02f8a2daa28efe51e6cceee3d3c","abstract_canon_sha256":"eb856fe7d08f30df23db5b89b3bab178c980355357f0438b02283e160437f352"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T02:24:01.872430Z","signature_b64":"BdBmDTvy9YpayI5/XcE+V9fxSApbSoYbSaoTyX+t9qJHnq02ofGWK21BqkpK45RVAnWXt2qhM+4nPsmKeee5Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"557bb2fd8ded821f5e57cc5fcee94b588af57dd60f66cecc5bd4e8f82e7c8c06","last_reissued_at":"2026-07-28T02:24:01.871313Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T02:24:01.871313Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mixture-of-Thought-Tokens: Unifying Perception and Reasoning for Free-form Multimodal Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","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","submitted_at":"2026-07-27T13:24:35Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24407","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/2607.24407/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":"2607.24407","created_at":"2026-07-28T02:24:01.871980+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.24407v1","created_at":"2026-07-28T02:24:01.871980+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24407","created_at":"2026-07-28T02:24:01.871980+00:00"},{"alias_kind":"pith_short_12","alias_value":"KV53F7MN5WBB","created_at":"2026-07-28T02:24:01.871980+00:00"},{"alias_kind":"pith_short_16","alias_value":"KV53F7MN5WBB6XSX","created_at":"2026-07-28T02:24:01.871980+00:00"},{"alias_kind":"pith_short_8","alias_value":"KV53F7MN","created_at":"2026-07-28T02:24:01.871980+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/KV53F7MN5WBB6XSXZRP452KLLC","json":"https://pith.science/pith/KV53F7MN5WBB6XSXZRP452KLLC.json","graph_json":"https://pith.science/api/pith-number/KV53F7MN5WBB6XSXZRP452KLLC/graph.json","events_json":"https://pith.science/api/pith-number/KV53F7MN5WBB6XSXZRP452KLLC/events.json","paper":"https://pith.science/paper/KV53F7MN"},"agent_actions":{"view_html":"https://pith.science/pith/KV53F7MN5WBB6XSXZRP452KLLC","download_json":"https://pith.science/pith/KV53F7MN5WBB6XSXZRP452KLLC.json","view_paper":"https://pith.science/paper/KV53F7MN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.24407&json=true","fetch_graph":"https://pith.science/api/pith-number/KV53F7MN5WBB6XSXZRP452KLLC/graph.json","fetch_events":"https://pith.science/api/pith-number/KV53F7MN5WBB6XSXZRP452KLLC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KV53F7MN5WBB6XSXZRP452KLLC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KV53F7MN5WBB6XSXZRP452KLLC/action/storage_attestation","attest_author":"https://pith.science/pith/KV53F7MN5WBB6XSXZRP452KLLC/action/author_attestation","sign_citation":"https://pith.science/pith/KV53F7MN5WBB6XSXZRP452KLLC/action/citation_signature","submit_replication":"https://pith.science/pith/KV53F7MN5WBB6XSXZRP452KLLC/action/replication_record"}},"created_at":"2026-07-28T02:24:01.871980+00:00","updated_at":"2026-07-28T02:24:01.871980+00:00"}