{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RGSRCDLCX4K4XCFA5UOQWIKFU6","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":"79e4aa0731732dd9347085dc388ba937e5d688fba27401aa05ffdef0d49241ac","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T11:07:19Z","title_canon_sha256":"72827841a10b9239b123a1fb3d08e7bcb387428976d412ab0916e4acfc2c7ffa"},"schema_version":"1.0","source":{"id":"2608.03471","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03471","created_at":"2026-08-05T01:35:55Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03471v1","created_at":"2026-08-05T01:35:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03471","created_at":"2026-08-05T01:35:55Z"},{"alias_kind":"pith_short_12","alias_value":"RGSRCDLCX4K4","created_at":"2026-08-05T01:35:55Z"},{"alias_kind":"pith_short_16","alias_value":"RGSRCDLCX4K4XCFA","created_at":"2026-08-05T01:35:55Z"},{"alias_kind":"pith_short_8","alias_value":"RGSRCDLC","created_at":"2026-08-05T01:35:55Z"}],"graph_snapshots":[{"event_id":"sha256:cdebf65b01d821f178175b02cde06a43560a5a37c702f249144cc83bf504dd0a","target":"graph","created_at":"2026-08-05T01:35:55Z","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/2608.03471/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative Vision-Language Models (VLMs) commonly treat bounding-box coordinates as independent output symbols, leaving numerical order and axis semantics implicit. We identify this representation as an important source of error in visual grounding. Hi-Token encodes each coordinate with axis-specific tokens for the hundreds, tens, and ones digits, which adds coarse-to-fine structure and increases token reuse while retaining the existing VLM architecture. Hi-GAR complements this representation with a geometry-based reward for Group Relative Policy Optimization (GRPO), using box overlap and coor","authors_text":"Dongming Zhang, Hao Wu, Jian Xue, Ke Lu, Kun Dong, Shun Mao, Siwen Jiao, Xiuyuan Zhu, Zijin Du","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T11:07:19Z","title":"Hi-Token: Hierarchical Coordinate Tokenization for Generative Visual Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03471","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":"sha256:9da85231cc4e3770934d6c16812ee50dbd50f30d10ab8a1ade8ce98fc87c8ed2","target":"record","created_at":"2026-08-05T01:35:55Z","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":"79e4aa0731732dd9347085dc388ba937e5d688fba27401aa05ffdef0d49241ac","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T11:07:19Z","title_canon_sha256":"72827841a10b9239b123a1fb3d08e7bcb387428976d412ab0916e4acfc2c7ffa"},"schema_version":"1.0","source":{"id":"2608.03471","kind":"arxiv","version":1}},"canonical_sha256":"89a5110d62bf15cb88a0ed1d0b2145a791707e2636f2882b06280c69d8bb9070","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89a5110d62bf15cb88a0ed1d0b2145a791707e2636f2882b06280c69d8bb9070","first_computed_at":"2026-08-05T01:35:55.152746Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T01:35:55.152746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SOOBtQPXKP+XHIwc2HbLa7nhNBqFyoIcOw+EmBkV/VkjxRPW8rpVq338bTnC3ynV8pz/ns7ElhsBYvukCqZNBQ==","signature_status":"signed_v1","signed_at":"2026-08-05T01:35:55.154169Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.03471","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9da85231cc4e3770934d6c16812ee50dbd50f30d10ab8a1ade8ce98fc87c8ed2","sha256:cdebf65b01d821f178175b02cde06a43560a5a37c702f249144cc83bf504dd0a"],"state_sha256":"1ae4f19b65715369a458b3ddee961579b4bc6cd892bad183854c205a6396319b"}