{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RGSRCDLCX4K4XCFA5UOQWIKFU6","short_pith_number":"pith:RGSRCDLC","schema_version":"1.0","canonical_sha256":"89a5110d62bf15cb88a0ed1d0b2145a791707e2636f2882b06280c69d8bb9070","source":{"kind":"arxiv","id":"2608.03471","version":1},"attestation_state":"computed","paper":{"title":"Hi-Token: Hierarchical Coordinate Tokenization for Generative Visual Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongming Zhang, Hao Wu, Jian Xue, Ke Lu, Kun Dong, Shun Mao, Siwen Jiao, Xiuyuan Zhu, Zijin Du","submitted_at":"2026-08-04T11:07:19Z","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"},"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":"2608.03471","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T11:07:19Z","cross_cats_sorted":[],"title_canon_sha256":"72827841a10b9239b123a1fb3d08e7bcb387428976d412ab0916e4acfc2c7ffa","abstract_canon_sha256":"79e4aa0731732dd9347085dc388ba937e5d688fba27401aa05ffdef0d49241ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:35:55.154169Z","signature_b64":"SOOBtQPXKP+XHIwc2HbLa7nhNBqFyoIcOw+EmBkV/VkjxRPW8rpVq338bTnC3ynV8pz/ns7ElhsBYvukCqZNBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89a5110d62bf15cb88a0ed1d0b2145a791707e2636f2882b06280c69d8bb9070","last_reissued_at":"2026-08-05T01:35:55.152746Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:35:55.152746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hi-Token: Hierarchical Coordinate Tokenization for Generative Visual Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongming Zhang, Hao Wu, Jian Xue, Ke Lu, Kun Dong, Shun Mao, Siwen Jiao, Xiuyuan Zhu, Zijin Du","submitted_at":"2026-08-04T11:07:19Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03471","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/2608.03471/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":"2608.03471","created_at":"2026-08-05T01:35:55.153157+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.03471v1","created_at":"2026-08-05T01:35:55.153157+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03471","created_at":"2026-08-05T01:35:55.153157+00:00"},{"alias_kind":"pith_short_12","alias_value":"RGSRCDLCX4K4","created_at":"2026-08-05T01:35:55.153157+00:00"},{"alias_kind":"pith_short_16","alias_value":"RGSRCDLCX4K4XCFA","created_at":"2026-08-05T01:35:55.153157+00:00"},{"alias_kind":"pith_short_8","alias_value":"RGSRCDLC","created_at":"2026-08-05T01:35:55.153157+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/RGSRCDLCX4K4XCFA5UOQWIKFU6","json":"https://pith.science/pith/RGSRCDLCX4K4XCFA5UOQWIKFU6.json","graph_json":"https://pith.science/api/pith-number/RGSRCDLCX4K4XCFA5UOQWIKFU6/graph.json","events_json":"https://pith.science/api/pith-number/RGSRCDLCX4K4XCFA5UOQWIKFU6/events.json","paper":"https://pith.science/paper/RGSRCDLC"},"agent_actions":{"view_html":"https://pith.science/pith/RGSRCDLCX4K4XCFA5UOQWIKFU6","download_json":"https://pith.science/pith/RGSRCDLCX4K4XCFA5UOQWIKFU6.json","view_paper":"https://pith.science/paper/RGSRCDLC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.03471&json=true","fetch_graph":"https://pith.science/api/pith-number/RGSRCDLCX4K4XCFA5UOQWIKFU6/graph.json","fetch_events":"https://pith.science/api/pith-number/RGSRCDLCX4K4XCFA5UOQWIKFU6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RGSRCDLCX4K4XCFA5UOQWIKFU6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RGSRCDLCX4K4XCFA5UOQWIKFU6/action/storage_attestation","attest_author":"https://pith.science/pith/RGSRCDLCX4K4XCFA5UOQWIKFU6/action/author_attestation","sign_citation":"https://pith.science/pith/RGSRCDLCX4K4XCFA5UOQWIKFU6/action/citation_signature","submit_replication":"https://pith.science/pith/RGSRCDLCX4K4XCFA5UOQWIKFU6/action/replication_record"}},"created_at":"2026-08-05T01:35:55.153157+00:00","updated_at":"2026-08-05T01:35:55.153157+00:00"}