{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:N226Z26H72VDV5SY5UJRTATQVM","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"65f12176845e443bb7e9f9d12e5f6e75e7a51315740fedfd1238a1a3c52eb46c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T09:17:48Z","title_canon_sha256":"3f461870282fed6bec88440870fc5b0ed1264c61c0105dc4c872c8312470cb6d"},"schema_version":"1.0","source":{"id":"2607.27902","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.27902","created_at":"2026-07-31T01:34:45Z"},{"alias_kind":"arxiv_version","alias_value":"2607.27902v1","created_at":"2026-07-31T01:34:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27902","created_at":"2026-07-31T01:34:45Z"},{"alias_kind":"pith_short_12","alias_value":"N226Z26H72VD","created_at":"2026-07-31T01:34:45Z"},{"alias_kind":"pith_short_16","alias_value":"N226Z26H72VDV5SY","created_at":"2026-07-31T01:34:45Z"},{"alias_kind":"pith_short_8","alias_value":"N226Z26H","created_at":"2026-07-31T01:34:45Z"}],"graph_snapshots":[{"event_id":"sha256:ccc7fae22de0d0d8993591ca40afcee0fde3fcae0b82446b1d90a54d09743acc","target":"graph","created_at":"2026-07-31T01:34:45Z","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/2607.27902/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scene text spotting requires high-precision alignment between textual recognition and spatial localization. While visual-token grounding has emerged as a promising formulation for Multimodal Large Language Models (MLLMs), the previous multi-patch paradigm often introduces redundant noise and localization ambiguity, particularly for dense or small text instances. To address this, we propose Single-Patch Text Spotting (SPaTS), a vision-centric framework that routes each text instance through a single anchor visual token and then recovers geometry via full-image refinement. To accurately identify","authors_text":"Huiguo He, Lianwen Jin, Peirong Zhang, Rui Tang, Shun Zhang, Wentao Yang, Yongxin Shi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T09:17:48Z","title":"One Patch Is Enough: Reinforcement-Optimized Visual Token Grounding for MLLM-Based Scene Text Spotting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27902","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:b30702cd904eb77b33561ca566ed018522a4c56dbe8d33388f51a039cdd97008","target":"record","created_at":"2026-07-31T01:34:45Z","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":"65f12176845e443bb7e9f9d12e5f6e75e7a51315740fedfd1238a1a3c52eb46c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T09:17:48Z","title_canon_sha256":"3f461870282fed6bec88440870fc5b0ed1264c61c0105dc4c872c8312470cb6d"},"schema_version":"1.0","source":{"id":"2607.27902","kind":"arxiv","version":1}},"canonical_sha256":"6eb5ecebc7feaa3af658ed13198270ab38a2ccd4e2ba39ebe13e2f9f5122f9d9","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6eb5ecebc7feaa3af658ed13198270ab38a2ccd4e2ba39ebe13e2f9f5122f9d9","first_computed_at":"2026-07-31T01:34:45.740322Z","kind":"pith_receipt","last_reissued_at":"2026-07-31T01:34:45.740322Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.27902","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b30702cd904eb77b33561ca566ed018522a4c56dbe8d33388f51a039cdd97008","sha256:ccc7fae22de0d0d8993591ca40afcee0fde3fcae0b82446b1d90a54d09743acc","sha256:c9143b9add971a7435c6b4c077a50b8c052b055d4722d45f00d9819e7ee6178e"],"state_sha256":"29b7f70f03393639740a728fca2d1635fe265a5cbe1dbbd213069c4bd3762ffa"}