{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:N226Z26H72VDV5SY5UJRTATQVM","short_pith_number":"pith:N226Z26H","canonical_record":{"source":{"id":"2607.27902","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T09:17:48Z","cross_cats_sorted":[],"title_canon_sha256":"3f461870282fed6bec88440870fc5b0ed1264c61c0105dc4c872c8312470cb6d","abstract_canon_sha256":"65f12176845e443bb7e9f9d12e5f6e75e7a51315740fedfd1238a1a3c52eb46c"},"schema_version":"1.0"},"canonical_sha256":"6eb5ecebc7feaa3af658ed13198270ab38a2ccd4e2ba39ebe13e2f9f5122f9d9","source":{"kind":"arxiv","id":"2607.27902","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:N226Z26H72VDV5SY5UJRTATQVM","target":"record","payload":{"canonical_record":{"source":{"id":"2607.27902","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T09:17:48Z","cross_cats_sorted":[],"title_canon_sha256":"3f461870282fed6bec88440870fc5b0ed1264c61c0105dc4c872c8312470cb6d","abstract_canon_sha256":"65f12176845e443bb7e9f9d12e5f6e75e7a51315740fedfd1238a1a3c52eb46c"},"schema_version":"1.0"},"canonical_sha256":"6eb5ecebc7feaa3af658ed13198270ab38a2ccd4e2ba39ebe13e2f9f5122f9d9","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6eb5ecebc7feaa3af658ed13198270ab38a2ccd4e2ba39ebe13e2f9f5122f9d9","last_reissued_at":"2026-07-31T01:34:45.740322Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:34:45.740322Z"},"source_kind":"arxiv","source_id":"2607.27902","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-31T01:34:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RN2pH/1n6TY79NUJa2DYHUyVOZ9/X4Hum8RG0x8VgF892dbUf6bE2CWsiY+yUnAae427dk3+p9vexxzvVWiBBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:16:41.378708Z"},"content_sha256":"b30702cd904eb77b33561ca566ed018522a4c56dbe8d33388f51a039cdd97008","schema_version":"1.0","event_id":"sha256:b30702cd904eb77b33561ca566ed018522a4c56dbe8d33388f51a039cdd97008"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:N226Z26H72VDV5SY5UJRTATQVM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"One Patch Is Enough: Reinforcement-Optimized Visual Token Grounding for MLLM-Based Scene Text Spotting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huiguo He, Lianwen Jin, Peirong Zhang, Rui Tang, Shun Zhang, Wentao Yang, Yongxin Shi","submitted_at":"2026-07-30T09:17:48Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27902","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/2607.27902/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-31T01:34:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mgoqdUgdUy6bwVU9usKlJhfn+4zmSCOqVYlOjUkRYRhlnkM2WOCcepXU4hpY7grSsEiywy6SEuUckHTexkIGDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:16:41.379195Z"},"content_sha256":"ccc7fae22de0d0d8993591ca40afcee0fde3fcae0b82446b1d90a54d09743acc","schema_version":"1.0","event_id":"sha256:ccc7fae22de0d0d8993591ca40afcee0fde3fcae0b82446b1d90a54d09743acc"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:N226Z26H72VDV5SY5UJRTATQVM","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1109/TPAMI.2016.2577031) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Shaoqing Ren, Kaiming He, Ross B. Girshick, and Jian Sun. 2017. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.IEEE Trans. Pattern Anal. Mach. Intell.39, 6 (2017), 1137–1149. doi:10.1109/TPAMI.2016. 2577031","arxiv_id":"2607.27902","detector":"doi_compliance","evidence":{"ref_index":37,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.1109/tpami.2016","reconstructed_doi":"10.1109/TPAMI.2016.2577031"},"severity":"advisory","ref_index":37,"audited_at":"2026-07-31T23:31:44.828552Z","event_type":"pith.integrity.v1","detected_doi":"10.1109/TPAMI.2016.2577031","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"13fe7826788c65a2524fbb1707328b6cb57b1b693ad5f9b2a75629021f0b50ad","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":14594,"payload_sha256":"616ed142c8df013a012351315543cc64bf0f0ed50a1334edd99c0832401309bd","signature_b64":"i1IgJ+3UyWwSZSvN0AJ6cTQqo24cND9rdFsF1JE9zwUCPmvxvDKyvWFcOh8Xkret24gdHQ42eJ/UELdXq2R+CQ==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-31T23:36:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WtReNYFmuv+03NmQRZYlvL1ikFKJgU/xS2Fp9HaBzXKYn13Ec65wvX0Bwc6FWQ8YkGYwoIcf0zZ/ISFCXey9Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:16:41.381594Z"},"content_sha256":"c9143b9add971a7435c6b4c077a50b8c052b055d4722d45f00d9819e7ee6178e","schema_version":"1.0","event_id":"sha256:c9143b9add971a7435c6b4c077a50b8c052b055d4722d45f00d9819e7ee6178e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N226Z26H72VDV5SY5UJRTATQVM/bundle.json","state_url":"https://pith.science/pith/N226Z26H72VDV5SY5UJRTATQVM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N226Z26H72VDV5SY5UJRTATQVM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T06:16:41Z","links":{"resolver":"https://pith.science/pith/N226Z26H72VDV5SY5UJRTATQVM","bundle":"https://pith.science/pith/N226Z26H72VDV5SY5UJRTATQVM/bundle.json","state":"https://pith.science/pith/N226Z26H72VDV5SY5UJRTATQVM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N226Z26H72VDV5SY5UJRTATQVM/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"46314pdLyt+gz17VAkd/0NwjkstkEN/Q2hozUhNrOunnYLZMuvuwqX49JYrAoWO4gDVX1l1EPoOUFNx3kV4mAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T06:16:41.383688Z","bundle_sha256":"87fcccab68b24d18c0c99ac97f4f325016d99394d7a1db24b38ce327ef113783"}}