{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EEOR7C6MTDZYQY6X2ECVTPPVCU","short_pith_number":"pith:EEOR7C6M","schema_version":"1.0","canonical_sha256":"211d1f8bcc98f38863d7d10559bdf5150f7e4a4f4e35cf3823729eb5fabcde0b","source":{"kind":"arxiv","id":"2605.18173","version":1},"attestation_state":"computed","paper":{"title":"Do You Need Text Rectification? Soft Attention Mask Embedding for Rectification-Free Scene Text Spotting","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antonio Colombo, Giovanni Bianchi","submitted_at":"2026-05-18T10:15:57Z","abstract_excerpt":"End-to-end scene text spotting, which unifies text detection and recognition within a single framework, has witnessed remarkable progress driven by deep learning advances. However, most existing approaches still suffer from incomplete mask proposals caused by multi-scale variation, arbitrary text shapes, and complex background interference, thereby degrading recognition accuracy. In this paper, we propose a novel Soft Attention Mask Embedding module (SAME) that leverages the global receptive field of Transformer encoders to encode high-level features and compute soft attention weights, which a"},"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":"2605.18173","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T10:15:57Z","cross_cats_sorted":[],"title_canon_sha256":"1fa2f8afaefd98821ba24b0614746dcba9af34508028f0d6646583e4e408ed90","abstract_canon_sha256":"1d483cc6f6da4a7eaf8c0fcf389c49d7e3f5e2fb9f61e26781264fb982e4d117"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:49.278377Z","signature_b64":"Tc29b3Leaban3BmRfSeYEt6O3TqkiF0sbj5RxfIB0OdwjpT6obNm9qujGqwSRVglyECZZrzXQOAy5y5oZ5/wCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"211d1f8bcc98f38863d7d10559bdf5150f7e4a4f4e35cf3823729eb5fabcde0b","last_reissued_at":"2026-05-20T00:05:49.277814Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:49.277814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do You Need Text Rectification? Soft Attention Mask Embedding for Rectification-Free Scene Text Spotting","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antonio Colombo, Giovanni Bianchi","submitted_at":"2026-05-18T10:15:57Z","abstract_excerpt":"End-to-end scene text spotting, which unifies text detection and recognition within a single framework, has witnessed remarkable progress driven by deep learning advances. However, most existing approaches still suffer from incomplete mask proposals caused by multi-scale variation, arbitrary text shapes, and complex background interference, thereby degrading recognition accuracy. In this paper, we propose a novel Soft Attention Mask Embedding module (SAME) that leverages the global receptive field of Transformer encoders to encode high-level features and compute soft attention weights, which a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18173","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/2605.18173/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T23:41:59.043069Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:35.350167Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"32ff4b870f027755249831cc144eafe87d61594344795b2dc3e8c84336e4c711"},"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":"2605.18173","created_at":"2026-05-20T00:05:49.277906+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18173v1","created_at":"2026-05-20T00:05:49.277906+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18173","created_at":"2026-05-20T00:05:49.277906+00:00"},{"alias_kind":"pith_short_12","alias_value":"EEOR7C6MTDZY","created_at":"2026-05-20T00:05:49.277906+00:00"},{"alias_kind":"pith_short_16","alias_value":"EEOR7C6MTDZYQY6X","created_at":"2026-05-20T00:05:49.277906+00:00"},{"alias_kind":"pith_short_8","alias_value":"EEOR7C6M","created_at":"2026-05-20T00:05:49.277906+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/EEOR7C6MTDZYQY6X2ECVTPPVCU","json":"https://pith.science/pith/EEOR7C6MTDZYQY6X2ECVTPPVCU.json","graph_json":"https://pith.science/api/pith-number/EEOR7C6MTDZYQY6X2ECVTPPVCU/graph.json","events_json":"https://pith.science/api/pith-number/EEOR7C6MTDZYQY6X2ECVTPPVCU/events.json","paper":"https://pith.science/paper/EEOR7C6M"},"agent_actions":{"view_html":"https://pith.science/pith/EEOR7C6MTDZYQY6X2ECVTPPVCU","download_json":"https://pith.science/pith/EEOR7C6MTDZYQY6X2ECVTPPVCU.json","view_paper":"https://pith.science/paper/EEOR7C6M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18173&json=true","fetch_graph":"https://pith.science/api/pith-number/EEOR7C6MTDZYQY6X2ECVTPPVCU/graph.json","fetch_events":"https://pith.science/api/pith-number/EEOR7C6MTDZYQY6X2ECVTPPVCU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EEOR7C6MTDZYQY6X2ECVTPPVCU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EEOR7C6MTDZYQY6X2ECVTPPVCU/action/storage_attestation","attest_author":"https://pith.science/pith/EEOR7C6MTDZYQY6X2ECVTPPVCU/action/author_attestation","sign_citation":"https://pith.science/pith/EEOR7C6MTDZYQY6X2ECVTPPVCU/action/citation_signature","submit_replication":"https://pith.science/pith/EEOR7C6MTDZYQY6X2ECVTPPVCU/action/replication_record"}},"created_at":"2026-05-20T00:05:49.277906+00:00","updated_at":"2026-05-20T00:05:49.277906+00:00"}