{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:E5CTOL6T2TEW7LIIBLNDBZTUSN","short_pith_number":"pith:E5CTOL6T","schema_version":"1.0","canonical_sha256":"2745372fd3d4c96fad080ada30e674935a5ccfd3a2384da8f5134fa9de868734","source":{"kind":"arxiv","id":"2605.14885","version":1},"attestation_state":"computed","paper":{"title":"Masked Next-Scale Prediction for Self-supervised Scene Text Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Liu, Yifei Zhang, Yu Zhou, Zeng Li, Zhuohao Chen","submitted_at":"2026-05-14T14:28:55Z","abstract_excerpt":"Scene Text Recognition requires modeling visual structures that evolve from coarse layouts to fine-grained character strokes. Training such models relies on large amounts of annotated data. Recent self-supervised approaches, such as Masked Image Modeling (MIM), alleviate this dependency by leveraging large-scale unlabeled data. Yet most existing MIM methods operate at a single spatial scale and fail to capture the hierarchical nature of scene text. In this work, we introduce Masked Next-Scale Prediction (MNSP), a unified self-supervised framework designed to explicitly model cross-scale struct"},"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":"2605.14885","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T14:28:55Z","cross_cats_sorted":[],"title_canon_sha256":"f9b5e4c2089443d41e301a11d4773dbe28db5328508a4ae2c266de0374912734","abstract_canon_sha256":"da082deeccfe69ea5fae433c732c8355373bc99dea2f99116f47573dd8665ba6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:56.004219Z","signature_b64":"X4PJhhxWH2Ux50wzQQaGFNqw1mvFpJWRjYO9jIM2jVgcxnAK39bgTNfouFqWQr2UEi1lxtCCSuHy0xmreJX/DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2745372fd3d4c96fad080ada30e674935a5ccfd3a2384da8f5134fa9de868734","last_reissued_at":"2026-05-17T23:38:56.003478Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:56.003478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Masked Next-Scale Prediction for Self-supervised Scene Text Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Liu, Yifei Zhang, Yu Zhou, Zeng Li, Zhuohao Chen","submitted_at":"2026-05-14T14:28:55Z","abstract_excerpt":"Scene Text Recognition requires modeling visual structures that evolve from coarse layouts to fine-grained character strokes. Training such models relies on large amounts of annotated data. Recent self-supervised approaches, such as Masked Image Modeling (MIM), alleviate this dependency by leveraging large-scale unlabeled data. Yet most existing MIM methods operate at a single spatial scale and fail to capture the hierarchical nature of scene text. In this work, we introduce Masked Next-Scale Prediction (MNSP), a unified self-supervised framework designed to explicitly model cross-scale struct"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.14885","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":""},"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":"2605.14885","created_at":"2026-05-17T23:38:56.003639+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14885v1","created_at":"2026-05-17T23:38:56.003639+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14885","created_at":"2026-05-17T23:38:56.003639+00:00"},{"alias_kind":"pith_short_12","alias_value":"E5CTOL6T2TEW","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"E5CTOL6T2TEW7LII","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"E5CTOL6T","created_at":"2026-05-18T12:33:37.589309+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/E5CTOL6T2TEW7LIIBLNDBZTUSN","json":"https://pith.science/pith/E5CTOL6T2TEW7LIIBLNDBZTUSN.json","graph_json":"https://pith.science/api/pith-number/E5CTOL6T2TEW7LIIBLNDBZTUSN/graph.json","events_json":"https://pith.science/api/pith-number/E5CTOL6T2TEW7LIIBLNDBZTUSN/events.json","paper":"https://pith.science/paper/E5CTOL6T"},"agent_actions":{"view_html":"https://pith.science/pith/E5CTOL6T2TEW7LIIBLNDBZTUSN","download_json":"https://pith.science/pith/E5CTOL6T2TEW7LIIBLNDBZTUSN.json","view_paper":"https://pith.science/paper/E5CTOL6T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14885&json=true","fetch_graph":"https://pith.science/api/pith-number/E5CTOL6T2TEW7LIIBLNDBZTUSN/graph.json","fetch_events":"https://pith.science/api/pith-number/E5CTOL6T2TEW7LIIBLNDBZTUSN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E5CTOL6T2TEW7LIIBLNDBZTUSN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E5CTOL6T2TEW7LIIBLNDBZTUSN/action/storage_attestation","attest_author":"https://pith.science/pith/E5CTOL6T2TEW7LIIBLNDBZTUSN/action/author_attestation","sign_citation":"https://pith.science/pith/E5CTOL6T2TEW7LIIBLNDBZTUSN/action/citation_signature","submit_replication":"https://pith.science/pith/E5CTOL6T2TEW7LIIBLNDBZTUSN/action/replication_record"}},"created_at":"2026-05-17T23:38:56.003639+00:00","updated_at":"2026-05-17T23:38:56.003639+00:00"}