{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:E5CTOL6T2TEW7LIIBLNDBZTUSN","short_pith_number":"pith:E5CTOL6T","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"},"canonical_sha256":"2745372fd3d4c96fad080ada30e674935a5ccfd3a2384da8f5134fa9de868734","source":{"kind":"arxiv","id":"2605.14885","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14885","created_at":"2026-05-17T23:38:56Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14885v1","created_at":"2026-05-17T23:38:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14885","created_at":"2026-05-17T23:38:56Z"},{"alias_kind":"pith_short_12","alias_value":"E5CTOL6T2TEW","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"E5CTOL6T2TEW7LII","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"E5CTOL6T","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:E5CTOL6T2TEW7LIIBLNDBZTUSN","target":"record","payload":{"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"},"canonical_sha256":"2745372fd3d4c96fad080ada30e674935a5ccfd3a2384da8f5134fa9de868734","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"},"source_kind":"arxiv","source_id":"2605.14885","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":"2026-05-17T23:38:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m6qJFXgKfhjmI7VdbaCYmtWiZcEJOM1sp3rEFPODWqEB6Mx8Au+jMF6fwb0uF/WmXcN/t0fI+0TeYZeaIMQtCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T16:47:58.398471Z"},"content_sha256":"913e1e7a6282823414563ffb9d6988e4a6c351efe04788182d4321a2e546beb6","schema_version":"1.0","event_id":"sha256:913e1e7a6282823414563ffb9d6988e4a6c351efe04788182d4321a2e546beb6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:E5CTOL6T2TEW7LIIBLNDBZTUSN","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sGJTYpIYDpt9K23PZ8157gD2SGu82/b0l0mMJVwswPjhG4yrBVDXzHfJ0/sHXJ2pKTiGZHZnOG3eEOVCamXGBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T16:47:58.398811Z"},"content_sha256":"870622e2c49d450ea0210fdda4f0220f4a8aa3cd6d69a12f0c2d482c1c15fcdc","schema_version":"1.0","event_id":"sha256:870622e2c49d450ea0210fdda4f0220f4a8aa3cd6d69a12f0c2d482c1c15fcdc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E5CTOL6T2TEW7LIIBLNDBZTUSN/bundle.json","state_url":"https://pith.science/pith/E5CTOL6T2TEW7LIIBLNDBZTUSN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E5CTOL6T2TEW7LIIBLNDBZTUSN/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":"2026-06-27T16:47:58Z","links":{"resolver":"https://pith.science/pith/E5CTOL6T2TEW7LIIBLNDBZTUSN","bundle":"https://pith.science/pith/E5CTOL6T2TEW7LIIBLNDBZTUSN/bundle.json","state":"https://pith.science/pith/E5CTOL6T2TEW7LIIBLNDBZTUSN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E5CTOL6T2TEW7LIIBLNDBZTUSN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:E5CTOL6T2TEW7LIIBLNDBZTUSN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"da082deeccfe69ea5fae433c732c8355373bc99dea2f99116f47573dd8665ba6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T14:28:55Z","title_canon_sha256":"f9b5e4c2089443d41e301a11d4773dbe28db5328508a4ae2c266de0374912734"},"schema_version":"1.0","source":{"id":"2605.14885","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14885","created_at":"2026-05-17T23:38:56Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14885v1","created_at":"2026-05-17T23:38:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14885","created_at":"2026-05-17T23:38:56Z"},{"alias_kind":"pith_short_12","alias_value":"E5CTOL6T2TEW","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"E5CTOL6T2TEW7LII","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"E5CTOL6T","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:870622e2c49d450ea0210fdda4f0220f4a8aa3cd6d69a12f0c2d482c1c15fcdc","target":"graph","created_at":"2026-05-17T23:38:56Z","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"},"paper":{"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","authors_text":"Chang Liu, Yifei Zhang, Yu Zhou, Zeng Li, Zhuohao Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T14:28:55Z","title":"Masked Next-Scale Prediction for Self-supervised Scene Text Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.14885","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":"sha256:913e1e7a6282823414563ffb9d6988e4a6c351efe04788182d4321a2e546beb6","target":"record","created_at":"2026-05-17T23:38:56Z","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":"da082deeccfe69ea5fae433c732c8355373bc99dea2f99116f47573dd8665ba6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T14:28:55Z","title_canon_sha256":"f9b5e4c2089443d41e301a11d4773dbe28db5328508a4ae2c266de0374912734"},"schema_version":"1.0","source":{"id":"2605.14885","kind":"arxiv","version":1}},"canonical_sha256":"2745372fd3d4c96fad080ada30e674935a5ccfd3a2384da8f5134fa9de868734","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2745372fd3d4c96fad080ada30e674935a5ccfd3a2384da8f5134fa9de868734","first_computed_at":"2026-05-17T23:38:56.003478Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:56.003478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X4PJhhxWH2Ux50wzQQaGFNqw1mvFpJWRjYO9jIM2jVgcxnAK39bgTNfouFqWQr2UEi1lxtCCSuHy0xmreJX/DA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:56.004219Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14885","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:913e1e7a6282823414563ffb9d6988e4a6c351efe04788182d4321a2e546beb6","sha256:870622e2c49d450ea0210fdda4f0220f4a8aa3cd6d69a12f0c2d482c1c15fcdc"],"state_sha256":"67cf2f0c500886ff5ff01b963e145dd8571dd05f51c95279b8d001394d9ea266"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hMwhkuEvjm1ODBZ/UcDbUAxaieEyRiD5WUKd3MjFEEr6PmmmlRLTStjLgmGuv9oJWCAU4hQCQyK3HPAOTFPuAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T16:47:58.400807Z","bundle_sha256":"5f06b0da22f3a67fb7385f3d59a004406c8aa497c7bebcecbd01549a8f39fd0e"}}