{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HF6H2CTWZF743FBXT6MUGLZMWH","short_pith_number":"pith:HF6H2CTW","schema_version":"1.0","canonical_sha256":"397c7d0a76c97fcd94379f99432f2cb1e4bf7e363e1e2f576de667c9ecdf7944","source":{"kind":"arxiv","id":"2408.05706","version":1},"attestation_state":"computed","paper":{"title":"Decoder Pre-Training with only Text for Scene Text Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shuai Zhao, Yongkun Du, Yu-Gang Jiang, Zhineng Chen","submitted_at":"2024-08-11T06:36:42Z","abstract_excerpt":"Scene text recognition (STR) pre-training methods have achieved remarkable progress, primarily relying on synthetic datasets. However, the domain gap between synthetic and real images poses a challenge in acquiring feature representations that align well with images on real scenes, thereby limiting the performance of these methods. We note that vision-language models like CLIP, pre-trained on extensive real image-text pairs, effectively align images and text in a unified embedding space, suggesting the potential to derive the representations of real images from text alone. Building upon this p"},"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":"2408.05706","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-11T06:36:42Z","cross_cats_sorted":[],"title_canon_sha256":"bdf1b9d67c59a292057342d2c6b720398f480d7c3f950726c5e1ac1640c72f1b","abstract_canon_sha256":"8a900a510bab3c2cf276a7fac699b07d90d84019cb86badaa57d251ecdffc786"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:23.925954Z","signature_b64":"U69VR2DinDX6CiPuD/NgVoiUkTXNpBxQgLBHhtAHGgGoGzjVOPDyTVlXcmI1VIZAtBICDM5Z/KeKm9R68V5BAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"397c7d0a76c97fcd94379f99432f2cb1e4bf7e363e1e2f576de667c9ecdf7944","last_reissued_at":"2026-07-05T08:54:23.925490Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:23.925490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decoder Pre-Training with only Text for Scene Text Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shuai Zhao, Yongkun Du, Yu-Gang Jiang, Zhineng Chen","submitted_at":"2024-08-11T06:36:42Z","abstract_excerpt":"Scene text recognition (STR) pre-training methods have achieved remarkable progress, primarily relying on synthetic datasets. However, the domain gap between synthetic and real images poses a challenge in acquiring feature representations that align well with images on real scenes, thereby limiting the performance of these methods. We note that vision-language models like CLIP, pre-trained on extensive real image-text pairs, effectively align images and text in a unified embedding space, suggesting the potential to derive the representations of real images from text alone. Building upon this p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.05706","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/2408.05706/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2408.05706","created_at":"2026-07-05T08:54:23.925548+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.05706v1","created_at":"2026-07-05T08:54:23.925548+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05706","created_at":"2026-07-05T08:54:23.925548+00:00"},{"alias_kind":"pith_short_12","alias_value":"HF6H2CTWZF74","created_at":"2026-07-05T08:54:23.925548+00:00"},{"alias_kind":"pith_short_16","alias_value":"HF6H2CTWZF743FBX","created_at":"2026-07-05T08:54:23.925548+00:00"},{"alias_kind":"pith_short_8","alias_value":"HF6H2CTW","created_at":"2026-07-05T08:54:23.925548+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/HF6H2CTWZF743FBXT6MUGLZMWH","json":"https://pith.science/pith/HF6H2CTWZF743FBXT6MUGLZMWH.json","graph_json":"https://pith.science/api/pith-number/HF6H2CTWZF743FBXT6MUGLZMWH/graph.json","events_json":"https://pith.science/api/pith-number/HF6H2CTWZF743FBXT6MUGLZMWH/events.json","paper":"https://pith.science/paper/HF6H2CTW"},"agent_actions":{"view_html":"https://pith.science/pith/HF6H2CTWZF743FBXT6MUGLZMWH","download_json":"https://pith.science/pith/HF6H2CTWZF743FBXT6MUGLZMWH.json","view_paper":"https://pith.science/paper/HF6H2CTW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.05706&json=true","fetch_graph":"https://pith.science/api/pith-number/HF6H2CTWZF743FBXT6MUGLZMWH/graph.json","fetch_events":"https://pith.science/api/pith-number/HF6H2CTWZF743FBXT6MUGLZMWH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HF6H2CTWZF743FBXT6MUGLZMWH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HF6H2CTWZF743FBXT6MUGLZMWH/action/storage_attestation","attest_author":"https://pith.science/pith/HF6H2CTWZF743FBXT6MUGLZMWH/action/author_attestation","sign_citation":"https://pith.science/pith/HF6H2CTWZF743FBXT6MUGLZMWH/action/citation_signature","submit_replication":"https://pith.science/pith/HF6H2CTWZF743FBXT6MUGLZMWH/action/replication_record"}},"created_at":"2026-07-05T08:54:23.925548+00:00","updated_at":"2026-07-05T08:54:23.925548+00:00"}