{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2CY43W2YS2J7WIIBOKY6PULTJF","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":"4fa5c3ee818544ea0c0abd156bd1b67c01992ebf9df4dbceae7d47372c5cfe3a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-23T12:51:20Z","title_canon_sha256":"209c33bf960b1d99ad2ed60f0978aa4558a87b8c2fd1f6912ba24f4faf9c9111"},"schema_version":"1.0","source":{"id":"2305.14014","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14014","created_at":"2026-07-05T09:53:38Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14014v4","created_at":"2026-07-05T09:53:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14014","created_at":"2026-07-05T09:53:38Z"},{"alias_kind":"pith_short_12","alias_value":"2CY43W2YS2J7","created_at":"2026-07-05T09:53:38Z"},{"alias_kind":"pith_short_16","alias_value":"2CY43W2YS2J7WIIB","created_at":"2026-07-05T09:53:38Z"},{"alias_kind":"pith_short_8","alias_value":"2CY43W2Y","created_at":"2026-07-05T09:53:38Z"}],"graph_snapshots":[{"event_id":"sha256:63b893583331bb4068c996d0800d59a880f2c2ff92d901c1af383d22bea5e2a9","target":"graph","created_at":"2026-07-05T09:53:38Z","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/2305.14014/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained vision-language models~(VLMs) are the de-facto foundation models for various downstream tasks. However, scene text recognition methods still prefer backbones pre-trained on a single modality, namely, the visual modality, despite the potential of VLMs to serve as powerful scene text readers. For example, CLIP can robustly identify regular (horizontal) and irregular (rotated, curved, blurred, or occluded) text in images. With such merits, we transform CLIP into a scene text reader and introduce CLIP4STR, a simple yet effective STR method built upon image and text encoders of CLIP. It","authors_text":"Linchao Zhu, Ruijie Quan, Shuai Zhao, Yi Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-23T12:51:20Z","title":"CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14014","kind":"arxiv","version":4},"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:b681d35ba3db5ad448fd9f1919b314b832646d4d7cbf8956c061ffa6c6ad44c5","target":"record","created_at":"2026-07-05T09:53:38Z","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":"4fa5c3ee818544ea0c0abd156bd1b67c01992ebf9df4dbceae7d47372c5cfe3a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-23T12:51:20Z","title_canon_sha256":"209c33bf960b1d99ad2ed60f0978aa4558a87b8c2fd1f6912ba24f4faf9c9111"},"schema_version":"1.0","source":{"id":"2305.14014","kind":"arxiv","version":4}},"canonical_sha256":"d0b1cddb589693fb210172b1e7d173495fe2d936cbcf7d09051b3fe59d76a29c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d0b1cddb589693fb210172b1e7d173495fe2d936cbcf7d09051b3fe59d76a29c","first_computed_at":"2026-07-05T09:53:38.683019Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:38.683019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xsbr0q3JRwLUQhNSookmD9LzgnXQu3if1VzhYJu8As3K5CVBpRGaHXKwhcaKDi9E4KMM/ibw0v+QuPhUiNNtCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:38.683467Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.14014","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b681d35ba3db5ad448fd9f1919b314b832646d4d7cbf8956c061ffa6c6ad44c5","sha256:63b893583331bb4068c996d0800d59a880f2c2ff92d901c1af383d22bea5e2a9"],"state_sha256":"7719de9d75fd97fabf8902724b77d51fc38d3b33c48511c1ceb1f7e07ed31b01"}