{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PCEDYSQ2MNHLGCGMETAIGOYFV2","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":"7752f93c50194f34b5c261a4e1a0119f8b5a374a6f22486dc1f095897ecf5218","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-08T04:00:20Z","title_canon_sha256":"8f96a8fcf6783055d746e5dd7e58898940a4d1ea96749e2d9a4a3dfd4f744108"},"schema_version":"1.0","source":{"id":"2310.04999","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.04999","created_at":"2026-07-05T06:59:01Z"},{"alias_kind":"arxiv_version","alias_value":"2310.04999v2","created_at":"2026-07-05T06:59:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.04999","created_at":"2026-07-05T06:59:01Z"},{"alias_kind":"pith_short_12","alias_value":"PCEDYSQ2MNHL","created_at":"2026-07-05T06:59:01Z"},{"alias_kind":"pith_short_16","alias_value":"PCEDYSQ2MNHLGCGM","created_at":"2026-07-05T06:59:01Z"},{"alias_kind":"pith_short_8","alias_value":"PCEDYSQ2","created_at":"2026-07-05T06:59:01Z"}],"graph_snapshots":[{"event_id":"sha256:24daa2648127fec88e3d39effa1f782bb5ef27a0859ca3d3cd61ac446d0be02a","target":"graph","created_at":"2026-07-05T06:59:01Z","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/2310.04999/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we explore the potential of the Contrastive Language-Image Pretraining (CLIP) model in scene text recognition (STR), and establish a novel Symmetrical Linguistic Feature Distillation framework (named CLIP-OCR) to leverage both visual and linguistic knowledge in CLIP. Different from previous CLIP-based methods mainly considering feature generalization on visual encoding, we propose a symmetrical distillation strategy (SDS) that further captures the linguistic knowledge in the CLIP text encoder. By cascading the CLIP image encoder with the reversed CLIP text encoder, a symmetrical","authors_text":"Boqiang Zhang, Hongtao Xie, Jianjun Xu, Yongdong Zhang, Yuxin Wang, Zixiao Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-08T04:00:20Z","title":"Symmetrical Linguistic Feature Distillation with CLIP for Scene Text Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.04999","kind":"arxiv","version":2},"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:c8bf03bbc06027d9fa07b1dc0069cc021c9948d04820899ea0063f531a03ad2d","target":"record","created_at":"2026-07-05T06:59:01Z","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":"7752f93c50194f34b5c261a4e1a0119f8b5a374a6f22486dc1f095897ecf5218","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-08T04:00:20Z","title_canon_sha256":"8f96a8fcf6783055d746e5dd7e58898940a4d1ea96749e2d9a4a3dfd4f744108"},"schema_version":"1.0","source":{"id":"2310.04999","kind":"arxiv","version":2}},"canonical_sha256":"78883c4a1a634eb308cc24c0833b05ae8670d9349fc52f2646831a2c5d2a15d4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78883c4a1a634eb308cc24c0833b05ae8670d9349fc52f2646831a2c5d2a15d4","first_computed_at":"2026-07-05T06:59:01.053121Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:59:01.053121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NyJo5+1j0UGNTf3pejrZPzzdGBiVkeJBFhlmb+sNMZo42e6w1YpjLoDC4ba1C8E2uamV1xPhE/fcs4hoQquuAw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:59:01.053630Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.04999","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8bf03bbc06027d9fa07b1dc0069cc021c9948d04820899ea0063f531a03ad2d","sha256:24daa2648127fec88e3d39effa1f782bb5ef27a0859ca3d3cd61ac446d0be02a"],"state_sha256":"4fcf1200fd13ebfcf0820f096cfc9a25062ddda4a7ec2f0954a7ba2a9f4a2f83"}