{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HF6H2CTWZF743FBXT6MUGLZMWH","short_pith_number":"pith:HF6H2CTW","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"},"canonical_sha256":"397c7d0a76c97fcd94379f99432f2cb1e4bf7e363e1e2f576de667c9ecdf7944","source":{"kind":"arxiv","id":"2408.05706","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.05706","created_at":"2026-07-05T08:54:23Z"},{"alias_kind":"arxiv_version","alias_value":"2408.05706v1","created_at":"2026-07-05T08:54:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05706","created_at":"2026-07-05T08:54:23Z"},{"alias_kind":"pith_short_12","alias_value":"HF6H2CTWZF74","created_at":"2026-07-05T08:54:23Z"},{"alias_kind":"pith_short_16","alias_value":"HF6H2CTWZF743FBX","created_at":"2026-07-05T08:54:23Z"},{"alias_kind":"pith_short_8","alias_value":"HF6H2CTW","created_at":"2026-07-05T08:54:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HF6H2CTWZF743FBXT6MUGLZMWH","target":"record","payload":{"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"},"canonical_sha256":"397c7d0a76c97fcd94379f99432f2cb1e4bf7e363e1e2f576de667c9ecdf7944","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"},"source_kind":"arxiv","source_id":"2408.05706","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":"2026-07-05T08:54:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KfE8BvI6rOeVjesPplgsdWkitqMJrVN2s1katVSyxFLIa8ujEQPgcF08UKgJ6FY+J5Ufqgjr2qtbEVdnF/rIBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:31:47.221931Z"},"content_sha256":"074eedfe7b5d34409a07daff22b518eb0658c6bd42396ce237eb74dfce495979","schema_version":"1.0","event_id":"sha256:074eedfe7b5d34409a07daff22b518eb0658c6bd42396ce237eb74dfce495979"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HF6H2CTWZF743FBXT6MUGLZMWH","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:54:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OdrUTDXNXF+wAP5uRQzI0NsTTICCk3WKScDgfNnItYDai7aFjvHK3D2Li8jW0psiEs/iy1f0QIH9mjzscQyzAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:31:47.222418Z"},"content_sha256":"e25141129d87a563f68b8b1d11872952d2f8afc89f17b95b6a5d67fcc322d54a","schema_version":"1.0","event_id":"sha256:e25141129d87a563f68b8b1d11872952d2f8afc89f17b95b6a5d67fcc322d54a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HF6H2CTWZF743FBXT6MUGLZMWH/bundle.json","state_url":"https://pith.science/pith/HF6H2CTWZF743FBXT6MUGLZMWH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HF6H2CTWZF743FBXT6MUGLZMWH/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":"2026-08-05T23:31:47Z","links":{"resolver":"https://pith.science/pith/HF6H2CTWZF743FBXT6MUGLZMWH","bundle":"https://pith.science/pith/HF6H2CTWZF743FBXT6MUGLZMWH/bundle.json","state":"https://pith.science/pith/HF6H2CTWZF743FBXT6MUGLZMWH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HF6H2CTWZF743FBXT6MUGLZMWH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HF6H2CTWZF743FBXT6MUGLZMWH","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":"8a900a510bab3c2cf276a7fac699b07d90d84019cb86badaa57d251ecdffc786","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-11T06:36:42Z","title_canon_sha256":"bdf1b9d67c59a292057342d2c6b720398f480d7c3f950726c5e1ac1640c72f1b"},"schema_version":"1.0","source":{"id":"2408.05706","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.05706","created_at":"2026-07-05T08:54:23Z"},{"alias_kind":"arxiv_version","alias_value":"2408.05706v1","created_at":"2026-07-05T08:54:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05706","created_at":"2026-07-05T08:54:23Z"},{"alias_kind":"pith_short_12","alias_value":"HF6H2CTWZF74","created_at":"2026-07-05T08:54:23Z"},{"alias_kind":"pith_short_16","alias_value":"HF6H2CTWZF743FBX","created_at":"2026-07-05T08:54:23Z"},{"alias_kind":"pith_short_8","alias_value":"HF6H2CTW","created_at":"2026-07-05T08:54:23Z"}],"graph_snapshots":[{"event_id":"sha256:e25141129d87a563f68b8b1d11872952d2f8afc89f17b95b6a5d67fcc322d54a","target":"graph","created_at":"2026-07-05T08:54:23Z","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/2408.05706/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Shuai Zhao, Yongkun Du, Yu-Gang Jiang, Zhineng Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-11T06:36:42Z","title":"Decoder Pre-Training with only Text for Scene Text Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.05706","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":"sha256:074eedfe7b5d34409a07daff22b518eb0658c6bd42396ce237eb74dfce495979","target":"record","created_at":"2026-07-05T08:54:23Z","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":"8a900a510bab3c2cf276a7fac699b07d90d84019cb86badaa57d251ecdffc786","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-11T06:36:42Z","title_canon_sha256":"bdf1b9d67c59a292057342d2c6b720398f480d7c3f950726c5e1ac1640c72f1b"},"schema_version":"1.0","source":{"id":"2408.05706","kind":"arxiv","version":1}},"canonical_sha256":"397c7d0a76c97fcd94379f99432f2cb1e4bf7e363e1e2f576de667c9ecdf7944","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"397c7d0a76c97fcd94379f99432f2cb1e4bf7e363e1e2f576de667c9ecdf7944","first_computed_at":"2026-07-05T08:54:23.925490Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:54:23.925490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U69VR2DinDX6CiPuD/NgVoiUkTXNpBxQgLBHhtAHGgGoGzjVOPDyTVlXcmI1VIZAtBICDM5Z/KeKm9R68V5BAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:54:23.925954Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.05706","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:074eedfe7b5d34409a07daff22b518eb0658c6bd42396ce237eb74dfce495979","sha256:e25141129d87a563f68b8b1d11872952d2f8afc89f17b95b6a5d67fcc322d54a"],"state_sha256":"ccfbc4d8c4eb2556e431112ec9a7e55db20964d07a4ae2447e29fff7279bcac1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ma+S6TenlQnsuue8iTvpcIMkAYjGqVDpxXABktYje1PHoH+sYp/ahzl0B1A2Lv7/qacG73M0Rj1Oy6lgpEfTDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T23:31:47.225590Z","bundle_sha256":"8908f19847753c961402fe6618ba7d9a06a02f4cfa0118033e99099308280d54"}}