{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:OUGURFFDFPBHXSRSL2IHG4QNAH","short_pith_number":"pith:OUGURFFD","canonical_record":{"source":{"id":"2207.08417","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-18T07:54:17Z","cross_cats_sorted":[],"title_canon_sha256":"cfe848204f401c3757fbf2698106834c900dd5a8e07fdf3325b8ada79059d8bc","abstract_canon_sha256":"558212f51ab4dce7750975a8b758d56b70fed28760255c825ac2a37e74993ad9"},"schema_version":"1.0"},"canonical_sha256":"750d4894a32bc27bca325e9073720d01f5420bf61988292b6e6c916eb347fb9d","source":{"kind":"arxiv","id":"2207.08417","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.08417","created_at":"2026-07-05T04:49:54Z"},{"alias_kind":"arxiv_version","alias_value":"2207.08417v3","created_at":"2026-07-05T04:49:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.08417","created_at":"2026-07-05T04:49:54Z"},{"alias_kind":"pith_short_12","alias_value":"OUGURFFDFPBH","created_at":"2026-07-05T04:49:54Z"},{"alias_kind":"pith_short_16","alias_value":"OUGURFFDFPBHXSRS","created_at":"2026-07-05T04:49:54Z"},{"alias_kind":"pith_short_8","alias_value":"OUGURFFD","created_at":"2026-07-05T04:49:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:OUGURFFDFPBHXSRSL2IHG4QNAH","target":"record","payload":{"canonical_record":{"source":{"id":"2207.08417","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-18T07:54:17Z","cross_cats_sorted":[],"title_canon_sha256":"cfe848204f401c3757fbf2698106834c900dd5a8e07fdf3325b8ada79059d8bc","abstract_canon_sha256":"558212f51ab4dce7750975a8b758d56b70fed28760255c825ac2a37e74993ad9"},"schema_version":"1.0"},"canonical_sha256":"750d4894a32bc27bca325e9073720d01f5420bf61988292b6e6c916eb347fb9d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:49:54.144508Z","signature_b64":"Q0zQY2ivcvgw0XnMVSI9U2WMD/mUB8jlDXTZSZLAWqvZNRWtUR8nq1IC+HecUNS7SjpZ4kH6BuTUYfzEsNAuCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"750d4894a32bc27bca325e9073720d01f5420bf61988292b6e6c916eb347fb9d","last_reissued_at":"2026-07-05T04:49:54.144047Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:49:54.144047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.08417","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:49:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sL+01yE515aIZu3nTgLnbin6BWrI26gLJ4qbqwKkoEYQn5UP0vsaBABK/PHW+6byNMrWSjbth+czN9HL1sHvAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:08:05.961119Z"},"content_sha256":"974ad5c3a23090425af96ca0eaf7989ca70149300f8f6732227af000b2189431","schema_version":"1.0","event_id":"sha256:974ad5c3a23090425af96ca0eaf7989ca70149300f8f6732227af000b2189431"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:OUGURFFDFPBHXSRSL2IHG4QNAH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Real-time End-to-End Video Text Spotter with Contrastive Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunhua Shen, Hong Zhou, Jiahong Li, Ping Luo, Size Li, Wejia Wu, Zhongyuan Wang, Zhuang Li","submitted_at":"2022-07-18T07:54:17Z","abstract_excerpt":"Video text spotting(VTS) is the task that requires simultaneously detecting, tracking and recognizing text in the video. Existing video text spotting methods typically develop sophisticated pipelines and multiple models, which is not friend for real-time applications. Here we propose a real-time end-to-end video text spotter with Contrastive Representation learning (CoText). Our contributions are three-fold: 1) CoText simultaneously address the three tasks (e.g., text detection, tracking, recognition) in a real-time end-to-end trainable framework. 2) With contrastive learning, CoText models lo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.08417","kind":"arxiv","version":3},"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/2207.08417/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":"2026-07-05T04:49:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lqoj2AQHVsjMqz8gfEXu69lSe1hqm/XN6mOXQwC2j++VtoYcfBNN2NLHS6qtx9HM9tUQQOLRetYjfio7ztYoDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:08:05.961488Z"},"content_sha256":"6efaba88a6a0526cfeb2ed2a1379228549e95f2fd161ce97bcaf11aa528334e6","schema_version":"1.0","event_id":"sha256:6efaba88a6a0526cfeb2ed2a1379228549e95f2fd161ce97bcaf11aa528334e6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OUGURFFDFPBHXSRSL2IHG4QNAH/bundle.json","state_url":"https://pith.science/pith/OUGURFFDFPBHXSRSL2IHG4QNAH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OUGURFFDFPBHXSRSL2IHG4QNAH/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":"2026-08-06T19:08:05Z","links":{"resolver":"https://pith.science/pith/OUGURFFDFPBHXSRSL2IHG4QNAH","bundle":"https://pith.science/pith/OUGURFFDFPBHXSRSL2IHG4QNAH/bundle.json","state":"https://pith.science/pith/OUGURFFDFPBHXSRSL2IHG4QNAH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OUGURFFDFPBHXSRSL2IHG4QNAH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:OUGURFFDFPBHXSRSL2IHG4QNAH","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":"558212f51ab4dce7750975a8b758d56b70fed28760255c825ac2a37e74993ad9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-18T07:54:17Z","title_canon_sha256":"cfe848204f401c3757fbf2698106834c900dd5a8e07fdf3325b8ada79059d8bc"},"schema_version":"1.0","source":{"id":"2207.08417","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.08417","created_at":"2026-07-05T04:49:54Z"},{"alias_kind":"arxiv_version","alias_value":"2207.08417v3","created_at":"2026-07-05T04:49:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.08417","created_at":"2026-07-05T04:49:54Z"},{"alias_kind":"pith_short_12","alias_value":"OUGURFFDFPBH","created_at":"2026-07-05T04:49:54Z"},{"alias_kind":"pith_short_16","alias_value":"OUGURFFDFPBHXSRS","created_at":"2026-07-05T04:49:54Z"},{"alias_kind":"pith_short_8","alias_value":"OUGURFFD","created_at":"2026-07-05T04:49:54Z"}],"graph_snapshots":[{"event_id":"sha256:6efaba88a6a0526cfeb2ed2a1379228549e95f2fd161ce97bcaf11aa528334e6","target":"graph","created_at":"2026-07-05T04:49:54Z","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/2207.08417/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video text spotting(VTS) is the task that requires simultaneously detecting, tracking and recognizing text in the video. Existing video text spotting methods typically develop sophisticated pipelines and multiple models, which is not friend for real-time applications. Here we propose a real-time end-to-end video text spotter with Contrastive Representation learning (CoText). Our contributions are three-fold: 1) CoText simultaneously address the three tasks (e.g., text detection, tracking, recognition) in a real-time end-to-end trainable framework. 2) With contrastive learning, CoText models lo","authors_text":"Chunhua Shen, Hong Zhou, Jiahong Li, Ping Luo, Size Li, Wejia Wu, Zhongyuan Wang, Zhuang Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-18T07:54:17Z","title":"Real-time End-to-End Video Text Spotter with Contrastive Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.08417","kind":"arxiv","version":3},"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":"sha256:974ad5c3a23090425af96ca0eaf7989ca70149300f8f6732227af000b2189431","target":"record","created_at":"2026-07-05T04:49:54Z","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":"558212f51ab4dce7750975a8b758d56b70fed28760255c825ac2a37e74993ad9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-18T07:54:17Z","title_canon_sha256":"cfe848204f401c3757fbf2698106834c900dd5a8e07fdf3325b8ada79059d8bc"},"schema_version":"1.0","source":{"id":"2207.08417","kind":"arxiv","version":3}},"canonical_sha256":"750d4894a32bc27bca325e9073720d01f5420bf61988292b6e6c916eb347fb9d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"750d4894a32bc27bca325e9073720d01f5420bf61988292b6e6c916eb347fb9d","first_computed_at":"2026-07-05T04:49:54.144047Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:49:54.144047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q0zQY2ivcvgw0XnMVSI9U2WMD/mUB8jlDXTZSZLAWqvZNRWtUR8nq1IC+HecUNS7SjpZ4kH6BuTUYfzEsNAuCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:49:54.144508Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.08417","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:974ad5c3a23090425af96ca0eaf7989ca70149300f8f6732227af000b2189431","sha256:6efaba88a6a0526cfeb2ed2a1379228549e95f2fd161ce97bcaf11aa528334e6"],"state_sha256":"e6687692e1853ee708f76b8ae8a884ab1ea55d07fe1f31d03d725966ff024ee7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NGBS08cfY8/DjFq7avB3TKebJi2c+A3AL84emlUnU/YXBTWQqblQOe2UAeF9txg13sfBcQtN9bu8bYEqfBnJCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T19:08:05.964784Z","bundle_sha256":"d85ed2edca0e9cf76b7a13800e57e2890bcd6c1d9e0b59705ac90cb9230a3d9e"}}