{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:P6JSXPHGVHNTWXMC4N7G2R7FG6","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":"bd1d22d9f938babb3b74c4af576002f876f828dfddcd37c17c328a98b8ce1600","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-20T12:14:58Z","title_canon_sha256":"73752332ee350676436e56204c8f667b1bc08e09c5431083c447ae2c9c1f62c9"},"schema_version":"1.0","source":{"id":"2203.10539","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.10539","created_at":"2026-07-05T04:50:15Z"},{"alias_kind":"arxiv_version","alias_value":"2203.10539v3","created_at":"2026-07-05T04:50:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.10539","created_at":"2026-07-05T04:50:15Z"},{"alias_kind":"pith_short_12","alias_value":"P6JSXPHGVHNT","created_at":"2026-07-05T04:50:15Z"},{"alias_kind":"pith_short_16","alias_value":"P6JSXPHGVHNTWXMC","created_at":"2026-07-05T04:50:15Z"},{"alias_kind":"pith_short_8","alias_value":"P6JSXPHG","created_at":"2026-07-05T04:50:15Z"}],"graph_snapshots":[{"event_id":"sha256:217e2ef14bd86cc0d022f37a18fd16758b2849b66daabdf63ddf7454aae329e4","target":"graph","created_at":"2026-07-05T04:50:15Z","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/2203.10539/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent video text spotting methods usually require the three-staged pipeline, i.e., detecting text in individual images, recognizing localized text, tracking text streams with post-processing to generate final results. These methods typically follow the tracking-by-match paradigm and develop sophisticated pipelines. In this paper, rooted in Transformer sequence modeling, we propose a simple, but effective end-to-end video text DEtection, Tracking, and Recognition framework (TransDETR). TransDETR mainly includes two advantages: 1) Different from the explicit match paradigm in the adjacent frame","authors_text":"Chunhua Shen, Debing Zhang, Hong Zhou, Ping Luo, Weijia Wu, Ying Fu, Yuanqiang Cai","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-20T12:14:58Z","title":"End-to-End Video Text Spotting with Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.10539","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":"sha256:4b1281bfa1469d28903045739a1a0729a668cef50992a35ae883762e8a459c74","target":"record","created_at":"2026-07-05T04:50:15Z","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":"bd1d22d9f938babb3b74c4af576002f876f828dfddcd37c17c328a98b8ce1600","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-20T12:14:58Z","title_canon_sha256":"73752332ee350676436e56204c8f667b1bc08e09c5431083c447ae2c9c1f62c9"},"schema_version":"1.0","source":{"id":"2203.10539","kind":"arxiv","version":3}},"canonical_sha256":"7f932bbce6a9db3b5d82e37e6d47e53798ff5f2b9a94a20de07954acdd8545c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f932bbce6a9db3b5d82e37e6d47e53798ff5f2b9a94a20de07954acdd8545c1","first_computed_at":"2026-07-05T04:50:15.306934Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:50:15.306934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7D1iWZSMAd3MnEj6AklmW5RBs/osomA5puW5gKDXL1DLX2qQ4MUpoxaONzA2xHv8XjqIZxu0qJeBGcaOEQR2BA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:50:15.307446Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.10539","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b1281bfa1469d28903045739a1a0729a668cef50992a35ae883762e8a459c74","sha256:217e2ef14bd86cc0d022f37a18fd16758b2849b66daabdf63ddf7454aae329e4"],"state_sha256":"33d66b959e152cc635c9b25a9c1a3000fcfe998da4abb9ad7173d31432cc8c37"}