{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OR2OGTNPYSPA3WTJUOEO4JTXEC","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":"7498c60a1c954d8029315d045f69dfe182b30a00c9df245b5b3c60791afb8493","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-30T15:49:03Z","title_canon_sha256":"b0c79dd6f82f83e24f9ddce3490fba90822772d2f0413b10beae41fb291bf308"},"schema_version":"1.0","source":{"id":"2404.19652","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.19652","created_at":"2026-07-05T09:44:34Z"},{"alias_kind":"arxiv_version","alias_value":"2404.19652v4","created_at":"2026-07-05T09:44:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.19652","created_at":"2026-07-05T09:44:34Z"},{"alias_kind":"pith_short_12","alias_value":"OR2OGTNPYSPA","created_at":"2026-07-05T09:44:34Z"},{"alias_kind":"pith_short_16","alias_value":"OR2OGTNPYSPA3WTJ","created_at":"2026-07-05T09:44:34Z"},{"alias_kind":"pith_short_8","alias_value":"OR2OGTNP","created_at":"2026-07-05T09:44:34Z"}],"graph_snapshots":[{"event_id":"sha256:8d8fa9209dddb3c3ebf23b9adc6064f5215e73843eefa143bd77fcac819ee927","target":"graph","created_at":"2026-07-05T09:44:34Z","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/2404.19652/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text spotting, a task involving the extraction of textual information from image or video sequences, faces challenges in cross-domain adaption, such as image-to-image and image-to-video generalization. In this paper, we introduce a new method, termed VimTS, which enhances the generalization ability of the model by achieving better synergy among different tasks. Typically, we propose a Prompt Queries Generation Module and a Tasks-aware Adapter to effectively convert the original single-task model into a multi-task model suitable for both image and video scenarios with minimal additional paramet","authors_text":"Chunhua Shen, Hao Lu, Hao Yan, Lianwen Jin, Linger Deng, Mingxin Huang, Weijia Wu, Xiang Bai, Yuliang Liu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-30T15:49:03Z","title":"VimTS: A Unified Video and Image Text Spotter for Enhancing the Cross-domain Generalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.19652","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":"sha256:0f3b50b7fa844a8d0a6135ac45feecf6f6d6c2a54377800a38a9e7520845cfa7","target":"record","created_at":"2026-07-05T09:44:34Z","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":"7498c60a1c954d8029315d045f69dfe182b30a00c9df245b5b3c60791afb8493","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-30T15:49:03Z","title_canon_sha256":"b0c79dd6f82f83e24f9ddce3490fba90822772d2f0413b10beae41fb291bf308"},"schema_version":"1.0","source":{"id":"2404.19652","kind":"arxiv","version":4}},"canonical_sha256":"7474e34dafc49e0dda69a388ee2677208f0931c3c8c5fcae482715fd7b8ccbd8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7474e34dafc49e0dda69a388ee2677208f0931c3c8c5fcae482715fd7b8ccbd8","first_computed_at":"2026-07-05T09:44:34.170121Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:44:34.170121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VESQ+GDRBk9FlUBeV+ewBdMXgvU3Jt+zAsuFG29nIb7C1ugJ7KTHTbRA01NkPpC474mAh1ZFjktHj10oARWOBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:44:34.170628Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.19652","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f3b50b7fa844a8d0a6135ac45feecf6f6d6c2a54377800a38a9e7520845cfa7","sha256:8d8fa9209dddb3c3ebf23b9adc6064f5215e73843eefa143bd77fcac819ee927"],"state_sha256":"a9aea961d685066e603471f9210f179a7beaa6278f2810279eb9082b01490a60"}