{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MNH2CAW4JMWLSFVO3VHH6DPSGM","short_pith_number":"pith:MNH2CAW4","schema_version":"1.0","canonical_sha256":"634fa102dc4b2cb916aedd4e7f0df2333509143071d19746cdd69b02314b33ed","source":{"kind":"arxiv","id":"2305.19957","version":2},"attestation_state":"computed","paper":{"title":"DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text Spotting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Du, Dacheng Tao, Jing Zhang, Juhua Liu, Maoyuan Ye, Shanshan Zhao, Tongliang Liu","submitted_at":"2023-05-31T15:44:00Z","abstract_excerpt":"End-to-end text spotting aims to integrate scene text detection and recognition into a unified framework. Dealing with the relationship between the two sub-tasks plays a pivotal role in designing effective spotters. Although Transformer-based methods eliminate the heuristic post-processing, they still suffer from the synergy issue between the sub-tasks and low training efficiency. Besides, they overlook the exploring on multilingual text spotting which requires an extra script identification task. In this paper, we present DeepSolo++, a simple DETR-like baseline that lets a single decoder with"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2305.19957","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-31T15:44:00Z","cross_cats_sorted":[],"title_canon_sha256":"f779323a9f8ae58233db8258c6e50604d8285143e485b191e2ee2831551f2af5","abstract_canon_sha256":"5ce864838cc2e5efabc8343ae124fdcf5eba7547ece78115b0337ada588fb88b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:26.960078Z","signature_b64":"xa2kAke96dLr54AF/LSB0RJ2sjDMfiYvqVHephvyAkIad9cYuQA0OUz4ZEZkWXE7/X0kRXaX6yuYywmue0woBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"634fa102dc4b2cb916aedd4e7f0df2333509143071d19746cdd69b02314b33ed","last_reissued_at":"2026-07-05T07:57:26.959608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:26.959608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text Spotting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Du, Dacheng Tao, Jing Zhang, Juhua Liu, Maoyuan Ye, Shanshan Zhao, Tongliang Liu","submitted_at":"2023-05-31T15:44:00Z","abstract_excerpt":"End-to-end text spotting aims to integrate scene text detection and recognition into a unified framework. Dealing with the relationship between the two sub-tasks plays a pivotal role in designing effective spotters. Although Transformer-based methods eliminate the heuristic post-processing, they still suffer from the synergy issue between the sub-tasks and low training efficiency. Besides, they overlook the exploring on multilingual text spotting which requires an extra script identification task. In this paper, we present DeepSolo++, a simple DETR-like baseline that lets a single decoder with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19957","kind":"arxiv","version":2},"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/2305.19957/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2305.19957","created_at":"2026-07-05T07:57:26.959666+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.19957v2","created_at":"2026-07-05T07:57:26.959666+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19957","created_at":"2026-07-05T07:57:26.959666+00:00"},{"alias_kind":"pith_short_12","alias_value":"MNH2CAW4JMWL","created_at":"2026-07-05T07:57:26.959666+00:00"},{"alias_kind":"pith_short_16","alias_value":"MNH2CAW4JMWLSFVO","created_at":"2026-07-05T07:57:26.959666+00:00"},{"alias_kind":"pith_short_8","alias_value":"MNH2CAW4","created_at":"2026-07-05T07:57:26.959666+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.15279","citing_title":"BCRNet: Enhancing Landmark Detection in Laparoscopic Liver Surgery via Bezier Curve Refinement","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MNH2CAW4JMWLSFVO3VHH6DPSGM","json":"https://pith.science/pith/MNH2CAW4JMWLSFVO3VHH6DPSGM.json","graph_json":"https://pith.science/api/pith-number/MNH2CAW4JMWLSFVO3VHH6DPSGM/graph.json","events_json":"https://pith.science/api/pith-number/MNH2CAW4JMWLSFVO3VHH6DPSGM/events.json","paper":"https://pith.science/paper/MNH2CAW4"},"agent_actions":{"view_html":"https://pith.science/pith/MNH2CAW4JMWLSFVO3VHH6DPSGM","download_json":"https://pith.science/pith/MNH2CAW4JMWLSFVO3VHH6DPSGM.json","view_paper":"https://pith.science/paper/MNH2CAW4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.19957&json=true","fetch_graph":"https://pith.science/api/pith-number/MNH2CAW4JMWLSFVO3VHH6DPSGM/graph.json","fetch_events":"https://pith.science/api/pith-number/MNH2CAW4JMWLSFVO3VHH6DPSGM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MNH2CAW4JMWLSFVO3VHH6DPSGM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MNH2CAW4JMWLSFVO3VHH6DPSGM/action/storage_attestation","attest_author":"https://pith.science/pith/MNH2CAW4JMWLSFVO3VHH6DPSGM/action/author_attestation","sign_citation":"https://pith.science/pith/MNH2CAW4JMWLSFVO3VHH6DPSGM/action/citation_signature","submit_replication":"https://pith.science/pith/MNH2CAW4JMWLSFVO3VHH6DPSGM/action/replication_record"}},"created_at":"2026-07-05T07:57:26.959666+00:00","updated_at":"2026-07-05T07:57:26.959666+00:00"}