{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5JQEBGKSRAOD52CUTAZKGSAFTM","short_pith_number":"pith:5JQEBGKS","schema_version":"1.0","canonical_sha256":"ea60409952881c3ee8549832a348059b3cb148d565abd6c9148140b1aeef0c73","source":{"kind":"arxiv","id":"2211.10772","version":4},"attestation_state":"computed","paper":{"title":"DeepSolo: Let Transformer Decoder with Explicit Points Solo for 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":"2022-11-19T19:06:22Z","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. In this paper, we present DeepSolo, a simple DETR-like baseline that lets a single Decoder with Explicit Points Solo for text detection and recognition simultaneously. Technically, for each text instance, we represen"},"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":"2211.10772","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-19T19:06:22Z","cross_cats_sorted":[],"title_canon_sha256":"eba76a0fb70da3741651bc34892a9bc888d56d91e851c0b69ba519f6040b8d72","abstract_canon_sha256":"a54dcf1c0a9a48489201d1209e69fba791748fb14420d7db74f04b5e834658e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:28.310109Z","signature_b64":"ESGtdyCMEMB4FDAIKLHs4lJdcasNO8wdx5sJ/cVa3bJPR4xWONfA+XfzCLNbeFRtkowA0r07bkunPN5xeXSiDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea60409952881c3ee8549832a348059b3cb148d565abd6c9148140b1aeef0c73","last_reissued_at":"2026-07-05T05:51:28.309656Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:28.309656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepSolo: Let Transformer Decoder with Explicit Points Solo for 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":"2022-11-19T19:06:22Z","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. In this paper, we present DeepSolo, a simple DETR-like baseline that lets a single Decoder with Explicit Points Solo for text detection and recognition simultaneously. Technically, for each text instance, we represen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.10772","kind":"arxiv","version":4},"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/2211.10772/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":"2211.10772","created_at":"2026-07-05T05:51:28.309713+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.10772v4","created_at":"2026-07-05T05:51:28.309713+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.10772","created_at":"2026-07-05T05:51:28.309713+00:00"},{"alias_kind":"pith_short_12","alias_value":"5JQEBGKSRAOD","created_at":"2026-07-05T05:51:28.309713+00:00"},{"alias_kind":"pith_short_16","alias_value":"5JQEBGKSRAOD52CU","created_at":"2026-07-05T05:51:28.309713+00:00"},{"alias_kind":"pith_short_8","alias_value":"5JQEBGKS","created_at":"2026-07-05T05:51:28.309713+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.15010","citing_title":"Hyper-Local Deformable Transformers for Text Spotting on Historical Maps","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5JQEBGKSRAOD52CUTAZKGSAFTM","json":"https://pith.science/pith/5JQEBGKSRAOD52CUTAZKGSAFTM.json","graph_json":"https://pith.science/api/pith-number/5JQEBGKSRAOD52CUTAZKGSAFTM/graph.json","events_json":"https://pith.science/api/pith-number/5JQEBGKSRAOD52CUTAZKGSAFTM/events.json","paper":"https://pith.science/paper/5JQEBGKS"},"agent_actions":{"view_html":"https://pith.science/pith/5JQEBGKSRAOD52CUTAZKGSAFTM","download_json":"https://pith.science/pith/5JQEBGKSRAOD52CUTAZKGSAFTM.json","view_paper":"https://pith.science/paper/5JQEBGKS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.10772&json=true","fetch_graph":"https://pith.science/api/pith-number/5JQEBGKSRAOD52CUTAZKGSAFTM/graph.json","fetch_events":"https://pith.science/api/pith-number/5JQEBGKSRAOD52CUTAZKGSAFTM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5JQEBGKSRAOD52CUTAZKGSAFTM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5JQEBGKSRAOD52CUTAZKGSAFTM/action/storage_attestation","attest_author":"https://pith.science/pith/5JQEBGKSRAOD52CUTAZKGSAFTM/action/author_attestation","sign_citation":"https://pith.science/pith/5JQEBGKSRAOD52CUTAZKGSAFTM/action/citation_signature","submit_replication":"https://pith.science/pith/5JQEBGKSRAOD52CUTAZKGSAFTM/action/replication_record"}},"created_at":"2026-07-05T05:51:28.309713+00:00","updated_at":"2026-07-05T05:51:28.309713+00:00"}