{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JUSTNWIJL64AHIYFJXAKWH2QGS","short_pith_number":"pith:JUSTNWIJ","schema_version":"1.0","canonical_sha256":"4d2536d9095fb803a3054dc0ab1f5034af26069d9e8993533461d24dc7c56748","source":{"kind":"arxiv","id":"2105.01848","version":1},"attestation_state":"computed","paper":{"title":"PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Literature Parsing Task B: Table Recognition to HTML","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dengyi Gu, Jiaquan Ye, Peng Gao, Rong Xiao, Xianbiao Qi, Yelin He, Yihao Chen","submitted_at":"2021-05-05T03:20:26Z","abstract_excerpt":"This paper presents our solution for ICDAR 2021 competition on scientific literature parsing taskB: table recognition to HTML. In our method, we divide the table content recognition task into foursub-tasks: table structure recognition, text line detection, text line recognition, and box assignment.Our table structure recognition algorithm is customized based on MASTER [1], a robust image textrecognition algorithm. PSENet [2] is used to detect each text line in the table image. For text linerecognition, our model is also built on MASTER. Finally, in the box assignment phase, we associatedthe te"},"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":"2105.01848","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-05T03:20:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"18d2dc7c0425f23ff3504e8ddf085ae9b55f371e401880f2861df141e1efed54","abstract_canon_sha256":"15206b3f8ea625e8900c95673bec0630be7f756dd1691cf5ce5208a799be1609"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:37:49.326982Z","signature_b64":"qyofa3fL6kSE/MR+O6qSt2SIA4sv74r0HZxGW5kbnfTUYgJQsOwAt//bTT/kIjIF6q9w1cpdscGFesEqFWHlDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d2536d9095fb803a3054dc0ab1f5034af26069d9e8993533461d24dc7c56748","last_reissued_at":"2026-07-05T02:37:49.326515Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:37:49.326515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Literature Parsing Task B: Table Recognition to HTML","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dengyi Gu, Jiaquan Ye, Peng Gao, Rong Xiao, Xianbiao Qi, Yelin He, Yihao Chen","submitted_at":"2021-05-05T03:20:26Z","abstract_excerpt":"This paper presents our solution for ICDAR 2021 competition on scientific literature parsing taskB: table recognition to HTML. In our method, we divide the table content recognition task into foursub-tasks: table structure recognition, text line detection, text line recognition, and box assignment.Our table structure recognition algorithm is customized based on MASTER [1], a robust image textrecognition algorithm. PSENet [2] is used to detect each text line in the table image. For text linerecognition, our model is also built on MASTER. Finally, in the box assignment phase, we associatedthe te"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.01848","kind":"arxiv","version":1},"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/2105.01848/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":"2105.01848","created_at":"2026-07-05T02:37:49.326579+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.01848v1","created_at":"2026-07-05T02:37:49.326579+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.01848","created_at":"2026-07-05T02:37:49.326579+00:00"},{"alias_kind":"pith_short_12","alias_value":"JUSTNWIJL64A","created_at":"2026-07-05T02:37:49.326579+00:00"},{"alias_kind":"pith_short_16","alias_value":"JUSTNWIJL64AHIYF","created_at":"2026-07-05T02:37:49.326579+00:00"},{"alias_kind":"pith_short_8","alias_value":"JUSTNWIJ","created_at":"2026-07-05T02:37:49.326579+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17874","citing_title":"Revisiting Structural Dependency in Autoregressive Multi-Task Table Recognition via Order-Independent Cell-Level Representations","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2410.21169","citing_title":"Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction","ref_index":280,"is_internal_anchor":false},{"citing_arxiv_id":"2409.18839","citing_title":"MinerU: An Open-Source Solution for Precise Document Content Extraction","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02880","citing_title":"InstructTable: Improving Table Structure Recognition Through Instructions","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16070","citing_title":"TableSeq: Unified Generation of Structure, Content, and Layout","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JUSTNWIJL64AHIYFJXAKWH2QGS","json":"https://pith.science/pith/JUSTNWIJL64AHIYFJXAKWH2QGS.json","graph_json":"https://pith.science/api/pith-number/JUSTNWIJL64AHIYFJXAKWH2QGS/graph.json","events_json":"https://pith.science/api/pith-number/JUSTNWIJL64AHIYFJXAKWH2QGS/events.json","paper":"https://pith.science/paper/JUSTNWIJ"},"agent_actions":{"view_html":"https://pith.science/pith/JUSTNWIJL64AHIYFJXAKWH2QGS","download_json":"https://pith.science/pith/JUSTNWIJL64AHIYFJXAKWH2QGS.json","view_paper":"https://pith.science/paper/JUSTNWIJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.01848&json=true","fetch_graph":"https://pith.science/api/pith-number/JUSTNWIJL64AHIYFJXAKWH2QGS/graph.json","fetch_events":"https://pith.science/api/pith-number/JUSTNWIJL64AHIYFJXAKWH2QGS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JUSTNWIJL64AHIYFJXAKWH2QGS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JUSTNWIJL64AHIYFJXAKWH2QGS/action/storage_attestation","attest_author":"https://pith.science/pith/JUSTNWIJL64AHIYFJXAKWH2QGS/action/author_attestation","sign_citation":"https://pith.science/pith/JUSTNWIJL64AHIYFJXAKWH2QGS/action/citation_signature","submit_replication":"https://pith.science/pith/JUSTNWIJL64AHIYFJXAKWH2QGS/action/replication_record"}},"created_at":"2026-07-05T02:37:49.326579+00:00","updated_at":"2026-07-05T02:37:49.326579+00:00"}