{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HBOMKGMC6XRZPET2A47S76FUY6","short_pith_number":"pith:HBOMKGMC","schema_version":"1.0","canonical_sha256":"385cc51982f5e397927a073f2ff8b4c791eb8e5266d5e302bd9258b835f5b39c","source":{"kind":"arxiv","id":"2404.15254","version":2},"attestation_state":"computed","paper":{"title":"UniMERNet: A Universal Network for Real-World Mathematical Expression Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Wang, Botian Shi, Bo Zhang, Chao Xu, Conghui He, Guang Liang, Zhuangcheng Gu","submitted_at":"2024-04-23T17:39:27Z","abstract_excerpt":"The paper introduces the UniMER dataset, marking the first study on Mathematical Expression Recognition (MER) targeting complex real-world scenarios. The UniMER dataset includes a large-scale training set, UniMER-1M, which offers unprecedented scale and diversity with one million training instances to train high-quality, robust models. Additionally, UniMER features a meticulously designed, diverse test set, UniMER-Test, which covers a variety of formula distributions found in real-world scenarios, providing a more comprehensive and fair evaluation. To better utilize the UniMER dataset, the pap"},"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":"2404.15254","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-23T17:39:27Z","cross_cats_sorted":[],"title_canon_sha256":"f855ed3864c8a82a15d999dd12eecb46e1674c435e3f260504260a816137f5f1","abstract_canon_sha256":"3a80f15513a3f7fe6477149e939b724aeba22abedef27a568a4c94ca4dda4ddc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:03:40.445763Z","signature_b64":"JeqRL+iU6N++Wun1M2iBEdH4yOHsip4Tfn4KePuuNEY21q/svvAjL78hC8NM3aA+Xl5FQiXcty9GqBrGh9HWAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"385cc51982f5e397927a073f2ff8b4c791eb8e5266d5e302bd9258b835f5b39c","last_reissued_at":"2026-07-05T09:03:40.445248Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:03:40.445248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniMERNet: A Universal Network for Real-World Mathematical Expression Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Wang, Botian Shi, Bo Zhang, Chao Xu, Conghui He, Guang Liang, Zhuangcheng Gu","submitted_at":"2024-04-23T17:39:27Z","abstract_excerpt":"The paper introduces the UniMER dataset, marking the first study on Mathematical Expression Recognition (MER) targeting complex real-world scenarios. The UniMER dataset includes a large-scale training set, UniMER-1M, which offers unprecedented scale and diversity with one million training instances to train high-quality, robust models. Additionally, UniMER features a meticulously designed, diverse test set, UniMER-Test, which covers a variety of formula distributions found in real-world scenarios, providing a more comprehensive and fair evaluation. To better utilize the UniMER dataset, the pap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15254","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/2404.15254/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":"2404.15254","created_at":"2026-07-05T09:03:40.445324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.15254v2","created_at":"2026-07-05T09:03:40.445324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15254","created_at":"2026-07-05T09:03:40.445324+00:00"},{"alias_kind":"pith_short_12","alias_value":"HBOMKGMC6XRZ","created_at":"2026-07-05T09:03:40.445324+00:00"},{"alias_kind":"pith_short_16","alias_value":"HBOMKGMC6XRZPET2","created_at":"2026-07-05T09:03:40.445324+00:00"},{"alias_kind":"pith_short_8","alias_value":"HBOMKGMC","created_at":"2026-07-05T09:03:40.445324+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07836","citing_title":"Infinity-Parser2 Technical Report","ref_index":80,"is_internal_anchor":true},{"citing_arxiv_id":"2606.01348","citing_title":"ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2410.21169","citing_title":"Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction","ref_index":238,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22186","citing_title":"MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2409.18839","citing_title":"MinerU: An Open-Source Solution for Precise Document Content Extraction","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2603.23885","citing_title":"Towards Real-World Document Parsing via Realistic Scene Synthesis and Document-Aware Training","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2603.24326","citing_title":"Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processing","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.00161","citing_title":"Q-Mask: Query-driven Causal Masks for Text Anchoring in OCR-Oriented Vision-Language Models","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04771","citing_title":"MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HBOMKGMC6XRZPET2A47S76FUY6","json":"https://pith.science/pith/HBOMKGMC6XRZPET2A47S76FUY6.json","graph_json":"https://pith.science/api/pith-number/HBOMKGMC6XRZPET2A47S76FUY6/graph.json","events_json":"https://pith.science/api/pith-number/HBOMKGMC6XRZPET2A47S76FUY6/events.json","paper":"https://pith.science/paper/HBOMKGMC"},"agent_actions":{"view_html":"https://pith.science/pith/HBOMKGMC6XRZPET2A47S76FUY6","download_json":"https://pith.science/pith/HBOMKGMC6XRZPET2A47S76FUY6.json","view_paper":"https://pith.science/paper/HBOMKGMC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.15254&json=true","fetch_graph":"https://pith.science/api/pith-number/HBOMKGMC6XRZPET2A47S76FUY6/graph.json","fetch_events":"https://pith.science/api/pith-number/HBOMKGMC6XRZPET2A47S76FUY6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HBOMKGMC6XRZPET2A47S76FUY6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HBOMKGMC6XRZPET2A47S76FUY6/action/storage_attestation","attest_author":"https://pith.science/pith/HBOMKGMC6XRZPET2A47S76FUY6/action/author_attestation","sign_citation":"https://pith.science/pith/HBOMKGMC6XRZPET2A47S76FUY6/action/citation_signature","submit_replication":"https://pith.science/pith/HBOMKGMC6XRZPET2A47S76FUY6/action/replication_record"}},"created_at":"2026-07-05T09:03:40.445324+00:00","updated_at":"2026-07-05T09:03:40.445324+00:00"}