{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TOKZAPUQ7VFWEMJ5HLQRNHLNY4","short_pith_number":"pith:TOKZAPUQ","schema_version":"1.0","canonical_sha256":"9b95903e90fd4b62313d3ae1169d6dc70411c1607fe24193ea7c993580fd1817","source":{"kind":"arxiv","id":"2502.07172","version":3},"attestation_state":"computed","paper":{"title":"SemiHMER: Semi-supervised Handwritten Mathematical Expression Recognition using pseudo-labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haoyang Shen, Kehua Chen","submitted_at":"2025-02-11T01:39:11Z","abstract_excerpt":"In this paper, we study semi-supervised Handwritten Mathematical Expression Recognition (HMER) via exploring both labeled data and extra unlabeled data. We propose a novel consistency regularization framework, termed SemiHMER, which introduces dual-branch semi-supervised learning. Specifically, we enforce consistency between the two networks for the same input image. The pseudo-label, generated by one perturbed recognition network, is utilized to supervise the other network using the standard cross-entropy loss. The SemiHMER consistency encourages high similarity between the predictions of the"},"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":"2502.07172","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-11T01:39:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bb11f649521a80754bd15966fd420fcd9764256d90305c66398ceab7fea1ee5d","abstract_canon_sha256":"3942a96cbd32f6475384405eacb240cd3dd8e7eea2558a0cdcf90a3494f389e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:16.468298Z","signature_b64":"OgPWubtRG5YSH2643rSW3SGJpapEYQfQo2tshl6QAOT+/Wy1KkC1u5Fo7bVf7LrKZb/u/0xM4RvuWm3EO6phDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b95903e90fd4b62313d3ae1169d6dc70411c1607fe24193ea7c993580fd1817","last_reissued_at":"2026-07-05T10:17:16.467831Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:16.467831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SemiHMER: Semi-supervised Handwritten Mathematical Expression Recognition using pseudo-labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haoyang Shen, Kehua Chen","submitted_at":"2025-02-11T01:39:11Z","abstract_excerpt":"In this paper, we study semi-supervised Handwritten Mathematical Expression Recognition (HMER) via exploring both labeled data and extra unlabeled data. We propose a novel consistency regularization framework, termed SemiHMER, which introduces dual-branch semi-supervised learning. Specifically, we enforce consistency between the two networks for the same input image. The pseudo-label, generated by one perturbed recognition network, is utilized to supervise the other network using the standard cross-entropy loss. The SemiHMER consistency encourages high similarity between the predictions of the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07172","kind":"arxiv","version":3},"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/2502.07172/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":"2502.07172","created_at":"2026-07-05T10:17:16.467886+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.07172v3","created_at":"2026-07-05T10:17:16.467886+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07172","created_at":"2026-07-05T10:17:16.467886+00:00"},{"alias_kind":"pith_short_12","alias_value":"TOKZAPUQ7VFW","created_at":"2026-07-05T10:17:16.467886+00:00"},{"alias_kind":"pith_short_16","alias_value":"TOKZAPUQ7VFWEMJ5","created_at":"2026-07-05T10:17:16.467886+00:00"},{"alias_kind":"pith_short_8","alias_value":"TOKZAPUQ","created_at":"2026-07-05T10:17:16.467886+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.05557","citing_title":"MMHMER:Multi-viewer and Multi-task for Handwritten Mathematical Expression Recognition","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TOKZAPUQ7VFWEMJ5HLQRNHLNY4","json":"https://pith.science/pith/TOKZAPUQ7VFWEMJ5HLQRNHLNY4.json","graph_json":"https://pith.science/api/pith-number/TOKZAPUQ7VFWEMJ5HLQRNHLNY4/graph.json","events_json":"https://pith.science/api/pith-number/TOKZAPUQ7VFWEMJ5HLQRNHLNY4/events.json","paper":"https://pith.science/paper/TOKZAPUQ"},"agent_actions":{"view_html":"https://pith.science/pith/TOKZAPUQ7VFWEMJ5HLQRNHLNY4","download_json":"https://pith.science/pith/TOKZAPUQ7VFWEMJ5HLQRNHLNY4.json","view_paper":"https://pith.science/paper/TOKZAPUQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.07172&json=true","fetch_graph":"https://pith.science/api/pith-number/TOKZAPUQ7VFWEMJ5HLQRNHLNY4/graph.json","fetch_events":"https://pith.science/api/pith-number/TOKZAPUQ7VFWEMJ5HLQRNHLNY4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TOKZAPUQ7VFWEMJ5HLQRNHLNY4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TOKZAPUQ7VFWEMJ5HLQRNHLNY4/action/storage_attestation","attest_author":"https://pith.science/pith/TOKZAPUQ7VFWEMJ5HLQRNHLNY4/action/author_attestation","sign_citation":"https://pith.science/pith/TOKZAPUQ7VFWEMJ5HLQRNHLNY4/action/citation_signature","submit_replication":"https://pith.science/pith/TOKZAPUQ7VFWEMJ5HLQRNHLNY4/action/replication_record"}},"created_at":"2026-07-05T10:17:16.467886+00:00","updated_at":"2026-07-05T10:17:16.467886+00:00"}