{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FOFNI6S4NACPRKADK2HHCYXMIR","short_pith_number":"pith:FOFNI6S4","schema_version":"1.0","canonical_sha256":"2b8ad47a5c6804f8a803568e7162ec447ab91f453cc251767cb26ad920baf796","source":{"kind":"arxiv","id":"2505.06624","version":1},"attestation_state":"computed","paper":{"title":"The Efficiency of Pre-training with Objective Masking in Pseudo Labeling for Semi-Supervised Text Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arezoo Hatefi, Frank Drewes, Monowar Bhuyan, Xuan-Son Vu","submitted_at":"2025-05-10T12:16:03Z","abstract_excerpt":"We extend and study a semi-supervised model for text classification proposed earlier by Hatefi et al. for classification tasks in which document classes are described by a small number of gold-labeled examples, while the majority of training examples is unlabeled. The model leverages the teacher-student architecture of Meta Pseudo Labels in which a ''teacher'' generates labels for originally unlabeled training data to train the ''student'' and updates its own model iteratively based on the performance of the student on the gold-labeled portion of the data. We extend the original model of Hatef"},"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":"2505.06624","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-10T12:16:03Z","cross_cats_sorted":[],"title_canon_sha256":"58a9f682e2381a6a2f910216b4bb1ec9cf402e0888b11a6a19cf1183dee9bdee","abstract_canon_sha256":"55c6a6e538b0b57333a990a14ba1af08344a9e5c1dfed9e2a63b8340263395bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:13.228313Z","signature_b64":"unXU4ubJBdLpfuz5XpzQJuga6GV4G12ozKXY60FTMzZTHPImdFyDPsyrjZJARl5PMEgoT4WOEQ3lpLVzRW3nCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b8ad47a5c6804f8a803568e7162ec447ab91f453cc251767cb26ad920baf796","last_reissued_at":"2026-07-05T11:01:13.227849Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:13.227849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Efficiency of Pre-training with Objective Masking in Pseudo Labeling for Semi-Supervised Text Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arezoo Hatefi, Frank Drewes, Monowar Bhuyan, Xuan-Son Vu","submitted_at":"2025-05-10T12:16:03Z","abstract_excerpt":"We extend and study a semi-supervised model for text classification proposed earlier by Hatefi et al. for classification tasks in which document classes are described by a small number of gold-labeled examples, while the majority of training examples is unlabeled. The model leverages the teacher-student architecture of Meta Pseudo Labels in which a ''teacher'' generates labels for originally unlabeled training data to train the ''student'' and updates its own model iteratively based on the performance of the student on the gold-labeled portion of the data. We extend the original model of Hatef"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06624","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/2505.06624/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":"2505.06624","created_at":"2026-07-05T11:01:13.227903+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.06624v1","created_at":"2026-07-05T11:01:13.227903+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06624","created_at":"2026-07-05T11:01:13.227903+00:00"},{"alias_kind":"pith_short_12","alias_value":"FOFNI6S4NACP","created_at":"2026-07-05T11:01:13.227903+00:00"},{"alias_kind":"pith_short_16","alias_value":"FOFNI6S4NACPRKAD","created_at":"2026-07-05T11:01:13.227903+00:00"},{"alias_kind":"pith_short_8","alias_value":"FOFNI6S4","created_at":"2026-07-05T11:01:13.227903+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FOFNI6S4NACPRKADK2HHCYXMIR","json":"https://pith.science/pith/FOFNI6S4NACPRKADK2HHCYXMIR.json","graph_json":"https://pith.science/api/pith-number/FOFNI6S4NACPRKADK2HHCYXMIR/graph.json","events_json":"https://pith.science/api/pith-number/FOFNI6S4NACPRKADK2HHCYXMIR/events.json","paper":"https://pith.science/paper/FOFNI6S4"},"agent_actions":{"view_html":"https://pith.science/pith/FOFNI6S4NACPRKADK2HHCYXMIR","download_json":"https://pith.science/pith/FOFNI6S4NACPRKADK2HHCYXMIR.json","view_paper":"https://pith.science/paper/FOFNI6S4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.06624&json=true","fetch_graph":"https://pith.science/api/pith-number/FOFNI6S4NACPRKADK2HHCYXMIR/graph.json","fetch_events":"https://pith.science/api/pith-number/FOFNI6S4NACPRKADK2HHCYXMIR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FOFNI6S4NACPRKADK2HHCYXMIR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FOFNI6S4NACPRKADK2HHCYXMIR/action/storage_attestation","attest_author":"https://pith.science/pith/FOFNI6S4NACPRKADK2HHCYXMIR/action/author_attestation","sign_citation":"https://pith.science/pith/FOFNI6S4NACPRKADK2HHCYXMIR/action/citation_signature","submit_replication":"https://pith.science/pith/FOFNI6S4NACPRKADK2HHCYXMIR/action/replication_record"}},"created_at":"2026-07-05T11:01:13.227903+00:00","updated_at":"2026-07-05T11:01:13.227903+00:00"}