{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:W2JN5T2FAHLGZC3S77VWSFJ2PW","short_pith_number":"pith:W2JN5T2F","schema_version":"1.0","canonical_sha256":"b692decf4501d66c8b72ffeb69153a7da2966a1b901934dc505140432eddcce6","source":{"kind":"arxiv","id":"2606.20089","version":1},"attestation_state":"computed","paper":{"title":"IHUBERT: Vector-Based Semantic Deduplication and Domain-Balanced Pretraining for Persian Resources","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Arash Ghafouri, Hossein Saberi, Mahdi Firouzmandi, Mohammad Reza Hasani Ahangar","submitted_at":"2026-06-18T11:10:22Z","abstract_excerpt":"Persian pretrained language models (PLMs) are still limited by the scarcity of large-scale, high-quality pretraining corpora and by insufficient evaluation beyond standard classification and NER tasks. We present IHUBERT, a monolingual Persian PLM trained from scratch with the RoBERTa-base encoder (125M parameters) on a 45 GB curated subset of the Sepahr-Danesh collection (about 7-8B tokens). To improve corpus quality and reduce redundancy, we employ a multi-stage preprocessing pipeline that includes normalization, exact and near-duplicate removal, anonymization, and vector-database-based sema"},"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":"2606.20089","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-18T11:10:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"59777d143b0e9c1c88ed5699a147eba258857a141802366e8ad96bd3492d28df","abstract_canon_sha256":"58dc7398bd65cb182c842c3ae385a9fb06db257d7a652447c1a77d59ca2f36ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:13:02.588829Z","signature_b64":"9mApyYSPKuLE+ZDDLF2o/Afr9oo5g9Yj7ANaQ5gOJAkflmu3lUzoj4LhxqfxmQVz85NGFbfa/AS0lr1/3/vRAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b692decf4501d66c8b72ffeb69153a7da2966a1b901934dc505140432eddcce6","last_reissued_at":"2026-06-19T16:13:02.588410Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:13:02.588410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IHUBERT: Vector-Based Semantic Deduplication and Domain-Balanced Pretraining for Persian Resources","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Arash Ghafouri, Hossein Saberi, Mahdi Firouzmandi, Mohammad Reza Hasani Ahangar","submitted_at":"2026-06-18T11:10:22Z","abstract_excerpt":"Persian pretrained language models (PLMs) are still limited by the scarcity of large-scale, high-quality pretraining corpora and by insufficient evaluation beyond standard classification and NER tasks. We present IHUBERT, a monolingual Persian PLM trained from scratch with the RoBERTa-base encoder (125M parameters) on a 45 GB curated subset of the Sepahr-Danesh collection (about 7-8B tokens). To improve corpus quality and reduce redundancy, we employ a multi-stage preprocessing pipeline that includes normalization, exact and near-duplicate removal, anonymization, and vector-database-based sema"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20089","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/2606.20089/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":"2606.20089","created_at":"2026-06-19T16:13:02.588467+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20089v1","created_at":"2026-06-19T16:13:02.588467+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20089","created_at":"2026-06-19T16:13:02.588467+00:00"},{"alias_kind":"pith_short_12","alias_value":"W2JN5T2FAHLG","created_at":"2026-06-19T16:13:02.588467+00:00"},{"alias_kind":"pith_short_16","alias_value":"W2JN5T2FAHLGZC3S","created_at":"2026-06-19T16:13:02.588467+00:00"},{"alias_kind":"pith_short_8","alias_value":"W2JN5T2F","created_at":"2026-06-19T16:13:02.588467+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/W2JN5T2FAHLGZC3S77VWSFJ2PW","json":"https://pith.science/pith/W2JN5T2FAHLGZC3S77VWSFJ2PW.json","graph_json":"https://pith.science/api/pith-number/W2JN5T2FAHLGZC3S77VWSFJ2PW/graph.json","events_json":"https://pith.science/api/pith-number/W2JN5T2FAHLGZC3S77VWSFJ2PW/events.json","paper":"https://pith.science/paper/W2JN5T2F"},"agent_actions":{"view_html":"https://pith.science/pith/W2JN5T2FAHLGZC3S77VWSFJ2PW","download_json":"https://pith.science/pith/W2JN5T2FAHLGZC3S77VWSFJ2PW.json","view_paper":"https://pith.science/paper/W2JN5T2F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20089&json=true","fetch_graph":"https://pith.science/api/pith-number/W2JN5T2FAHLGZC3S77VWSFJ2PW/graph.json","fetch_events":"https://pith.science/api/pith-number/W2JN5T2FAHLGZC3S77VWSFJ2PW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W2JN5T2FAHLGZC3S77VWSFJ2PW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W2JN5T2FAHLGZC3S77VWSFJ2PW/action/storage_attestation","attest_author":"https://pith.science/pith/W2JN5T2FAHLGZC3S77VWSFJ2PW/action/author_attestation","sign_citation":"https://pith.science/pith/W2JN5T2FAHLGZC3S77VWSFJ2PW/action/citation_signature","submit_replication":"https://pith.science/pith/W2JN5T2FAHLGZC3S77VWSFJ2PW/action/replication_record"}},"created_at":"2026-06-19T16:13:02.588467+00:00","updated_at":"2026-06-19T16:13:02.588467+00:00"}