{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:65BMMBJOIBX7OIR2KQ5TEKACJP","short_pith_number":"pith:65BMMBJO","schema_version":"1.0","canonical_sha256":"f742c6052e406ff7223a543b3228024beed03b26fc88fd0a91aeae99399b3fa7","source":{"kind":"arxiv","id":"1808.07046","version":1},"attestation_state":"computed","paper":{"title":"ISNA-Set: A novel English Corpus of Iran NEWS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hadi Sadoghi-Yazdi, Mohammad Kamel","submitted_at":"2018-08-21T17:58:05Z","abstract_excerpt":"News agencies publish news on their websites all over the world. Moreover, creating novel corpuses is necessary to bring natural processing to new domains. Textual processing of online news is challenging in terms of the strategy of collecting data, the complex structure of news websites, and selecting or designing suitable algorithms for processing these types of data. Despite the previous works which focus on creating corpuses for Iran news in Persian, in this paper, we introduce a new corpus for English news of a national news agency. ISNA-Set is a new dataset of English news of Iranian Stu"},"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":"1808.07046","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-21T17:58:05Z","cross_cats_sorted":[],"title_canon_sha256":"34f04bdd8a09bcffc08fb62b504331a34845c0f4b94ab37244ad07e334f68a5b","abstract_canon_sha256":"140c7e3c8551115ef2e516a32f474700a725b7fbac3e68c758640c5f2c67fb16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:38.302061Z","signature_b64":"HlEaaNEzMfd5g2pNbq4bofOBm+FQi/9d/hM17LMRrd9eVFsK6eHvby4UHcZfMhEzrna3uTC3AdQ+47AlX3JkDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f742c6052e406ff7223a543b3228024beed03b26fc88fd0a91aeae99399b3fa7","last_reissued_at":"2026-05-18T00:07:38.301338Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:38.301338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ISNA-Set: A novel English Corpus of Iran NEWS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hadi Sadoghi-Yazdi, Mohammad Kamel","submitted_at":"2018-08-21T17:58:05Z","abstract_excerpt":"News agencies publish news on their websites all over the world. Moreover, creating novel corpuses is necessary to bring natural processing to new domains. Textual processing of online news is challenging in terms of the strategy of collecting data, the complex structure of news websites, and selecting or designing suitable algorithms for processing these types of data. Despite the previous works which focus on creating corpuses for Iran news in Persian, in this paper, we introduce a new corpus for English news of a national news agency. ISNA-Set is a new dataset of English news of Iranian Stu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.07046","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":""},"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":"1808.07046","created_at":"2026-05-18T00:07:38.301444+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.07046v1","created_at":"2026-05-18T00:07:38.301444+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.07046","created_at":"2026-05-18T00:07:38.301444+00:00"},{"alias_kind":"pith_short_12","alias_value":"65BMMBJOIBX7","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"65BMMBJOIBX7OIR2","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"65BMMBJO","created_at":"2026-05-18T12:32:08.215937+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/65BMMBJOIBX7OIR2KQ5TEKACJP","json":"https://pith.science/pith/65BMMBJOIBX7OIR2KQ5TEKACJP.json","graph_json":"https://pith.science/api/pith-number/65BMMBJOIBX7OIR2KQ5TEKACJP/graph.json","events_json":"https://pith.science/api/pith-number/65BMMBJOIBX7OIR2KQ5TEKACJP/events.json","paper":"https://pith.science/paper/65BMMBJO"},"agent_actions":{"view_html":"https://pith.science/pith/65BMMBJOIBX7OIR2KQ5TEKACJP","download_json":"https://pith.science/pith/65BMMBJOIBX7OIR2KQ5TEKACJP.json","view_paper":"https://pith.science/paper/65BMMBJO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.07046&json=true","fetch_graph":"https://pith.science/api/pith-number/65BMMBJOIBX7OIR2KQ5TEKACJP/graph.json","fetch_events":"https://pith.science/api/pith-number/65BMMBJOIBX7OIR2KQ5TEKACJP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/65BMMBJOIBX7OIR2KQ5TEKACJP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/65BMMBJOIBX7OIR2KQ5TEKACJP/action/storage_attestation","attest_author":"https://pith.science/pith/65BMMBJOIBX7OIR2KQ5TEKACJP/action/author_attestation","sign_citation":"https://pith.science/pith/65BMMBJOIBX7OIR2KQ5TEKACJP/action/citation_signature","submit_replication":"https://pith.science/pith/65BMMBJOIBX7OIR2KQ5TEKACJP/action/replication_record"}},"created_at":"2026-05-18T00:07:38.301444+00:00","updated_at":"2026-05-18T00:07:38.301444+00:00"}