{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:BKBOHLGO27OF6FMFSQG3T5VOHH","short_pith_number":"pith:BKBOHLGO","schema_version":"1.0","canonical_sha256":"0a82e3acced7dc5f1585940db9f6ae39f71edd76820dcc0f62f419124074c67a","source":{"kind":"arxiv","id":"1704.06726","version":1},"attestation_state":"computed","paper":{"title":"Distant Supervision for Topic Classification of Tweets in Curated Streams","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.IR","authors_text":"Jimmy Lin, Nimesh Ghelani, Salman Mohammed","submitted_at":"2017-04-22T00:23:32Z","abstract_excerpt":"We tackle the challenge of topic classification of tweets in the context of analyzing a large collection of curated streams by news outlets and other organizations to deliver relevant content to users. Our approach is novel in applying distant supervision based on semi-automatically identifying curated streams that are topically focused (for example, on politics, entertainment, or sports). These streams provide a source of labeled data to train topic classifiers that can then be applied to categorize tweets from more topically-diffuse streams. Experiments on both noisy labels and human ground-"},"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":"1704.06726","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-04-22T00:23:32Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"7692304e2914cbf34282c9e4931d99d17e796ae8e04e0979916255f260bd5709","abstract_canon_sha256":"baf67565341a3b8faa621f3ce3784452db421ecb0d7fede6016e341176596aaa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:45:57.765996Z","signature_b64":"fy0eU1nhtJh34bKYdo5Af/VHnjgx6wlsTAEOpLK0mQAW+MztRzItlhmvAsd317Qr0RJtwA6K4/g8ehpQd8/dCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a82e3acced7dc5f1585940db9f6ae39f71edd76820dcc0f62f419124074c67a","last_reissued_at":"2026-05-18T00:45:57.765381Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:45:57.765381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distant Supervision for Topic Classification of Tweets in Curated Streams","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.IR","authors_text":"Jimmy Lin, Nimesh Ghelani, Salman Mohammed","submitted_at":"2017-04-22T00:23:32Z","abstract_excerpt":"We tackle the challenge of topic classification of tweets in the context of analyzing a large collection of curated streams by news outlets and other organizations to deliver relevant content to users. Our approach is novel in applying distant supervision based on semi-automatically identifying curated streams that are topically focused (for example, on politics, entertainment, or sports). These streams provide a source of labeled data to train topic classifiers that can then be applied to categorize tweets from more topically-diffuse streams. Experiments on both noisy labels and human ground-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.06726","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":"1704.06726","created_at":"2026-05-18T00:45:57.765476+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.06726v1","created_at":"2026-05-18T00:45:57.765476+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.06726","created_at":"2026-05-18T00:45:57.765476+00:00"},{"alias_kind":"pith_short_12","alias_value":"BKBOHLGO27OF","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"BKBOHLGO27OF6FMF","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"BKBOHLGO","created_at":"2026-05-18T12:31:08.081275+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/BKBOHLGO27OF6FMFSQG3T5VOHH","json":"https://pith.science/pith/BKBOHLGO27OF6FMFSQG3T5VOHH.json","graph_json":"https://pith.science/api/pith-number/BKBOHLGO27OF6FMFSQG3T5VOHH/graph.json","events_json":"https://pith.science/api/pith-number/BKBOHLGO27OF6FMFSQG3T5VOHH/events.json","paper":"https://pith.science/paper/BKBOHLGO"},"agent_actions":{"view_html":"https://pith.science/pith/BKBOHLGO27OF6FMFSQG3T5VOHH","download_json":"https://pith.science/pith/BKBOHLGO27OF6FMFSQG3T5VOHH.json","view_paper":"https://pith.science/paper/BKBOHLGO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.06726&json=true","fetch_graph":"https://pith.science/api/pith-number/BKBOHLGO27OF6FMFSQG3T5VOHH/graph.json","fetch_events":"https://pith.science/api/pith-number/BKBOHLGO27OF6FMFSQG3T5VOHH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BKBOHLGO27OF6FMFSQG3T5VOHH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BKBOHLGO27OF6FMFSQG3T5VOHH/action/storage_attestation","attest_author":"https://pith.science/pith/BKBOHLGO27OF6FMFSQG3T5VOHH/action/author_attestation","sign_citation":"https://pith.science/pith/BKBOHLGO27OF6FMFSQG3T5VOHH/action/citation_signature","submit_replication":"https://pith.science/pith/BKBOHLGO27OF6FMFSQG3T5VOHH/action/replication_record"}},"created_at":"2026-05-18T00:45:57.765476+00:00","updated_at":"2026-05-18T00:45:57.765476+00:00"}