{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:5F5LS5ICSNBGOBGD3WRBJIJ6NT","short_pith_number":"pith:5F5LS5IC","schema_version":"1.0","canonical_sha256":"e97ab9750293426704c3dda214a13e6cec1df42b36b3f29348ac63b30149b43b","source":{"kind":"arxiv","id":"1503.04424","version":1},"attestation_state":"computed","paper":{"title":"Bridging Social Media via Distant Supervision","license":"http://creativecommons.org/licenses/by-nc-sa/3.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Fabrizio Sebastiani, Hassan Sajjad, Tarek El-Ganainy, Walid Magdy","submitted_at":"2015-03-15T13:22:03Z","abstract_excerpt":"Microblog classification has received a lot of attention in recent years. Different classification tasks have been investigated, most of them focusing on classifying microblogs into a small number of classes (five or less) using a training set of manually annotated tweets. Unfortunately, labelling data is tedious and expensive, and finding tweets that cover all the classes of interest is not always straightforward, especially when some of the classes do not frequently arise in practice. In this paper we study an approach to tweet classification based on distant supervision, whereby we automati"},"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":"1503.04424","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/3.0/","primary_cat":"cs.IR","submitted_at":"2015-03-15T13:22:03Z","cross_cats_sorted":[],"title_canon_sha256":"04be90d3b510bd7e8c7a6794080d52b7e563805e79ab3e7aafe8f0fcbf106aec","abstract_canon_sha256":"e5f84caac35737d7c2d9f7ef41bed8a90297ee7db5d431a381c72203f7e1d586"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:15:24.399323Z","signature_b64":"XKLrO7VcA+Nh9KwC4ItQt/UYvZsZMTHwznN3WUsYYwlHt3WwWBkyYJr2uuNRn5nlEA5IvT3VN/6AY57A+WhxBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e97ab9750293426704c3dda214a13e6cec1df42b36b3f29348ac63b30149b43b","last_reissued_at":"2026-07-05T03:15:24.398968Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:15:24.398968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging Social Media via Distant Supervision","license":"http://creativecommons.org/licenses/by-nc-sa/3.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Fabrizio Sebastiani, Hassan Sajjad, Tarek El-Ganainy, Walid Magdy","submitted_at":"2015-03-15T13:22:03Z","abstract_excerpt":"Microblog classification has received a lot of attention in recent years. Different classification tasks have been investigated, most of them focusing on classifying microblogs into a small number of classes (five or less) using a training set of manually annotated tweets. Unfortunately, labelling data is tedious and expensive, and finding tweets that cover all the classes of interest is not always straightforward, especially when some of the classes do not frequently arise in practice. In this paper we study an approach to tweet classification based on distant supervision, whereby we automati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.04424","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/1503.04424/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":"1503.04424","created_at":"2026-07-05T03:15:24.399020+00:00"},{"alias_kind":"arxiv_version","alias_value":"1503.04424v1","created_at":"2026-07-05T03:15:24.399020+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.04424","created_at":"2026-07-05T03:15:24.399020+00:00"},{"alias_kind":"pith_short_12","alias_value":"5F5LS5ICSNBG","created_at":"2026-07-05T03:15:24.399020+00:00"},{"alias_kind":"pith_short_16","alias_value":"5F5LS5ICSNBGOBGD","created_at":"2026-07-05T03:15:24.399020+00:00"},{"alias_kind":"pith_short_8","alias_value":"5F5LS5IC","created_at":"2026-07-05T03:15:24.399020+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/5F5LS5ICSNBGOBGD3WRBJIJ6NT","json":"https://pith.science/pith/5F5LS5ICSNBGOBGD3WRBJIJ6NT.json","graph_json":"https://pith.science/api/pith-number/5F5LS5ICSNBGOBGD3WRBJIJ6NT/graph.json","events_json":"https://pith.science/api/pith-number/5F5LS5ICSNBGOBGD3WRBJIJ6NT/events.json","paper":"https://pith.science/paper/5F5LS5IC"},"agent_actions":{"view_html":"https://pith.science/pith/5F5LS5ICSNBGOBGD3WRBJIJ6NT","download_json":"https://pith.science/pith/5F5LS5ICSNBGOBGD3WRBJIJ6NT.json","view_paper":"https://pith.science/paper/5F5LS5IC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1503.04424&json=true","fetch_graph":"https://pith.science/api/pith-number/5F5LS5ICSNBGOBGD3WRBJIJ6NT/graph.json","fetch_events":"https://pith.science/api/pith-number/5F5LS5ICSNBGOBGD3WRBJIJ6NT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5F5LS5ICSNBGOBGD3WRBJIJ6NT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5F5LS5ICSNBGOBGD3WRBJIJ6NT/action/storage_attestation","attest_author":"https://pith.science/pith/5F5LS5ICSNBGOBGD3WRBJIJ6NT/action/author_attestation","sign_citation":"https://pith.science/pith/5F5LS5ICSNBGOBGD3WRBJIJ6NT/action/citation_signature","submit_replication":"https://pith.science/pith/5F5LS5ICSNBGOBGD3WRBJIJ6NT/action/replication_record"}},"created_at":"2026-07-05T03:15:24.399020+00:00","updated_at":"2026-07-05T03:15:24.399020+00:00"}