{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:WEDBAYHIEEDLED3Z26DGSQQ2E7","short_pith_number":"pith:WEDBAYHI","schema_version":"1.0","canonical_sha256":"b1061060e82106b20f79d78669421a27f1b4c51a8c8febde1b0827f477f81a51","source":{"kind":"arxiv","id":"2005.14024","version":1},"attestation_state":"computed","paper":{"title":"The POLUSA Dataset: 0.9M Political News Articles Balanced by Time and Outlet Popularity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.SI"],"primary_cat":"cs.DL","authors_text":"Felix Hamborg, Lukas Gebhard","submitted_at":"2020-05-27T14:24:11Z","abstract_excerpt":"News articles covering policy issues are an essential source of information in the social sciences and are also frequently used for other use cases, e.g., to train NLP language models. To derive meaningful insights from the analysis of news, large datasets are required that represent real-world distributions, e.g., with respect to the contained outlets' popularity, topically, or across time. Information on the political leanings of media publishers is often needed, e.g., to study differences in news reporting across the political spectrum, which is one of the prime use cases in the social scie"},"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":"2005.14024","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2020-05-27T14:24:11Z","cross_cats_sorted":["cs.IR","cs.SI"],"title_canon_sha256":"8f06b526c7c4663305bcf422c5c851541fcd8a2b7b43736162204e2f5ea4311f","abstract_canon_sha256":"a2c381260612c222cfb23e4a69ba7b1486079f657d832c51a41381fc4d496728"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:06:27.642150Z","signature_b64":"091cmb60edR9tLGYEHDXr6T2ZcZxC++OnQJSWA3VtXL0M7kzPd474XQCd/h62jn4vgOp2lqHHhc2Grl4PQ4BCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1061060e82106b20f79d78669421a27f1b4c51a8c8febde1b0827f477f81a51","last_reissued_at":"2026-07-05T01:06:27.641719Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:06:27.641719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The POLUSA Dataset: 0.9M Political News Articles Balanced by Time and Outlet Popularity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.SI"],"primary_cat":"cs.DL","authors_text":"Felix Hamborg, Lukas Gebhard","submitted_at":"2020-05-27T14:24:11Z","abstract_excerpt":"News articles covering policy issues are an essential source of information in the social sciences and are also frequently used for other use cases, e.g., to train NLP language models. To derive meaningful insights from the analysis of news, large datasets are required that represent real-world distributions, e.g., with respect to the contained outlets' popularity, topically, or across time. Information on the political leanings of media publishers is often needed, e.g., to study differences in news reporting across the political spectrum, which is one of the prime use cases in the social scie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.14024","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/2005.14024/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":"2005.14024","created_at":"2026-07-05T01:06:27.641775+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.14024v1","created_at":"2026-07-05T01:06:27.641775+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.14024","created_at":"2026-07-05T01:06:27.641775+00:00"},{"alias_kind":"pith_short_12","alias_value":"WEDBAYHIEEDL","created_at":"2026-07-05T01:06:27.641775+00:00"},{"alias_kind":"pith_short_16","alias_value":"WEDBAYHIEEDLED3Z","created_at":"2026-07-05T01:06:27.641775+00:00"},{"alias_kind":"pith_short_8","alias_value":"WEDBAYHI","created_at":"2026-07-05T01:06:27.641775+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/WEDBAYHIEEDLED3Z26DGSQQ2E7","json":"https://pith.science/pith/WEDBAYHIEEDLED3Z26DGSQQ2E7.json","graph_json":"https://pith.science/api/pith-number/WEDBAYHIEEDLED3Z26DGSQQ2E7/graph.json","events_json":"https://pith.science/api/pith-number/WEDBAYHIEEDLED3Z26DGSQQ2E7/events.json","paper":"https://pith.science/paper/WEDBAYHI"},"agent_actions":{"view_html":"https://pith.science/pith/WEDBAYHIEEDLED3Z26DGSQQ2E7","download_json":"https://pith.science/pith/WEDBAYHIEEDLED3Z26DGSQQ2E7.json","view_paper":"https://pith.science/paper/WEDBAYHI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.14024&json=true","fetch_graph":"https://pith.science/api/pith-number/WEDBAYHIEEDLED3Z26DGSQQ2E7/graph.json","fetch_events":"https://pith.science/api/pith-number/WEDBAYHIEEDLED3Z26DGSQQ2E7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WEDBAYHIEEDLED3Z26DGSQQ2E7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WEDBAYHIEEDLED3Z26DGSQQ2E7/action/storage_attestation","attest_author":"https://pith.science/pith/WEDBAYHIEEDLED3Z26DGSQQ2E7/action/author_attestation","sign_citation":"https://pith.science/pith/WEDBAYHIEEDLED3Z26DGSQQ2E7/action/citation_signature","submit_replication":"https://pith.science/pith/WEDBAYHIEEDLED3Z26DGSQQ2E7/action/replication_record"}},"created_at":"2026-07-05T01:06:27.641775+00:00","updated_at":"2026-07-05T01:06:27.641775+00:00"}