{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:D4N2JWQED7RWGIVNSQ3HDA7OGK","short_pith_number":"pith:D4N2JWQE","schema_version":"1.0","canonical_sha256":"1f1ba4da041fe36322ad94367183ee32b3172c2e062448a0b786abe2bbb47618","source":{"kind":"arxiv","id":"2102.04567","version":1},"attestation_state":"computed","paper":{"title":"NELA-GT-2020: A Large Multi-Labelled News Dataset for The Study of Misinformation in News Articles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Benjamin D. Horne, Maur\\'icio Gruppi, Sibel Adal{\\i}","submitted_at":"2021-02-08T22:55:37Z","abstract_excerpt":"In this paper, we present an updated version of the NELA-GT-2019 dataset, entitled NELA-GT-2020. NELA-GT-2020 contains nearly 1.8M news articles from 519 sources collected between January 1st, 2020 and December 31st, 2020. Just as with NELA-GT-2018 and NELA-GT-2019, these sources come from a wide range of mainstream news sources and alternative news sources. Included in the dataset are source-level ground truth labels from Media Bias/Fact Check (MBFC) covering multiple dimensions of veracity. Additionally, new in the 2020 dataset are the Tweets embedded in the collected news articles, adding a"},"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":"2102.04567","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2021-02-08T22:55:37Z","cross_cats_sorted":[],"title_canon_sha256":"5b20c9e17a35a5262a830bf2c27ccf2d612e1b67025386cfa0261c064007b422","abstract_canon_sha256":"e90a71ade64b937a8a264b45e72a5223dfbe28faad201eb42f409ddbca1e2b1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:14:01.928754Z","signature_b64":"Q85mxobm/1AOfTznMutogryOlxVJgk1bmWXA+Cv+1KByleHeWpjTHokcDFNTKQosQBYfdA5y2nJscZqxU7+1Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f1ba4da041fe36322ad94367183ee32b3172c2e062448a0b786abe2bbb47618","last_reissued_at":"2026-07-05T02:14:01.928277Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:14:01.928277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NELA-GT-2020: A Large Multi-Labelled News Dataset for The Study of Misinformation in News Articles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Benjamin D. Horne, Maur\\'icio Gruppi, Sibel Adal{\\i}","submitted_at":"2021-02-08T22:55:37Z","abstract_excerpt":"In this paper, we present an updated version of the NELA-GT-2019 dataset, entitled NELA-GT-2020. NELA-GT-2020 contains nearly 1.8M news articles from 519 sources collected between January 1st, 2020 and December 31st, 2020. Just as with NELA-GT-2018 and NELA-GT-2019, these sources come from a wide range of mainstream news sources and alternative news sources. Included in the dataset are source-level ground truth labels from Media Bias/Fact Check (MBFC) covering multiple dimensions of veracity. Additionally, new in the 2020 dataset are the Tweets embedded in the collected news articles, adding a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.04567","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/2102.04567/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":"2102.04567","created_at":"2026-07-05T02:14:01.928334+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.04567v1","created_at":"2026-07-05T02:14:01.928334+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.04567","created_at":"2026-07-05T02:14:01.928334+00:00"},{"alias_kind":"pith_short_12","alias_value":"D4N2JWQED7RW","created_at":"2026-07-05T02:14:01.928334+00:00"},{"alias_kind":"pith_short_16","alias_value":"D4N2JWQED7RWGIVN","created_at":"2026-07-05T02:14:01.928334+00:00"},{"alias_kind":"pith_short_8","alias_value":"D4N2JWQE","created_at":"2026-07-05T02:14:01.928334+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.21309","citing_title":"When Bigger Isn't Better: A Comprehensive Fairness Evaluation of Political Bias in Multi-News Summarisation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20131","citing_title":"Whose Story Gets Told? Positionality and Bias in LLM Summaries of Life Narratives","ref_index":198,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D4N2JWQED7RWGIVNSQ3HDA7OGK","json":"https://pith.science/pith/D4N2JWQED7RWGIVNSQ3HDA7OGK.json","graph_json":"https://pith.science/api/pith-number/D4N2JWQED7RWGIVNSQ3HDA7OGK/graph.json","events_json":"https://pith.science/api/pith-number/D4N2JWQED7RWGIVNSQ3HDA7OGK/events.json","paper":"https://pith.science/paper/D4N2JWQE"},"agent_actions":{"view_html":"https://pith.science/pith/D4N2JWQED7RWGIVNSQ3HDA7OGK","download_json":"https://pith.science/pith/D4N2JWQED7RWGIVNSQ3HDA7OGK.json","view_paper":"https://pith.science/paper/D4N2JWQE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.04567&json=true","fetch_graph":"https://pith.science/api/pith-number/D4N2JWQED7RWGIVNSQ3HDA7OGK/graph.json","fetch_events":"https://pith.science/api/pith-number/D4N2JWQED7RWGIVNSQ3HDA7OGK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D4N2JWQED7RWGIVNSQ3HDA7OGK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D4N2JWQED7RWGIVNSQ3HDA7OGK/action/storage_attestation","attest_author":"https://pith.science/pith/D4N2JWQED7RWGIVNSQ3HDA7OGK/action/author_attestation","sign_citation":"https://pith.science/pith/D4N2JWQED7RWGIVNSQ3HDA7OGK/action/citation_signature","submit_replication":"https://pith.science/pith/D4N2JWQED7RWGIVNSQ3HDA7OGK/action/replication_record"}},"created_at":"2026-07-05T02:14:01.928334+00:00","updated_at":"2026-07-05T02:14:01.928334+00:00"}