{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CGTVRNJGIZYHFY3F3TGZIBRJXU","short_pith_number":"pith:CGTVRNJG","schema_version":"1.0","canonical_sha256":"11a758b526467072e365dccd940629bd1396c4027bdd35b9e24a6e86015f0f9d","source":{"kind":"arxiv","id":"2205.00619","version":1},"attestation_state":"computed","paper":{"title":"POLITICS: Pretraining with Same-story Article Comparison for Ideology Prediction and Stance Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Wegsman, Lu Wang, Nick Beauchamp, Xinliang Frederick Zhang, Yujian Liu","submitted_at":"2022-05-02T02:10:05Z","abstract_excerpt":"Ideology is at the core of political science research. Yet, there still does not exist general-purpose tools to characterize and predict ideology across different genres of text. To this end, we study Pretrained Language Models using novel ideology-driven pretraining objectives that rely on the comparison of articles on the same story written by media of different ideologies. We further collect a large-scale dataset, consisting of more than 3.6M political news articles, for pretraining. Our model POLITICS outperforms strong baselines and the previous state-of-the-art models on ideology predict"},"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":"2205.00619","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-02T02:10:05Z","cross_cats_sorted":[],"title_canon_sha256":"8082287dbb83a9289160d4f5c0216651f5339ffbae051957110b0150d7c047c4","abstract_canon_sha256":"c54966dd78ead5434960c54952773b472b5d9cbd32418933c67fc5fdefde56fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:19:14.799995Z","signature_b64":"SQLCFaDcT2Ionif6C58nrO8FdhgoLWH17w9fJLLC/yUZl++tKafgCwWGhNWycvI7n8FRZ6xomRsfMZnSJub+Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11a758b526467072e365dccd940629bd1396c4027bdd35b9e24a6e86015f0f9d","last_reissued_at":"2026-07-05T04:19:14.799548Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:19:14.799548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"POLITICS: Pretraining with Same-story Article Comparison for Ideology Prediction and Stance Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Wegsman, Lu Wang, Nick Beauchamp, Xinliang Frederick Zhang, Yujian Liu","submitted_at":"2022-05-02T02:10:05Z","abstract_excerpt":"Ideology is at the core of political science research. Yet, there still does not exist general-purpose tools to characterize and predict ideology across different genres of text. To this end, we study Pretrained Language Models using novel ideology-driven pretraining objectives that rely on the comparison of articles on the same story written by media of different ideologies. We further collect a large-scale dataset, consisting of more than 3.6M political news articles, for pretraining. Our model POLITICS outperforms strong baselines and the previous state-of-the-art models on ideology predict"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.00619","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/2205.00619/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":"2205.00619","created_at":"2026-07-05T04:19:14.799608+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.00619v1","created_at":"2026-07-05T04:19:14.799608+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.00619","created_at":"2026-07-05T04:19:14.799608+00:00"},{"alias_kind":"pith_short_12","alias_value":"CGTVRNJGIZYH","created_at":"2026-07-05T04:19:14.799608+00:00"},{"alias_kind":"pith_short_16","alias_value":"CGTVRNJGIZYHFY3F","created_at":"2026-07-05T04:19:14.799608+00:00"},{"alias_kind":"pith_short_8","alias_value":"CGTVRNJG","created_at":"2026-07-05T04:19:14.799608+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.10467","citing_title":"MGM: Global Understanding of Audience Overlap Graphs for Predicting the Factuality and the Bias of News Media","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CGTVRNJGIZYHFY3F3TGZIBRJXU","json":"https://pith.science/pith/CGTVRNJGIZYHFY3F3TGZIBRJXU.json","graph_json":"https://pith.science/api/pith-number/CGTVRNJGIZYHFY3F3TGZIBRJXU/graph.json","events_json":"https://pith.science/api/pith-number/CGTVRNJGIZYHFY3F3TGZIBRJXU/events.json","paper":"https://pith.science/paper/CGTVRNJG"},"agent_actions":{"view_html":"https://pith.science/pith/CGTVRNJGIZYHFY3F3TGZIBRJXU","download_json":"https://pith.science/pith/CGTVRNJGIZYHFY3F3TGZIBRJXU.json","view_paper":"https://pith.science/paper/CGTVRNJG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.00619&json=true","fetch_graph":"https://pith.science/api/pith-number/CGTVRNJGIZYHFY3F3TGZIBRJXU/graph.json","fetch_events":"https://pith.science/api/pith-number/CGTVRNJGIZYHFY3F3TGZIBRJXU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CGTVRNJGIZYHFY3F3TGZIBRJXU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CGTVRNJGIZYHFY3F3TGZIBRJXU/action/storage_attestation","attest_author":"https://pith.science/pith/CGTVRNJGIZYHFY3F3TGZIBRJXU/action/author_attestation","sign_citation":"https://pith.science/pith/CGTVRNJGIZYHFY3F3TGZIBRJXU/action/citation_signature","submit_replication":"https://pith.science/pith/CGTVRNJGIZYHFY3F3TGZIBRJXU/action/replication_record"}},"created_at":"2026-07-05T04:19:14.799608+00:00","updated_at":"2026-07-05T04:19:14.799608+00:00"}