{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FRAHVTKO34YJGF5XSCQR34JI3Y","short_pith_number":"pith:FRAHVTKO","schema_version":"1.0","canonical_sha256":"2c407acd4edf309317b790a11df128de2b366096516b054b98f0fc2589097890","source":{"kind":"arxiv","id":"2508.03250","version":4},"attestation_state":"computed","paper":{"title":"RooseBERT: A New Deal For Political Language Modelling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Deborah Dore, Elena Cabrio, Serena Villata","submitted_at":"2025-08-05T09:28:20Z","abstract_excerpt":"The increasing amount of political debates and politics-related discussions calls for the definition of novel computational methods to automatically analyse such content with the final goal of lightening up political deliberation to citizens. However, the specificity of the political language and the argumentative form of these debates (employing hidden communication strategies and leveraging implicit arguments) make this task very challenging, even for current general-purpose pre-trained Language Models (LMs). To address this, we introduce a novel pre-trained LM for political discourse langua"},"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":"2508.03250","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-05T09:28:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1e01663c76a6892838c47da3a4e3c0125b623ad30eaa6c86cff5f885b61c37b5","abstract_canon_sha256":"4c352d3f26df6a5e1daae8c8d178815e52eb32d0946176577d30841e4ca6c326"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:09:50.524944Z","signature_b64":"S6ytSFZrgviFgNmH+FI8fS8t4yTGNHuVxds3cm9HwNwVScz8NKRsCx1Hz9c4kMoUArpTfrCirXwk0is8jGdMCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c407acd4edf309317b790a11df128de2b366096516b054b98f0fc2589097890","last_reissued_at":"2026-06-19T16:09:50.524552Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:09:50.524552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RooseBERT: A New Deal For Political Language Modelling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Deborah Dore, Elena Cabrio, Serena Villata","submitted_at":"2025-08-05T09:28:20Z","abstract_excerpt":"The increasing amount of political debates and politics-related discussions calls for the definition of novel computational methods to automatically analyse such content with the final goal of lightening up political deliberation to citizens. However, the specificity of the political language and the argumentative form of these debates (employing hidden communication strategies and leveraging implicit arguments) make this task very challenging, even for current general-purpose pre-trained Language Models (LMs). To address this, we introduce a novel pre-trained LM for political discourse langua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.03250","kind":"arxiv","version":4},"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/2508.03250/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":"2508.03250","created_at":"2026-06-19T16:09:50.524608+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.03250v4","created_at":"2026-06-19T16:09:50.524608+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.03250","created_at":"2026-06-19T16:09:50.524608+00:00"},{"alias_kind":"pith_short_12","alias_value":"FRAHVTKO34YJ","created_at":"2026-06-19T16:09:50.524608+00:00"},{"alias_kind":"pith_short_16","alias_value":"FRAHVTKO34YJGF5X","created_at":"2026-06-19T16:09:50.524608+00:00"},{"alias_kind":"pith_short_8","alias_value":"FRAHVTKO","created_at":"2026-06-19T16:09:50.524608+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/FRAHVTKO34YJGF5XSCQR34JI3Y","json":"https://pith.science/pith/FRAHVTKO34YJGF5XSCQR34JI3Y.json","graph_json":"https://pith.science/api/pith-number/FRAHVTKO34YJGF5XSCQR34JI3Y/graph.json","events_json":"https://pith.science/api/pith-number/FRAHVTKO34YJGF5XSCQR34JI3Y/events.json","paper":"https://pith.science/paper/FRAHVTKO"},"agent_actions":{"view_html":"https://pith.science/pith/FRAHVTKO34YJGF5XSCQR34JI3Y","download_json":"https://pith.science/pith/FRAHVTKO34YJGF5XSCQR34JI3Y.json","view_paper":"https://pith.science/paper/FRAHVTKO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.03250&json=true","fetch_graph":"https://pith.science/api/pith-number/FRAHVTKO34YJGF5XSCQR34JI3Y/graph.json","fetch_events":"https://pith.science/api/pith-number/FRAHVTKO34YJGF5XSCQR34JI3Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FRAHVTKO34YJGF5XSCQR34JI3Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FRAHVTKO34YJGF5XSCQR34JI3Y/action/storage_attestation","attest_author":"https://pith.science/pith/FRAHVTKO34YJGF5XSCQR34JI3Y/action/author_attestation","sign_citation":"https://pith.science/pith/FRAHVTKO34YJGF5XSCQR34JI3Y/action/citation_signature","submit_replication":"https://pith.science/pith/FRAHVTKO34YJGF5XSCQR34JI3Y/action/replication_record"}},"created_at":"2026-06-19T16:09:50.524608+00:00","updated_at":"2026-06-19T16:09:50.524608+00:00"}