{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FSKQX3TV2K5G5LYSTKYZAAGHSS","short_pith_number":"pith:FSKQX3TV","schema_version":"1.0","canonical_sha256":"2c950bee75d2ba6eaf129ab19000c7949a54f629bc71de1b2d0fc5cc42912bf1","source":{"kind":"arxiv","id":"2503.10515","version":2},"attestation_state":"computed","paper":{"title":"Probing LLMs for Multilingual Discourse Generalization Through a Unified Label Set","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Barbara Plank, Florian Eichin, Michael A. Hedderich, Yang Janet Liu","submitted_at":"2025-03-13T16:20:25Z","abstract_excerpt":"Discourse understanding is essential for many NLP tasks, yet most existing work remains constrained by framework-dependent discourse representations. This work investigates whether large language models (LLMs) capture discourse knowledge that generalizes across languages and frameworks. We address this question along two dimensions: (1) developing a unified discourse relation label set to facilitate cross-lingual and cross-framework discourse analysis, and (2) probing LLMs to assess whether they encode generalizable discourse abstractions. Using multilingual discourse relation classification 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":"2503.10515","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-13T16:20:25Z","cross_cats_sorted":[],"title_canon_sha256":"6070b5c886a0f0f05eb62fb7eed4969c1ed981e83b3135412c2fc880aa987841","abstract_canon_sha256":"943d17f98218dc251cf4cd8852498bfc4a2553a89ac0d9bf5a31f886bc8f5748"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:45.272389Z","signature_b64":"Ff6azegK8AL/LqTwSuIcwVH689Aa5mNaA1LxfJNNt/Ki0h6jXNU+WXAN5jVTDdXu/Kkn0aDwtOl1gi6vFblNCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c950bee75d2ba6eaf129ab19000c7949a54f629bc71de1b2d0fc5cc42912bf1","last_reissued_at":"2026-07-05T11:15:45.271923Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:45.271923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Probing LLMs for Multilingual Discourse Generalization Through a Unified Label Set","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Barbara Plank, Florian Eichin, Michael A. Hedderich, Yang Janet Liu","submitted_at":"2025-03-13T16:20:25Z","abstract_excerpt":"Discourse understanding is essential for many NLP tasks, yet most existing work remains constrained by framework-dependent discourse representations. This work investigates whether large language models (LLMs) capture discourse knowledge that generalizes across languages and frameworks. We address this question along two dimensions: (1) developing a unified discourse relation label set to facilitate cross-lingual and cross-framework discourse analysis, and (2) probing LLMs to assess whether they encode generalizable discourse abstractions. Using multilingual discourse relation classification a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10515","kind":"arxiv","version":2},"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/2503.10515/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":"2503.10515","created_at":"2026-07-05T11:15:45.271980+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.10515v2","created_at":"2026-07-05T11:15:45.271980+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10515","created_at":"2026-07-05T11:15:45.271980+00:00"},{"alias_kind":"pith_short_12","alias_value":"FSKQX3TV2K5G","created_at":"2026-07-05T11:15:45.271980+00:00"},{"alias_kind":"pith_short_16","alias_value":"FSKQX3TV2K5G5LYS","created_at":"2026-07-05T11:15:45.271980+00:00"},{"alias_kind":"pith_short_8","alias_value":"FSKQX3TV","created_at":"2026-07-05T11:15:45.271980+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/FSKQX3TV2K5G5LYSTKYZAAGHSS","json":"https://pith.science/pith/FSKQX3TV2K5G5LYSTKYZAAGHSS.json","graph_json":"https://pith.science/api/pith-number/FSKQX3TV2K5G5LYSTKYZAAGHSS/graph.json","events_json":"https://pith.science/api/pith-number/FSKQX3TV2K5G5LYSTKYZAAGHSS/events.json","paper":"https://pith.science/paper/FSKQX3TV"},"agent_actions":{"view_html":"https://pith.science/pith/FSKQX3TV2K5G5LYSTKYZAAGHSS","download_json":"https://pith.science/pith/FSKQX3TV2K5G5LYSTKYZAAGHSS.json","view_paper":"https://pith.science/paper/FSKQX3TV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.10515&json=true","fetch_graph":"https://pith.science/api/pith-number/FSKQX3TV2K5G5LYSTKYZAAGHSS/graph.json","fetch_events":"https://pith.science/api/pith-number/FSKQX3TV2K5G5LYSTKYZAAGHSS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FSKQX3TV2K5G5LYSTKYZAAGHSS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FSKQX3TV2K5G5LYSTKYZAAGHSS/action/storage_attestation","attest_author":"https://pith.science/pith/FSKQX3TV2K5G5LYSTKYZAAGHSS/action/author_attestation","sign_citation":"https://pith.science/pith/FSKQX3TV2K5G5LYSTKYZAAGHSS/action/citation_signature","submit_replication":"https://pith.science/pith/FSKQX3TV2K5G5LYSTKYZAAGHSS/action/replication_record"}},"created_at":"2026-07-05T11:15:45.271980+00:00","updated_at":"2026-07-05T11:15:45.271980+00:00"}