{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:446TGTYE3FSOH5SPBG2OOOGFVX","short_pith_number":"pith:446TGTYE","schema_version":"1.0","canonical_sha256":"e73d334f04d964e3f64f09b4e738c5add2efd8d4a2f8562f50f395bd798915f8","source":{"kind":"arxiv","id":"2401.07105","version":3},"attestation_state":"computed","paper":{"title":"Graph Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anette Frank, Moritz Plenz","submitted_at":"2024-01-13T16:09:49Z","abstract_excerpt":"While Language Models (LMs) are the workhorses of NLP, their interplay with structured knowledge graphs (KGs) is still actively researched. Current methods for encoding such graphs typically either (i) linearize them for embedding with LMs -- which underutilize structural information, or (ii) use Graph Neural Networks (GNNs) to preserve the graph structure -- but GNNs cannot represent text features as well as pretrained LMs. In our work we introduce a novel LM type, the Graph Language Model (GLM), that integrates the strengths of both approaches and mitigates their weaknesses. The GLM paramete"},"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":"2401.07105","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-13T16:09:49Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0cdd80f6118f76b3b116353934b80112cdebb06af3e247dae6e0b7531c2a0bb8","abstract_canon_sha256":"902824b11af83da74f53d900406eb187a7509d988f71d36a200116ac9beb7fd5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:17.755517Z","signature_b64":"DD9mqvM3JRZQqzSIQcQjWFh0y/PbbNppprGu3hpkVKGfEUSKqjSKv7ULPkd4dPtEM3LAewSf0fc8TvoWcicnAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e73d334f04d964e3f64f09b4e738c5add2efd8d4a2f8562f50f395bd798915f8","last_reissued_at":"2026-07-05T08:26:17.754928Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:17.754928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anette Frank, Moritz Plenz","submitted_at":"2024-01-13T16:09:49Z","abstract_excerpt":"While Language Models (LMs) are the workhorses of NLP, their interplay with structured knowledge graphs (KGs) is still actively researched. Current methods for encoding such graphs typically either (i) linearize them for embedding with LMs -- which underutilize structural information, or (ii) use Graph Neural Networks (GNNs) to preserve the graph structure -- but GNNs cannot represent text features as well as pretrained LMs. In our work we introduce a novel LM type, the Graph Language Model (GLM), that integrates the strengths of both approaches and mitigates their weaknesses. The GLM paramete"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.07105","kind":"arxiv","version":3},"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/2401.07105/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":"2401.07105","created_at":"2026-07-05T08:26:17.755003+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.07105v3","created_at":"2026-07-05T08:26:17.755003+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.07105","created_at":"2026-07-05T08:26:17.755003+00:00"},{"alias_kind":"pith_short_12","alias_value":"446TGTYE3FSO","created_at":"2026-07-05T08:26:17.755003+00:00"},{"alias_kind":"pith_short_16","alias_value":"446TGTYE3FSOH5SP","created_at":"2026-07-05T08:26:17.755003+00:00"},{"alias_kind":"pith_short_8","alias_value":"446TGTYE","created_at":"2026-07-05T08:26:17.755003+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/446TGTYE3FSOH5SPBG2OOOGFVX","json":"https://pith.science/pith/446TGTYE3FSOH5SPBG2OOOGFVX.json","graph_json":"https://pith.science/api/pith-number/446TGTYE3FSOH5SPBG2OOOGFVX/graph.json","events_json":"https://pith.science/api/pith-number/446TGTYE3FSOH5SPBG2OOOGFVX/events.json","paper":"https://pith.science/paper/446TGTYE"},"agent_actions":{"view_html":"https://pith.science/pith/446TGTYE3FSOH5SPBG2OOOGFVX","download_json":"https://pith.science/pith/446TGTYE3FSOH5SPBG2OOOGFVX.json","view_paper":"https://pith.science/paper/446TGTYE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.07105&json=true","fetch_graph":"https://pith.science/api/pith-number/446TGTYE3FSOH5SPBG2OOOGFVX/graph.json","fetch_events":"https://pith.science/api/pith-number/446TGTYE3FSOH5SPBG2OOOGFVX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/446TGTYE3FSOH5SPBG2OOOGFVX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/446TGTYE3FSOH5SPBG2OOOGFVX/action/storage_attestation","attest_author":"https://pith.science/pith/446TGTYE3FSOH5SPBG2OOOGFVX/action/author_attestation","sign_citation":"https://pith.science/pith/446TGTYE3FSOH5SPBG2OOOGFVX/action/citation_signature","submit_replication":"https://pith.science/pith/446TGTYE3FSOH5SPBG2OOOGFVX/action/replication_record"}},"created_at":"2026-07-05T08:26:17.755003+00:00","updated_at":"2026-07-05T08:26:17.755003+00:00"}