{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JQEJTHV4WQFOGZUPKHJAP4HT5L","short_pith_number":"pith:JQEJTHV4","schema_version":"1.0","canonical_sha256":"4c08999ebcb40ae3668f51d207f0f3eae70b4d728fe203674e4c5a85cec54033","source":{"kind":"arxiv","id":"2502.19512","version":1},"attestation_state":"computed","paper":{"title":"TRIX: A More Expressive Model for Zero-shot Domain Transfer in Knowledge Graphs","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Beatrice Bevilacqua, Bruno Ribeiro, Mikhail Galkin, Yucheng Zhang","submitted_at":"2025-02-26T19:23:49Z","abstract_excerpt":"Fully inductive knowledge graph models can be trained on multiple domains and subsequently perform zero-shot knowledge graph completion (KGC) in new unseen domains. This is an important capability towards the goal of having foundation models for knowledge graphs. In this work, we introduce a more expressive and capable fully inductive model, dubbed TRIX, which not only yields strictly more expressive triplet embeddings (head entity, relation, tail entity) compared to state-of-the-art methods, but also introduces a new capability: directly handling both entity and relation prediction tasks in i"},"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":"2502.19512","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-26T19:23:49Z","cross_cats_sorted":[],"title_canon_sha256":"63779a83bb4bacb2f802fb7ec671f551364450588c399095854655731f3c9fdc","abstract_canon_sha256":"8ff761e133358b27e754b2d58fffa5261221d48a977261387424134d26098a21"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:47.848828Z","signature_b64":"aG5aDKXvVTb0d5bx27WSFlH+IbsvShvvUA04OUr1xhLFPSha/u03Lj/KRO+/ipf5HhE//fwX8rxd4EJvujbJDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c08999ebcb40ae3668f51d207f0f3eae70b4d728fe203674e4c5a85cec54033","last_reissued_at":"2026-07-05T10:20:47.848299Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:47.848299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TRIX: A More Expressive Model for Zero-shot Domain Transfer in Knowledge Graphs","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Beatrice Bevilacqua, Bruno Ribeiro, Mikhail Galkin, Yucheng Zhang","submitted_at":"2025-02-26T19:23:49Z","abstract_excerpt":"Fully inductive knowledge graph models can be trained on multiple domains and subsequently perform zero-shot knowledge graph completion (KGC) in new unseen domains. This is an important capability towards the goal of having foundation models for knowledge graphs. In this work, we introduce a more expressive and capable fully inductive model, dubbed TRIX, which not only yields strictly more expressive triplet embeddings (head entity, relation, tail entity) compared to state-of-the-art methods, but also introduces a new capability: directly handling both entity and relation prediction tasks in i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.19512","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/2502.19512/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":"2502.19512","created_at":"2026-07-05T10:20:47.848375+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.19512v1","created_at":"2026-07-05T10:20:47.848375+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.19512","created_at":"2026-07-05T10:20:47.848375+00:00"},{"alias_kind":"pith_short_12","alias_value":"JQEJTHV4WQFO","created_at":"2026-07-05T10:20:47.848375+00:00"},{"alias_kind":"pith_short_16","alias_value":"JQEJTHV4WQFOGZUP","created_at":"2026-07-05T10:20:47.848375+00:00"},{"alias_kind":"pith_short_8","alias_value":"JQEJTHV4","created_at":"2026-07-05T10:20:47.848375+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14907","citing_title":"KGPFN: Unlocking the Potential of Knowledge Graph Foundation Model via In-Context Learning","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2601.21174","citing_title":"Breaking the Reasoning Horizon in Entity Alignment Foundation Models","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JQEJTHV4WQFOGZUPKHJAP4HT5L","json":"https://pith.science/pith/JQEJTHV4WQFOGZUPKHJAP4HT5L.json","graph_json":"https://pith.science/api/pith-number/JQEJTHV4WQFOGZUPKHJAP4HT5L/graph.json","events_json":"https://pith.science/api/pith-number/JQEJTHV4WQFOGZUPKHJAP4HT5L/events.json","paper":"https://pith.science/paper/JQEJTHV4"},"agent_actions":{"view_html":"https://pith.science/pith/JQEJTHV4WQFOGZUPKHJAP4HT5L","download_json":"https://pith.science/pith/JQEJTHV4WQFOGZUPKHJAP4HT5L.json","view_paper":"https://pith.science/paper/JQEJTHV4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.19512&json=true","fetch_graph":"https://pith.science/api/pith-number/JQEJTHV4WQFOGZUPKHJAP4HT5L/graph.json","fetch_events":"https://pith.science/api/pith-number/JQEJTHV4WQFOGZUPKHJAP4HT5L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JQEJTHV4WQFOGZUPKHJAP4HT5L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JQEJTHV4WQFOGZUPKHJAP4HT5L/action/storage_attestation","attest_author":"https://pith.science/pith/JQEJTHV4WQFOGZUPKHJAP4HT5L/action/author_attestation","sign_citation":"https://pith.science/pith/JQEJTHV4WQFOGZUPKHJAP4HT5L/action/citation_signature","submit_replication":"https://pith.science/pith/JQEJTHV4WQFOGZUPKHJAP4HT5L/action/replication_record"}},"created_at":"2026-07-05T10:20:47.848375+00:00","updated_at":"2026-07-05T10:20:47.848375+00:00"}