{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2OVK7CJDSEOWO2PDZTH6WVDRQV","short_pith_number":"pith:2OVK7CJD","schema_version":"1.0","canonical_sha256":"d3aaaf8923911d6769e3cccfeb547185584a5f9ca830565606a881182fe22ada","source":{"kind":"arxiv","id":"2502.16949","version":3},"attestation_state":"computed","paper":{"title":"SparseTransX: Efficient Training of Translation-Based Knowledge Graph Embeddings Using Sparse Matrix Operations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Ariful Azad, Md Saidul Hoque Anik","submitted_at":"2025-02-24T08:21:48Z","abstract_excerpt":"Knowledge graph (KG) learning offers a powerful framework for generating new knowledge and making inferences. Training KG embedding can take a significantly long time, especially for larger datasets. Our analysis shows that the gradient computation of embedding is one of the dominant functions in the translation-based KG embedding training loop. We address this issue by replacing the core embedding computation with SpMM (Sparse-Dense Matrix Multiplication) kernels. This allows us to unify multiple scatter (and gather) operations as a single operation, reducing training time and memory usage. W"},"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":"2502.16949","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-24T08:21:48Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"bf7421906ec0c1d86519993efb64148a96df8aaabda14cd7bf9d16c327f6627e","abstract_canon_sha256":"edd72624d3c4191376584b4494c96682b0c42dc96b817d21b240f920f46f3f1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:15.940356Z","signature_b64":"PfOnSgPuuD/2vKB/ZGgKaJl7bKxTnHylB6rOVj57CejXhVjpQ9heqK6DjoO+/hHuPEPOe+DXOEe1dKvVZa+eAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3aaaf8923911d6769e3cccfeb547185584a5f9ca830565606a881182fe22ada","last_reissued_at":"2026-07-05T10:56:15.939913Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:15.939913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SparseTransX: Efficient Training of Translation-Based Knowledge Graph Embeddings Using Sparse Matrix Operations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Ariful Azad, Md Saidul Hoque Anik","submitted_at":"2025-02-24T08:21:48Z","abstract_excerpt":"Knowledge graph (KG) learning offers a powerful framework for generating new knowledge and making inferences. Training KG embedding can take a significantly long time, especially for larger datasets. Our analysis shows that the gradient computation of embedding is one of the dominant functions in the translation-based KG embedding training loop. We address this issue by replacing the core embedding computation with SpMM (Sparse-Dense Matrix Multiplication) kernels. This allows us to unify multiple scatter (and gather) operations as a single operation, reducing training time and memory usage. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.16949","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/2502.16949/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":"2502.16949","created_at":"2026-07-05T10:56:15.939966+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.16949v3","created_at":"2026-07-05T10:56:15.939966+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.16949","created_at":"2026-07-05T10:56:15.939966+00:00"},{"alias_kind":"pith_short_12","alias_value":"2OVK7CJDSEOW","created_at":"2026-07-05T10:56:15.939966+00:00"},{"alias_kind":"pith_short_16","alias_value":"2OVK7CJDSEOWO2PD","created_at":"2026-07-05T10:56:15.939966+00:00"},{"alias_kind":"pith_short_8","alias_value":"2OVK7CJD","created_at":"2026-07-05T10:56:15.939966+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/2OVK7CJDSEOWO2PDZTH6WVDRQV","json":"https://pith.science/pith/2OVK7CJDSEOWO2PDZTH6WVDRQV.json","graph_json":"https://pith.science/api/pith-number/2OVK7CJDSEOWO2PDZTH6WVDRQV/graph.json","events_json":"https://pith.science/api/pith-number/2OVK7CJDSEOWO2PDZTH6WVDRQV/events.json","paper":"https://pith.science/paper/2OVK7CJD"},"agent_actions":{"view_html":"https://pith.science/pith/2OVK7CJDSEOWO2PDZTH6WVDRQV","download_json":"https://pith.science/pith/2OVK7CJDSEOWO2PDZTH6WVDRQV.json","view_paper":"https://pith.science/paper/2OVK7CJD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.16949&json=true","fetch_graph":"https://pith.science/api/pith-number/2OVK7CJDSEOWO2PDZTH6WVDRQV/graph.json","fetch_events":"https://pith.science/api/pith-number/2OVK7CJDSEOWO2PDZTH6WVDRQV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2OVK7CJDSEOWO2PDZTH6WVDRQV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2OVK7CJDSEOWO2PDZTH6WVDRQV/action/storage_attestation","attest_author":"https://pith.science/pith/2OVK7CJDSEOWO2PDZTH6WVDRQV/action/author_attestation","sign_citation":"https://pith.science/pith/2OVK7CJDSEOWO2PDZTH6WVDRQV/action/citation_signature","submit_replication":"https://pith.science/pith/2OVK7CJDSEOWO2PDZTH6WVDRQV/action/replication_record"}},"created_at":"2026-07-05T10:56:15.939966+00:00","updated_at":"2026-07-05T10:56:15.939966+00:00"}