{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FEGICTQCXGTGYXMCQCMFQCR22H","short_pith_number":"pith:FEGICTQC","schema_version":"1.0","canonical_sha256":"290c814e02b9a66c5d828098580a3ad1e31542d62695e4c8c4e7b94bb25dba61","source":{"kind":"arxiv","id":"2307.05627","version":1},"attestation_state":"computed","paper":{"title":"Separate-and-Aggregate: A Transformer-based Patch Refinement Model for Knowledge Graph Completion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chen Chen, Kwok-Yan Lam, Quan Z. Sheng, Yang Zhang, Yufei Wang","submitted_at":"2023-07-11T06:27:13Z","abstract_excerpt":"Knowledge graph completion (KGC) is the task of inferencing missing facts from any given knowledge graphs (KG). Previous KGC methods typically represent knowledge graph entities and relations as trainable continuous embeddings and fuse the embeddings of the entity $h$ (or $t$) and relation $r$ into hidden representations of query $(h, r, ?)$ (or $(?, r, t$)) to approximate the missing entities. To achieve this, they either use shallow linear transformations or deep convolutional modules. However, the linear transformations suffer from the expressiveness issue while the deep convolutional modul"},"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":"2307.05627","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-11T06:27:13Z","cross_cats_sorted":[],"title_canon_sha256":"3b7c3d706508adc92eec8a96f99838ab1ba39211d97d75f34bf75d5ddc4d31e0","abstract_canon_sha256":"a686adbdd1451f5368b430ae5e3dcc1903645ea016a7a27d3b7bca67311af692"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:30:10.610248Z","signature_b64":"dy/jrNbx1gWIHDEUWU99Q4ubZsWO2LG6RKAg6CkVLUxeAyV03VzMmEVxQL8xtNTZAX+ONItOvdfnStilE4ZTCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"290c814e02b9a66c5d828098580a3ad1e31542d62695e4c8c4e7b94bb25dba61","last_reissued_at":"2026-07-05T06:30:10.609642Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:30:10.609642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Separate-and-Aggregate: A Transformer-based Patch Refinement Model for Knowledge Graph Completion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chen Chen, Kwok-Yan Lam, Quan Z. Sheng, Yang Zhang, Yufei Wang","submitted_at":"2023-07-11T06:27:13Z","abstract_excerpt":"Knowledge graph completion (KGC) is the task of inferencing missing facts from any given knowledge graphs (KG). Previous KGC methods typically represent knowledge graph entities and relations as trainable continuous embeddings and fuse the embeddings of the entity $h$ (or $t$) and relation $r$ into hidden representations of query $(h, r, ?)$ (or $(?, r, t$)) to approximate the missing entities. To achieve this, they either use shallow linear transformations or deep convolutional modules. However, the linear transformations suffer from the expressiveness issue while the deep convolutional modul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.05627","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/2307.05627/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":"2307.05627","created_at":"2026-07-05T06:30:10.609697+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.05627v1","created_at":"2026-07-05T06:30:10.609697+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.05627","created_at":"2026-07-05T06:30:10.609697+00:00"},{"alias_kind":"pith_short_12","alias_value":"FEGICTQCXGTG","created_at":"2026-07-05T06:30:10.609697+00:00"},{"alias_kind":"pith_short_16","alias_value":"FEGICTQCXGTGYXMC","created_at":"2026-07-05T06:30:10.609697+00:00"},{"alias_kind":"pith_short_8","alias_value":"FEGICTQC","created_at":"2026-07-05T06:30:10.609697+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/FEGICTQCXGTGYXMCQCMFQCR22H","json":"https://pith.science/pith/FEGICTQCXGTGYXMCQCMFQCR22H.json","graph_json":"https://pith.science/api/pith-number/FEGICTQCXGTGYXMCQCMFQCR22H/graph.json","events_json":"https://pith.science/api/pith-number/FEGICTQCXGTGYXMCQCMFQCR22H/events.json","paper":"https://pith.science/paper/FEGICTQC"},"agent_actions":{"view_html":"https://pith.science/pith/FEGICTQCXGTGYXMCQCMFQCR22H","download_json":"https://pith.science/pith/FEGICTQCXGTGYXMCQCMFQCR22H.json","view_paper":"https://pith.science/paper/FEGICTQC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.05627&json=true","fetch_graph":"https://pith.science/api/pith-number/FEGICTQCXGTGYXMCQCMFQCR22H/graph.json","fetch_events":"https://pith.science/api/pith-number/FEGICTQCXGTGYXMCQCMFQCR22H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FEGICTQCXGTGYXMCQCMFQCR22H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FEGICTQCXGTGYXMCQCMFQCR22H/action/storage_attestation","attest_author":"https://pith.science/pith/FEGICTQCXGTGYXMCQCMFQCR22H/action/author_attestation","sign_citation":"https://pith.science/pith/FEGICTQCXGTGYXMCQCMFQCR22H/action/citation_signature","submit_replication":"https://pith.science/pith/FEGICTQCXGTGYXMCQCMFQCR22H/action/replication_record"}},"created_at":"2026-07-05T06:30:10.609697+00:00","updated_at":"2026-07-05T06:30:10.609697+00:00"}