{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NMKWGJKN6KBLPJOEOVOK3QITZU","short_pith_number":"pith:NMKWGJKN","schema_version":"1.0","canonical_sha256":"6b1563254df282b7a5c4755cadc113cd3b77a8d95191193b25d70485dd06c871","source":{"kind":"arxiv","id":"2605.24064","version":1},"attestation_state":"computed","paper":{"title":"Generative Representation Learning on Hyper-relational Knowledge Graphs via Masked Discrete Diffusion","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jaejun Lee, Joyce Jiyoung Whang, Seheon Kim","submitted_at":"2026-05-22T04:18:30Z","abstract_excerpt":"Hyper-relational knowledge graphs (HKGs) effectively represent complex facts. While inferring new knowledge in HKGs is a critical problem, current methods cast it as a simple link prediction, assuming that nearly all entities and relations within a fact are known, leaving only a single blank to be filled. However, this restricted assumption may not hold in real-world scenarios in which multiple, or even all, constituent components of a fact may be missing simultaneously. To bridge this gap, we introduce a task called fact generation: generating a valid hyper-relational fact from an arbitrarily"},"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":"2605.24064","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T04:18:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c4d36bab22ca73712a1673fde21bf190542344a66c92a6fffa8ea7df5343c330","abstract_canon_sha256":"c0e5bf17ec635970f347dfbd5712003ada5284ce09139e1a24c5b4526cf689fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:02:43.530659Z","signature_b64":"ZLjxYsrDRPXtaXBtILZvcYXyNDGD2zQo0D9WG7P06LeCp3sWgzwU0hi1SztIW49ExmFW0vLmPNNJe6JujwJMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b1563254df282b7a5c4755cadc113cd3b77a8d95191193b25d70485dd06c871","last_reissued_at":"2026-05-26T01:02:43.529912Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:02:43.529912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Representation Learning on Hyper-relational Knowledge Graphs via Masked Discrete Diffusion","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jaejun Lee, Joyce Jiyoung Whang, Seheon Kim","submitted_at":"2026-05-22T04:18:30Z","abstract_excerpt":"Hyper-relational knowledge graphs (HKGs) effectively represent complex facts. While inferring new knowledge in HKGs is a critical problem, current methods cast it as a simple link prediction, assuming that nearly all entities and relations within a fact are known, leaving only a single blank to be filled. However, this restricted assumption may not hold in real-world scenarios in which multiple, or even all, constituent components of a fact may be missing simultaneously. To bridge this gap, we introduce a task called fact generation: generating a valid hyper-relational fact from an arbitrarily"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24064","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/2605.24064/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":"2605.24064","created_at":"2026-05-26T01:02:43.530026+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24064v1","created_at":"2026-05-26T01:02:43.530026+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24064","created_at":"2026-05-26T01:02:43.530026+00:00"},{"alias_kind":"pith_short_12","alias_value":"NMKWGJKN6KBL","created_at":"2026-05-26T01:02:43.530026+00:00"},{"alias_kind":"pith_short_16","alias_value":"NMKWGJKN6KBLPJOE","created_at":"2026-05-26T01:02:43.530026+00:00"},{"alias_kind":"pith_short_8","alias_value":"NMKWGJKN","created_at":"2026-05-26T01:02:43.530026+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/NMKWGJKN6KBLPJOEOVOK3QITZU","json":"https://pith.science/pith/NMKWGJKN6KBLPJOEOVOK3QITZU.json","graph_json":"https://pith.science/api/pith-number/NMKWGJKN6KBLPJOEOVOK3QITZU/graph.json","events_json":"https://pith.science/api/pith-number/NMKWGJKN6KBLPJOEOVOK3QITZU/events.json","paper":"https://pith.science/paper/NMKWGJKN"},"agent_actions":{"view_html":"https://pith.science/pith/NMKWGJKN6KBLPJOEOVOK3QITZU","download_json":"https://pith.science/pith/NMKWGJKN6KBLPJOEOVOK3QITZU.json","view_paper":"https://pith.science/paper/NMKWGJKN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24064&json=true","fetch_graph":"https://pith.science/api/pith-number/NMKWGJKN6KBLPJOEOVOK3QITZU/graph.json","fetch_events":"https://pith.science/api/pith-number/NMKWGJKN6KBLPJOEOVOK3QITZU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NMKWGJKN6KBLPJOEOVOK3QITZU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NMKWGJKN6KBLPJOEOVOK3QITZU/action/storage_attestation","attest_author":"https://pith.science/pith/NMKWGJKN6KBLPJOEOVOK3QITZU/action/author_attestation","sign_citation":"https://pith.science/pith/NMKWGJKN6KBLPJOEOVOK3QITZU/action/citation_signature","submit_replication":"https://pith.science/pith/NMKWGJKN6KBLPJOEOVOK3QITZU/action/replication_record"}},"created_at":"2026-05-26T01:02:43.530026+00:00","updated_at":"2026-05-26T01:02:43.530026+00:00"}