{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:B37BMMHN6AGCOM4XTPPXEORJ4L","short_pith_number":"pith:B37BMMHN","schema_version":"1.0","canonical_sha256":"0efe1630edf00c2733979bdf723a29e2f6193113aefd5b783070ecd10ad61a7b","source":{"kind":"arxiv","id":"2303.03922","version":1},"attestation_state":"computed","paper":{"title":"Structure Pretraining and Prompt Tuning for Knowledge Graph Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Huajun Chen, Mingyang Chen, Wenting Song, Wen Zhang, Yajing Xu, Yufeng Huang, Yushan Zhu, Yuxia Geng","submitted_at":"2023-03-03T02:58:17Z","abstract_excerpt":"Knowledge graphs (KG) are essential background knowledge providers in many tasks. When designing models for KG-related tasks, one of the key tasks is to devise the Knowledge Representation and Fusion (KRF) module that learns the representation of elements from KGs and fuses them with task representations. While due to the difference of KGs and perspectives to be considered during fusion across tasks, duplicate and ad hoc KRF modules design are conducted among tasks. In this paper, we propose a novel knowledge graph pretraining model KGTransformer that could serve as a uniform KRF module in div"},"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":"2303.03922","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-03T02:58:17Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"35dbf8b7201cc0e87547b9f25bc861226050000004fc33214cc90cab1eb1f917","abstract_canon_sha256":"bc1043a58d894100af79a426c3756d1a7eab42e600a9ff0d9837a3d0815f4ebe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:00.990454Z","signature_b64":"VJyt+oLF9KRwIwsh3i1UxmIjMp+D8sKpByYQZV6OyqeMb3k2GCZkSGlGbEcmPfGR7/SPeaSH6k7ZcXEYRIsHBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0efe1630edf00c2733979bdf723a29e2f6193113aefd5b783070ecd10ad61a7b","last_reissued_at":"2026-07-05T05:49:00.990012Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:00.990012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structure Pretraining and Prompt Tuning for Knowledge Graph Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Huajun Chen, Mingyang Chen, Wenting Song, Wen Zhang, Yajing Xu, Yufeng Huang, Yushan Zhu, Yuxia Geng","submitted_at":"2023-03-03T02:58:17Z","abstract_excerpt":"Knowledge graphs (KG) are essential background knowledge providers in many tasks. When designing models for KG-related tasks, one of the key tasks is to devise the Knowledge Representation and Fusion (KRF) module that learns the representation of elements from KGs and fuses them with task representations. While due to the difference of KGs and perspectives to be considered during fusion across tasks, duplicate and ad hoc KRF modules design are conducted among tasks. In this paper, we propose a novel knowledge graph pretraining model KGTransformer that could serve as a uniform KRF module in div"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.03922","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/2303.03922/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":"2303.03922","created_at":"2026-07-05T05:49:00.990069+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.03922v1","created_at":"2026-07-05T05:49:00.990069+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.03922","created_at":"2026-07-05T05:49:00.990069+00:00"},{"alias_kind":"pith_short_12","alias_value":"B37BMMHN6AGC","created_at":"2026-07-05T05:49:00.990069+00:00"},{"alias_kind":"pith_short_16","alias_value":"B37BMMHN6AGCOM4X","created_at":"2026-07-05T05:49:00.990069+00:00"},{"alias_kind":"pith_short_8","alias_value":"B37BMMHN","created_at":"2026-07-05T05:49:00.990069+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/B37BMMHN6AGCOM4XTPPXEORJ4L","json":"https://pith.science/pith/B37BMMHN6AGCOM4XTPPXEORJ4L.json","graph_json":"https://pith.science/api/pith-number/B37BMMHN6AGCOM4XTPPXEORJ4L/graph.json","events_json":"https://pith.science/api/pith-number/B37BMMHN6AGCOM4XTPPXEORJ4L/events.json","paper":"https://pith.science/paper/B37BMMHN"},"agent_actions":{"view_html":"https://pith.science/pith/B37BMMHN6AGCOM4XTPPXEORJ4L","download_json":"https://pith.science/pith/B37BMMHN6AGCOM4XTPPXEORJ4L.json","view_paper":"https://pith.science/paper/B37BMMHN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.03922&json=true","fetch_graph":"https://pith.science/api/pith-number/B37BMMHN6AGCOM4XTPPXEORJ4L/graph.json","fetch_events":"https://pith.science/api/pith-number/B37BMMHN6AGCOM4XTPPXEORJ4L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B37BMMHN6AGCOM4XTPPXEORJ4L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B37BMMHN6AGCOM4XTPPXEORJ4L/action/storage_attestation","attest_author":"https://pith.science/pith/B37BMMHN6AGCOM4XTPPXEORJ4L/action/author_attestation","sign_citation":"https://pith.science/pith/B37BMMHN6AGCOM4XTPPXEORJ4L/action/citation_signature","submit_replication":"https://pith.science/pith/B37BMMHN6AGCOM4XTPPXEORJ4L/action/replication_record"}},"created_at":"2026-07-05T05:49:00.990069+00:00","updated_at":"2026-07-05T05:49:00.990069+00:00"}