{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:UF3XRKWVZ35HVP3UTKKON2RLD6","short_pith_number":"pith:UF3XRKWV","canonical_record":{"source":{"id":"2312.01837","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-04T12:20:25Z","cross_cats_sorted":[],"title_canon_sha256":"da340ea98b81f3147861627905177dd431e239a9a4e98b015c98a9b6c4b7758d","abstract_canon_sha256":"043a485c10b99476082809fa486e98eba13c5aabf59c5037ceb40ec3380d3564"},"schema_version":"1.0"},"canonical_sha256":"a17778aad5cefa7abf749a94e6ea2b1f8ca7aefee3935f8abfe077d909a1de05","source":{"kind":"arxiv","id":"2312.01837","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.01837","created_at":"2026-07-05T09:56:34Z"},{"alias_kind":"arxiv_version","alias_value":"2312.01837v2","created_at":"2026-07-05T09:56:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.01837","created_at":"2026-07-05T09:56:34Z"},{"alias_kind":"pith_short_12","alias_value":"UF3XRKWVZ35H","created_at":"2026-07-05T09:56:34Z"},{"alias_kind":"pith_short_16","alias_value":"UF3XRKWVZ35HVP3U","created_at":"2026-07-05T09:56:34Z"},{"alias_kind":"pith_short_8","alias_value":"UF3XRKWV","created_at":"2026-07-05T09:56:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:UF3XRKWVZ35HVP3UTKKON2RLD6","target":"record","payload":{"canonical_record":{"source":{"id":"2312.01837","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-04T12:20:25Z","cross_cats_sorted":[],"title_canon_sha256":"da340ea98b81f3147861627905177dd431e239a9a4e98b015c98a9b6c4b7758d","abstract_canon_sha256":"043a485c10b99476082809fa486e98eba13c5aabf59c5037ceb40ec3380d3564"},"schema_version":"1.0"},"canonical_sha256":"a17778aad5cefa7abf749a94e6ea2b1f8ca7aefee3935f8abfe077d909a1de05","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:34.649572Z","signature_b64":"fdnquy1WVg0XaLq1x3EUMKMJRwJYgQP1x5KvTH3aPeOfPnxD4zQKLRxN1ih92Uiy7sTDtQBICs9pdsknBOIMCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a17778aad5cefa7abf749a94e6ea2b1f8ca7aefee3935f8abfe077d909a1de05","last_reissued_at":"2026-07-05T09:56:34.649109Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:34.649109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.01837","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:56:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"olI6Z6CCNz0DyYVkwIUCtWKhWbaH6w59VDPtR1FK3afoE8utSXoEeBC0M987ans1zoPqq2N5SJR23a/dZ7uXBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:45:34.746659Z"},"content_sha256":"cf20f2ac8bf21a34bae8a6a168e0efc34056b113544dcb9ca69858fe440ab1ad","schema_version":"1.0","event_id":"sha256:cf20f2ac8bf21a34bae8a6a168e0efc34056b113544dcb9ca69858fe440ab1ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:UF3XRKWVZ35HVP3UTKKON2RLD6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Prompting Disentangled Embeddings for Knowledge Graph Completion with Pre-trained Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jeff Z. Pan, Jiaoyan Chen, Wen Zhang, Xiaoliang Xu, Yuhang Zeng, Yuxia Geng, Yuxiang Wang, Zhuo Chen","submitted_at":"2023-12-04T12:20:25Z","abstract_excerpt":"Both graph structures and textual information play a critical role in Knowledge Graph Completion (KGC). With the success of Pre-trained Language Models (PLMs) such as BERT, they have been applied for text encoding for KGC. However, the current methods mostly prefer to fine-tune PLMs, leading to huge training costs and limited scalability to larger PLMs. In contrast, we propose to utilize prompts and perform KGC on a frozen PLM with only the prompts trained. Accordingly, we propose a new KGC method named PDKGC with two prompts -- a hard task prompt which is to adapt the KGC task to the PLM pre-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.01837","kind":"arxiv","version":2},"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/2312.01837/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:56:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NQuIEQ5odkbQ3xCHcu7MMs+2KyjXpY68yeQuhAa/POJINNJnxK5XfDo/jSGJdj5jNS1L5RlFsakkPAPujbyXAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:45:34.747227Z"},"content_sha256":"76980c32f9fa676925de344a28ad9e9d03870dd5f3fb0aeccf263068f23a1d05","schema_version":"1.0","event_id":"sha256:76980c32f9fa676925de344a28ad9e9d03870dd5f3fb0aeccf263068f23a1d05"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UF3XRKWVZ35HVP3UTKKON2RLD6/bundle.json","state_url":"https://pith.science/pith/UF3XRKWVZ35HVP3UTKKON2RLD6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UF3XRKWVZ35HVP3UTKKON2RLD6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T02:45:34Z","links":{"resolver":"https://pith.science/pith/UF3XRKWVZ35HVP3UTKKON2RLD6","bundle":"https://pith.science/pith/UF3XRKWVZ35HVP3UTKKON2RLD6/bundle.json","state":"https://pith.science/pith/UF3XRKWVZ35HVP3UTKKON2RLD6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UF3XRKWVZ35HVP3UTKKON2RLD6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UF3XRKWVZ35HVP3UTKKON2RLD6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"043a485c10b99476082809fa486e98eba13c5aabf59c5037ceb40ec3380d3564","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-04T12:20:25Z","title_canon_sha256":"da340ea98b81f3147861627905177dd431e239a9a4e98b015c98a9b6c4b7758d"},"schema_version":"1.0","source":{"id":"2312.01837","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.01837","created_at":"2026-07-05T09:56:34Z"},{"alias_kind":"arxiv_version","alias_value":"2312.01837v2","created_at":"2026-07-05T09:56:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.01837","created_at":"2026-07-05T09:56:34Z"},{"alias_kind":"pith_short_12","alias_value":"UF3XRKWVZ35H","created_at":"2026-07-05T09:56:34Z"},{"alias_kind":"pith_short_16","alias_value":"UF3XRKWVZ35HVP3U","created_at":"2026-07-05T09:56:34Z"},{"alias_kind":"pith_short_8","alias_value":"UF3XRKWV","created_at":"2026-07-05T09:56:34Z"}],"graph_snapshots":[{"event_id":"sha256:76980c32f9fa676925de344a28ad9e9d03870dd5f3fb0aeccf263068f23a1d05","target":"graph","created_at":"2026-07-05T09:56:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2312.01837/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Both graph structures and textual information play a critical role in Knowledge Graph Completion (KGC). With the success of Pre-trained Language Models (PLMs) such as BERT, they have been applied for text encoding for KGC. However, the current methods mostly prefer to fine-tune PLMs, leading to huge training costs and limited scalability to larger PLMs. In contrast, we propose to utilize prompts and perform KGC on a frozen PLM with only the prompts trained. Accordingly, we propose a new KGC method named PDKGC with two prompts -- a hard task prompt which is to adapt the KGC task to the PLM pre-","authors_text":"Jeff Z. Pan, Jiaoyan Chen, Wen Zhang, Xiaoliang Xu, Yuhang Zeng, Yuxia Geng, Yuxiang Wang, Zhuo Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-04T12:20:25Z","title":"Prompting Disentangled Embeddings for Knowledge Graph Completion with Pre-trained Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.01837","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cf20f2ac8bf21a34bae8a6a168e0efc34056b113544dcb9ca69858fe440ab1ad","target":"record","created_at":"2026-07-05T09:56:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"043a485c10b99476082809fa486e98eba13c5aabf59c5037ceb40ec3380d3564","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-04T12:20:25Z","title_canon_sha256":"da340ea98b81f3147861627905177dd431e239a9a4e98b015c98a9b6c4b7758d"},"schema_version":"1.0","source":{"id":"2312.01837","kind":"arxiv","version":2}},"canonical_sha256":"a17778aad5cefa7abf749a94e6ea2b1f8ca7aefee3935f8abfe077d909a1de05","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a17778aad5cefa7abf749a94e6ea2b1f8ca7aefee3935f8abfe077d909a1de05","first_computed_at":"2026-07-05T09:56:34.649109Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:56:34.649109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fdnquy1WVg0XaLq1x3EUMKMJRwJYgQP1x5KvTH3aPeOfPnxD4zQKLRxN1ih92Uiy7sTDtQBICs9pdsknBOIMCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:56:34.649572Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.01837","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf20f2ac8bf21a34bae8a6a168e0efc34056b113544dcb9ca69858fe440ab1ad","sha256:76980c32f9fa676925de344a28ad9e9d03870dd5f3fb0aeccf263068f23a1d05"],"state_sha256":"059fa4f19f2b81de12fa3847b26aef804bc224930c1ade59912d495758da0bfe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hLE0EZ87DkzWKbOSttQchPewvwvAwhEtERO/8reRS7k46wqLriVy/R/l85omG5i1J74FB67qZRR2P2cQ/ixODg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T02:45:34.752587Z","bundle_sha256":"febfdaaf47e461d2a93eac0b741e4c9daa202bdbc25c7e56417afbdf3f403189"}}