{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ATVPAUXHNDBPZTPL47BJ24CVCM","short_pith_number":"pith:ATVPAUXH","canonical_record":{"source":{"id":"2306.02679","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-05T08:11:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"927dea7b4783905eb0cbc9391960d8f8e5be07675ecfa397842689b47a6b2fd9","abstract_canon_sha256":"b24a426999b6b8e4149ebaca4c098d7ecb0db1977be1a4608492a2c91f99a18d"},"schema_version":"1.0"},"canonical_sha256":"04eaf052e768c2fccdebe7c29d70551329202fb64419505d0aba35c6a5762b8c","source":{"kind":"arxiv","id":"2306.02679","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.02679","created_at":"2026-07-05T06:17:30Z"},{"alias_kind":"arxiv_version","alias_value":"2306.02679v1","created_at":"2026-07-05T06:17:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02679","created_at":"2026-07-05T06:17:30Z"},{"alias_kind":"pith_short_12","alias_value":"ATVPAUXHNDBP","created_at":"2026-07-05T06:17:30Z"},{"alias_kind":"pith_short_16","alias_value":"ATVPAUXHNDBPZTPL","created_at":"2026-07-05T06:17:30Z"},{"alias_kind":"pith_short_8","alias_value":"ATVPAUXH","created_at":"2026-07-05T06:17:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ATVPAUXHNDBPZTPL47BJ24CVCM","target":"record","payload":{"canonical_record":{"source":{"id":"2306.02679","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-05T08:11:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"927dea7b4783905eb0cbc9391960d8f8e5be07675ecfa397842689b47a6b2fd9","abstract_canon_sha256":"b24a426999b6b8e4149ebaca4c098d7ecb0db1977be1a4608492a2c91f99a18d"},"schema_version":"1.0"},"canonical_sha256":"04eaf052e768c2fccdebe7c29d70551329202fb64419505d0aba35c6a5762b8c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:30.057715Z","signature_b64":"pL2L+gBW2CS0AOUZC4fKy8dKVDltWt+qPm8YyKdsdedMH2aaC4gtWJNHqiTQUgJQXoyVExW+Jjy55IVvVBRHDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04eaf052e768c2fccdebe7c29d70551329202fb64419505d0aba35c6a5762b8c","last_reissued_at":"2026-07-05T06:17:30.057286Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:30.057286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.02679","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:17:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oSCC4Igp62MrkyccJHRhzIwTaYfFC3+hpJKjFNBbEtdotT/UuMWygR0mGBwIEaIttSDRjr/dvBpm0MMQojoyCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T16:43:27.425807Z"},"content_sha256":"148bb23cd9a9d68656bfddb81805bffe7797922df796916546ba1464afda1846","schema_version":"1.0","event_id":"sha256:148bb23cd9a9d68656bfddb81805bffe7797922df796916546ba1464afda1846"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ATVPAUXHNDBPZTPL47BJ24CVCM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Joint Pre-training and Local Re-training: Transferable Representation Learning on Multi-source Knowledge Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiacheng Huang, Jinghao Lin, Qijin Chen, Wei Hu, Xiaozhou Xu, Zequn Sun","submitted_at":"2023-06-05T08:11:59Z","abstract_excerpt":"In this paper, we present the ``joint pre-training and local re-training'' framework for learning and applying multi-source knowledge graph (KG) embeddings. We are motivated by the fact that different KGs contain complementary information to improve KG embeddings and downstream tasks. We pre-train a large teacher KG embedding model over linked multi-source KGs and distill knowledge to train a student model for a task-specific KG. To enable knowledge transfer across different KGs, we use entity alignment to build a linked subgraph for connecting the pre-trained KGs and the target KG. The linked"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02679","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/2306.02679/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":"2026-07-05T06:17:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mjcHAu0/uuY+9q68AJCTOmVnaaYVlGyj1Y8Mp04cnjcT5dNa8TZGdVIWN4bwn5mbg2iyXBd9RQ+xQAEcPWsWCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T16:43:27.426182Z"},"content_sha256":"1339e66552631541f60903fffdea19bc9a7e24ce7cef4ae06bb6049adec18fd3","schema_version":"1.0","event_id":"sha256:1339e66552631541f60903fffdea19bc9a7e24ce7cef4ae06bb6049adec18fd3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ATVPAUXHNDBPZTPL47BJ24CVCM/bundle.json","state_url":"https://pith.science/pith/ATVPAUXHNDBPZTPL47BJ24CVCM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ATVPAUXHNDBPZTPL47BJ24CVCM/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":"2026-07-10T16:43:27Z","links":{"resolver":"https://pith.science/pith/ATVPAUXHNDBPZTPL47BJ24CVCM","bundle":"https://pith.science/pith/ATVPAUXHNDBPZTPL47BJ24CVCM/bundle.json","state":"https://pith.science/pith/ATVPAUXHNDBPZTPL47BJ24CVCM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ATVPAUXHNDBPZTPL47BJ24CVCM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ATVPAUXHNDBPZTPL47BJ24CVCM","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":"b24a426999b6b8e4149ebaca4c098d7ecb0db1977be1a4608492a2c91f99a18d","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-05T08:11:59Z","title_canon_sha256":"927dea7b4783905eb0cbc9391960d8f8e5be07675ecfa397842689b47a6b2fd9"},"schema_version":"1.0","source":{"id":"2306.02679","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.02679","created_at":"2026-07-05T06:17:30Z"},{"alias_kind":"arxiv_version","alias_value":"2306.02679v1","created_at":"2026-07-05T06:17:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02679","created_at":"2026-07-05T06:17:30Z"},{"alias_kind":"pith_short_12","alias_value":"ATVPAUXHNDBP","created_at":"2026-07-05T06:17:30Z"},{"alias_kind":"pith_short_16","alias_value":"ATVPAUXHNDBPZTPL","created_at":"2026-07-05T06:17:30Z"},{"alias_kind":"pith_short_8","alias_value":"ATVPAUXH","created_at":"2026-07-05T06:17:30Z"}],"graph_snapshots":[{"event_id":"sha256:1339e66552631541f60903fffdea19bc9a7e24ce7cef4ae06bb6049adec18fd3","target":"graph","created_at":"2026-07-05T06:17:30Z","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/2306.02679/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present the ``joint pre-training and local re-training'' framework for learning and applying multi-source knowledge graph (KG) embeddings. We are motivated by the fact that different KGs contain complementary information to improve KG embeddings and downstream tasks. We pre-train a large teacher KG embedding model over linked multi-source KGs and distill knowledge to train a student model for a task-specific KG. To enable knowledge transfer across different KGs, we use entity alignment to build a linked subgraph for connecting the pre-trained KGs and the target KG. The linked","authors_text":"Jiacheng Huang, Jinghao Lin, Qijin Chen, Wei Hu, Xiaozhou Xu, Zequn Sun","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-05T08:11:59Z","title":"Joint Pre-training and Local Re-training: Transferable Representation Learning on Multi-source Knowledge Graphs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02679","kind":"arxiv","version":1},"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":"sha256:148bb23cd9a9d68656bfddb81805bffe7797922df796916546ba1464afda1846","target":"record","created_at":"2026-07-05T06:17:30Z","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":"b24a426999b6b8e4149ebaca4c098d7ecb0db1977be1a4608492a2c91f99a18d","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-05T08:11:59Z","title_canon_sha256":"927dea7b4783905eb0cbc9391960d8f8e5be07675ecfa397842689b47a6b2fd9"},"schema_version":"1.0","source":{"id":"2306.02679","kind":"arxiv","version":1}},"canonical_sha256":"04eaf052e768c2fccdebe7c29d70551329202fb64419505d0aba35c6a5762b8c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04eaf052e768c2fccdebe7c29d70551329202fb64419505d0aba35c6a5762b8c","first_computed_at":"2026-07-05T06:17:30.057286Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:17:30.057286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pL2L+gBW2CS0AOUZC4fKy8dKVDltWt+qPm8YyKdsdedMH2aaC4gtWJNHqiTQUgJQXoyVExW+Jjy55IVvVBRHDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:17:30.057715Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.02679","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:148bb23cd9a9d68656bfddb81805bffe7797922df796916546ba1464afda1846","sha256:1339e66552631541f60903fffdea19bc9a7e24ce7cef4ae06bb6049adec18fd3"],"state_sha256":"4ceeef533fb1ebb4e74765a7c845788edaff775b9bfcc89854143dcdc4ea9098"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xD74cyULRxPqo6PdZ8DU5+K7emcUrOZSFw6MU9poLgr/jAkRb1ZMgFSFvBPQ0QOo8m4MmNAsNoDQLhWoo6qMCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T16:43:27.428293Z","bundle_sha256":"1e0cda1f59e9c4bfa02e4c19b9dd27c08f1a9fd83f56b6581dc33faaab841f85"}}