{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IM3WTXN7WJPFELH2JT4NEV2RTN","short_pith_number":"pith:IM3WTXN7","schema_version":"1.0","canonical_sha256":"433769ddbfb25e522cfa4cf8d257519b628cf3709c9b4535bd7e94d4e2dceb7c","source":{"kind":"arxiv","id":"2305.12209","version":1},"attestation_state":"computed","paper":{"title":"Self-Distillation with Meta Learning for Knowledge Graph Completion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengming Li, Junhao Liu, Min Yang, Yunshui Li","submitted_at":"2023-05-20T15:12:25Z","abstract_excerpt":"In this paper, we propose a selfdistillation framework with meta learning(MetaSD) for knowledge graph completion with dynamic pruning, which aims to learn compressed graph embeddings and tackle the longtail samples. Specifically, we first propose a dynamic pruning technique to obtain a small pruned model from a large source model, where the pruning mask of the pruned model could be updated adaptively per epoch after the model weights are updated. The pruned model is supposed to be more sensitive to difficult to memorize samples(e.g., longtail samples) than the source model. Then, we propose a "},"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":"2305.12209","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-20T15:12:25Z","cross_cats_sorted":[],"title_canon_sha256":"82a03162fdf9d4ff7ca0ff501137f20f5212adcb54474fb06c25604f997f8fa6","abstract_canon_sha256":"e89faac86192ebec262092d43618bf0c5c423c2229142ea5f3fe130f9e80a1aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:07.784431Z","signature_b64":"kW/WaqYU8rMlQEHVDmOYXfuj8I3gDuytwJ2o0Y2TAWSHWN2UR/eU7n+lz6+0vEHHURIGEe9zUoI92FRznahrDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"433769ddbfb25e522cfa4cf8d257519b628cf3709c9b4535bd7e94d4e2dceb7c","last_reissued_at":"2026-07-05T06:12:07.783960Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:07.783960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Distillation with Meta Learning for Knowledge Graph Completion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengming Li, Junhao Liu, Min Yang, Yunshui Li","submitted_at":"2023-05-20T15:12:25Z","abstract_excerpt":"In this paper, we propose a selfdistillation framework with meta learning(MetaSD) for knowledge graph completion with dynamic pruning, which aims to learn compressed graph embeddings and tackle the longtail samples. Specifically, we first propose a dynamic pruning technique to obtain a small pruned model from a large source model, where the pruning mask of the pruned model could be updated adaptively per epoch after the model weights are updated. The pruned model is supposed to be more sensitive to difficult to memorize samples(e.g., longtail samples) than the source model. Then, we propose a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12209","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/2305.12209/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":"2305.12209","created_at":"2026-07-05T06:12:07.784016+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.12209v1","created_at":"2026-07-05T06:12:07.784016+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12209","created_at":"2026-07-05T06:12:07.784016+00:00"},{"alias_kind":"pith_short_12","alias_value":"IM3WTXN7WJPF","created_at":"2026-07-05T06:12:07.784016+00:00"},{"alias_kind":"pith_short_16","alias_value":"IM3WTXN7WJPFELH2","created_at":"2026-07-05T06:12:07.784016+00:00"},{"alias_kind":"pith_short_8","alias_value":"IM3WTXN7","created_at":"2026-07-05T06:12:07.784016+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/IM3WTXN7WJPFELH2JT4NEV2RTN","json":"https://pith.science/pith/IM3WTXN7WJPFELH2JT4NEV2RTN.json","graph_json":"https://pith.science/api/pith-number/IM3WTXN7WJPFELH2JT4NEV2RTN/graph.json","events_json":"https://pith.science/api/pith-number/IM3WTXN7WJPFELH2JT4NEV2RTN/events.json","paper":"https://pith.science/paper/IM3WTXN7"},"agent_actions":{"view_html":"https://pith.science/pith/IM3WTXN7WJPFELH2JT4NEV2RTN","download_json":"https://pith.science/pith/IM3WTXN7WJPFELH2JT4NEV2RTN.json","view_paper":"https://pith.science/paper/IM3WTXN7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.12209&json=true","fetch_graph":"https://pith.science/api/pith-number/IM3WTXN7WJPFELH2JT4NEV2RTN/graph.json","fetch_events":"https://pith.science/api/pith-number/IM3WTXN7WJPFELH2JT4NEV2RTN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IM3WTXN7WJPFELH2JT4NEV2RTN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IM3WTXN7WJPFELH2JT4NEV2RTN/action/storage_attestation","attest_author":"https://pith.science/pith/IM3WTXN7WJPFELH2JT4NEV2RTN/action/author_attestation","sign_citation":"https://pith.science/pith/IM3WTXN7WJPFELH2JT4NEV2RTN/action/citation_signature","submit_replication":"https://pith.science/pith/IM3WTXN7WJPFELH2JT4NEV2RTN/action/replication_record"}},"created_at":"2026-07-05T06:12:07.784016+00:00","updated_at":"2026-07-05T06:12:07.784016+00:00"}