{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FIWA5DPG5WVIWFQPLGPEUGEXQC","short_pith_number":"pith:FIWA5DPG","schema_version":"1.0","canonical_sha256":"2a2c0e8de6edaa8b160f599e4a189780a7c657711b935a91b57a0397ef54ea82","source":{"kind":"arxiv","id":"2210.13715","version":1},"attestation_state":"computed","paper":{"title":"PALT: Parameter-Lite Transfer of Language Models for Knowledge Graph Completion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chenguang Wang, Dawn Song, Heng Ji, Jianhao Shen, Jiawei Han, Koushik Sen, Ming Zhang, Ye Yuan","submitted_at":"2022-10-25T02:22:29Z","abstract_excerpt":"This paper presents a parameter-lite transfer learning approach of pretrained language models (LM) for knowledge graph (KG) completion. Instead of finetuning, which modifies all LM parameters, we only tune a few new parameters while keeping the original LM parameters fixed. We establish this via reformulating KG completion as a \"fill-in-the-blank\" task, and introducing a parameter-lite encoder on top of the original LMs. We show that, by tuning far fewer parameters than finetuning, LMs transfer non-trivially to most tasks and reach competitiveness with prior state-of-the-art approaches. For in"},"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":"2210.13715","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-25T02:22:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5be0f8d5760c16e6804cf4f86d7ba27ef9b3bfc422a3087204d61c870c8e1048","abstract_canon_sha256":"a2d803fd22c1d520d55aec6cd1db013c00cdf1b90d1053dc8b1458c99a947861"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:10:21.440855Z","signature_b64":"7Pq/4vKHNZQ+jv4nU0nCTEslC4clm7xhO8UoxsmhjCNkJATOj6/uz09cMZzDvjx7UX1B4vYPKankqftGeBsAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a2c0e8de6edaa8b160f599e4a189780a7c657711b935a91b57a0397ef54ea82","last_reissued_at":"2026-07-05T05:10:21.440419Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:10:21.440419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PALT: Parameter-Lite Transfer of Language Models for Knowledge Graph Completion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chenguang Wang, Dawn Song, Heng Ji, Jianhao Shen, Jiawei Han, Koushik Sen, Ming Zhang, Ye Yuan","submitted_at":"2022-10-25T02:22:29Z","abstract_excerpt":"This paper presents a parameter-lite transfer learning approach of pretrained language models (LM) for knowledge graph (KG) completion. Instead of finetuning, which modifies all LM parameters, we only tune a few new parameters while keeping the original LM parameters fixed. We establish this via reformulating KG completion as a \"fill-in-the-blank\" task, and introducing a parameter-lite encoder on top of the original LMs. We show that, by tuning far fewer parameters than finetuning, LMs transfer non-trivially to most tasks and reach competitiveness with prior state-of-the-art approaches. For in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.13715","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/2210.13715/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":"2210.13715","created_at":"2026-07-05T05:10:21.440476+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.13715v1","created_at":"2026-07-05T05:10:21.440476+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.13715","created_at":"2026-07-05T05:10:21.440476+00:00"},{"alias_kind":"pith_short_12","alias_value":"FIWA5DPG5WVI","created_at":"2026-07-05T05:10:21.440476+00:00"},{"alias_kind":"pith_short_16","alias_value":"FIWA5DPG5WVIWFQP","created_at":"2026-07-05T05:10:21.440476+00:00"},{"alias_kind":"pith_short_8","alias_value":"FIWA5DPG","created_at":"2026-07-05T05:10:21.440476+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/FIWA5DPG5WVIWFQPLGPEUGEXQC","json":"https://pith.science/pith/FIWA5DPG5WVIWFQPLGPEUGEXQC.json","graph_json":"https://pith.science/api/pith-number/FIWA5DPG5WVIWFQPLGPEUGEXQC/graph.json","events_json":"https://pith.science/api/pith-number/FIWA5DPG5WVIWFQPLGPEUGEXQC/events.json","paper":"https://pith.science/paper/FIWA5DPG"},"agent_actions":{"view_html":"https://pith.science/pith/FIWA5DPG5WVIWFQPLGPEUGEXQC","download_json":"https://pith.science/pith/FIWA5DPG5WVIWFQPLGPEUGEXQC.json","view_paper":"https://pith.science/paper/FIWA5DPG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.13715&json=true","fetch_graph":"https://pith.science/api/pith-number/FIWA5DPG5WVIWFQPLGPEUGEXQC/graph.json","fetch_events":"https://pith.science/api/pith-number/FIWA5DPG5WVIWFQPLGPEUGEXQC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FIWA5DPG5WVIWFQPLGPEUGEXQC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FIWA5DPG5WVIWFQPLGPEUGEXQC/action/storage_attestation","attest_author":"https://pith.science/pith/FIWA5DPG5WVIWFQPLGPEUGEXQC/action/author_attestation","sign_citation":"https://pith.science/pith/FIWA5DPG5WVIWFQPLGPEUGEXQC/action/citation_signature","submit_replication":"https://pith.science/pith/FIWA5DPG5WVIWFQPLGPEUGEXQC/action/replication_record"}},"created_at":"2026-07-05T05:10:21.440476+00:00","updated_at":"2026-07-05T05:10:21.440476+00:00"}