{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VZLCVGYLEEX5QLJLCFPAH3O76Q","short_pith_number":"pith:VZLCVGYL","schema_version":"1.0","canonical_sha256":"ae562a9b0b212fd82d2b115e03eddff4101c18599ea7190526c3c9f9cdbc2b89","source":{"kind":"arxiv","id":"2106.03164","version":1},"attestation_state":"computed","paper":{"title":"On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bosheng Ding, Hai Ye, Jia-Wei Low, Lidong Bing, Linlin Liu, Liying Cheng, Luo Si, Qingyu Tan, Ruidan He","submitted_at":"2021-06-06T16:10:12Z","abstract_excerpt":"Adapter-based tuning has recently arisen as an alternative to fine-tuning. It works by adding light-weight adapter modules to a pretrained language model (PrLM) and only updating the parameters of adapter modules when learning on a downstream task. As such, it adds only a few trainable parameters per new task, allowing a high degree of parameter sharing. Prior studies have shown that adapter-based tuning often achieves comparable results to fine-tuning. However, existing work only focuses on the parameter-efficient aspect of adapter-based tuning while lacking further investigation on its effec"},"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":"2106.03164","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-06T16:10:12Z","cross_cats_sorted":[],"title_canon_sha256":"c7cffd5015b8bbbcbcdc2c4545cbb24299240f0b00c93319750c34386b8a8873","abstract_canon_sha256":"554ba9890d70152bd72fc766e1aea02b606c5ad62fa55fa14bac642ab37c44e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:46.994290Z","signature_b64":"uDilCZyBjzX2Zq07xkfVBjfq3byxlf0o5Cufe4qQZ7dwkt6x8+c1blEufA78Q/cCQqLA0tzxI9WMkI8WFOnZAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae562a9b0b212fd82d2b115e03eddff4101c18599ea7190526c3c9f9cdbc2b89","last_reissued_at":"2026-07-05T02:46:46.993907Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:46.993907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bosheng Ding, Hai Ye, Jia-Wei Low, Lidong Bing, Linlin Liu, Liying Cheng, Luo Si, Qingyu Tan, Ruidan He","submitted_at":"2021-06-06T16:10:12Z","abstract_excerpt":"Adapter-based tuning has recently arisen as an alternative to fine-tuning. It works by adding light-weight adapter modules to a pretrained language model (PrLM) and only updating the parameters of adapter modules when learning on a downstream task. As such, it adds only a few trainable parameters per new task, allowing a high degree of parameter sharing. Prior studies have shown that adapter-based tuning often achieves comparable results to fine-tuning. However, existing work only focuses on the parameter-efficient aspect of adapter-based tuning while lacking further investigation on its effec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03164","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/2106.03164/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":"2106.03164","created_at":"2026-07-05T02:46:46.993963+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.03164v1","created_at":"2026-07-05T02:46:46.993963+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03164","created_at":"2026-07-05T02:46:46.993963+00:00"},{"alias_kind":"pith_short_12","alias_value":"VZLCVGYLEEX5","created_at":"2026-07-05T02:46:46.993963+00:00"},{"alias_kind":"pith_short_16","alias_value":"VZLCVGYLEEX5QLJL","created_at":"2026-07-05T02:46:46.993963+00:00"},{"alias_kind":"pith_short_8","alias_value":"VZLCVGYL","created_at":"2026-07-05T02:46:46.993963+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.06819","citing_title":"Beyond End-to-End: Dynamic Chain Optimization for Private LLM Adaptation on the Edge","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VZLCVGYLEEX5QLJLCFPAH3O76Q","json":"https://pith.science/pith/VZLCVGYLEEX5QLJLCFPAH3O76Q.json","graph_json":"https://pith.science/api/pith-number/VZLCVGYLEEX5QLJLCFPAH3O76Q/graph.json","events_json":"https://pith.science/api/pith-number/VZLCVGYLEEX5QLJLCFPAH3O76Q/events.json","paper":"https://pith.science/paper/VZLCVGYL"},"agent_actions":{"view_html":"https://pith.science/pith/VZLCVGYLEEX5QLJLCFPAH3O76Q","download_json":"https://pith.science/pith/VZLCVGYLEEX5QLJLCFPAH3O76Q.json","view_paper":"https://pith.science/paper/VZLCVGYL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.03164&json=true","fetch_graph":"https://pith.science/api/pith-number/VZLCVGYLEEX5QLJLCFPAH3O76Q/graph.json","fetch_events":"https://pith.science/api/pith-number/VZLCVGYLEEX5QLJLCFPAH3O76Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VZLCVGYLEEX5QLJLCFPAH3O76Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VZLCVGYLEEX5QLJLCFPAH3O76Q/action/storage_attestation","attest_author":"https://pith.science/pith/VZLCVGYLEEX5QLJLCFPAH3O76Q/action/author_attestation","sign_citation":"https://pith.science/pith/VZLCVGYLEEX5QLJLCFPAH3O76Q/action/citation_signature","submit_replication":"https://pith.science/pith/VZLCVGYLEEX5QLJLCFPAH3O76Q/action/replication_record"}},"created_at":"2026-07-05T02:46:46.993963+00:00","updated_at":"2026-07-05T02:46:46.993963+00:00"}