{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EZVFTG5EWE7JYNM4GVZP22ZYSD","short_pith_number":"pith:EZVFTG5E","schema_version":"1.0","canonical_sha256":"266a599ba4b13e9c359c3572fd6b3890e6afc4d49cf97497424333238f55ba8d","source":{"kind":"arxiv","id":"2310.11670","version":3},"attestation_state":"computed","paper":{"title":"Prototype-based HyperAdapter for Sample-Efficient Multi-task Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hao Zhao, Jie Fu, Zhaofeng He","submitted_at":"2023-10-18T02:42:17Z","abstract_excerpt":"Parameter-efficient fine-tuning (PEFT) has shown its effectiveness in adapting the pre-trained language models to downstream tasks while only updating a small number of parameters. Despite the success, most existing methods independently adapt to each task without considering knowledge transfer between tasks and are limited to low-data regimes. To overcome this issue, we propose Prototype-based HyperAdapter (PHA), a novel framework built on the adapter-tuning and hypernetwork. It introduces an instance-dense retriever and a prototypical hypernetwork to generate the conditional modules in a sam"},"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":"2310.11670","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-18T02:42:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a41b5931e987ef1bd024fbcebd149c4dac6fb646de202fce92a316d8c1fd8085","abstract_canon_sha256":"c3c36463d5b87878334ef48029b038b0c44e7a5f58313c50ca99b28a64096d39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:36.924964Z","signature_b64":"OTHFH0MXER43u6I2qxENM44kgPEUQGIh7htio3k0Z9OJ6C08EDu5Us5eU0q30tbfic2WAw2pafnFsR/LI6nSCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"266a599ba4b13e9c359c3572fd6b3890e6afc4d49cf97497424333238f55ba8d","last_reissued_at":"2026-07-05T07:11:36.924486Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:36.924486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prototype-based HyperAdapter for Sample-Efficient Multi-task Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hao Zhao, Jie Fu, Zhaofeng He","submitted_at":"2023-10-18T02:42:17Z","abstract_excerpt":"Parameter-efficient fine-tuning (PEFT) has shown its effectiveness in adapting the pre-trained language models to downstream tasks while only updating a small number of parameters. Despite the success, most existing methods independently adapt to each task without considering knowledge transfer between tasks and are limited to low-data regimes. To overcome this issue, we propose Prototype-based HyperAdapter (PHA), a novel framework built on the adapter-tuning and hypernetwork. It introduces an instance-dense retriever and a prototypical hypernetwork to generate the conditional modules in a sam"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11670","kind":"arxiv","version":3},"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/2310.11670/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":"2310.11670","created_at":"2026-07-05T07:11:36.924549+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.11670v3","created_at":"2026-07-05T07:11:36.924549+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11670","created_at":"2026-07-05T07:11:36.924549+00:00"},{"alias_kind":"pith_short_12","alias_value":"EZVFTG5EWE7J","created_at":"2026-07-05T07:11:36.924549+00:00"},{"alias_kind":"pith_short_16","alias_value":"EZVFTG5EWE7JYNM4","created_at":"2026-07-05T07:11:36.924549+00:00"},{"alias_kind":"pith_short_8","alias_value":"EZVFTG5E","created_at":"2026-07-05T07:11:36.924549+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01671","citing_title":"When Meaning Travels: A Granular Lens on Hybrid-MoE's Role in Idiomatic Understanding for Language Models","ref_index":117,"is_internal_anchor":false},{"citing_arxiv_id":"2602.01051","citing_title":"SwiftRepertoire: Few-Shot Immune-Signature Synthesis via Dynamic Kernel Codes","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2403.14608","citing_title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EZVFTG5EWE7JYNM4GVZP22ZYSD","json":"https://pith.science/pith/EZVFTG5EWE7JYNM4GVZP22ZYSD.json","graph_json":"https://pith.science/api/pith-number/EZVFTG5EWE7JYNM4GVZP22ZYSD/graph.json","events_json":"https://pith.science/api/pith-number/EZVFTG5EWE7JYNM4GVZP22ZYSD/events.json","paper":"https://pith.science/paper/EZVFTG5E"},"agent_actions":{"view_html":"https://pith.science/pith/EZVFTG5EWE7JYNM4GVZP22ZYSD","download_json":"https://pith.science/pith/EZVFTG5EWE7JYNM4GVZP22ZYSD.json","view_paper":"https://pith.science/paper/EZVFTG5E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.11670&json=true","fetch_graph":"https://pith.science/api/pith-number/EZVFTG5EWE7JYNM4GVZP22ZYSD/graph.json","fetch_events":"https://pith.science/api/pith-number/EZVFTG5EWE7JYNM4GVZP22ZYSD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EZVFTG5EWE7JYNM4GVZP22ZYSD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EZVFTG5EWE7JYNM4GVZP22ZYSD/action/storage_attestation","attest_author":"https://pith.science/pith/EZVFTG5EWE7JYNM4GVZP22ZYSD/action/author_attestation","sign_citation":"https://pith.science/pith/EZVFTG5EWE7JYNM4GVZP22ZYSD/action/citation_signature","submit_replication":"https://pith.science/pith/EZVFTG5EWE7JYNM4GVZP22ZYSD/action/replication_record"}},"created_at":"2026-07-05T07:11:36.924549+00:00","updated_at":"2026-07-05T07:11:36.924549+00:00"}