{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:42UIUVB7XD5QRKD4X6CVAYCZHV","short_pith_number":"pith:42UIUVB7","schema_version":"1.0","canonical_sha256":"e6a88a543fb8fb08a87cbf855060593d794ed1cf3994d81d7a16751221d50b4c","source":{"kind":"arxiv","id":"2301.01821","version":1},"attestation_state":"computed","paper":{"title":"Parameter-Efficient Fine-Tuning Design Spaces","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alex Smola, Aston Zhang, Diyi Yang, Jiaao Chen, Mu Li, Xingjian Shi","submitted_at":"2023-01-04T21:00:18Z","abstract_excerpt":"Parameter-efficient fine-tuning aims to achieve performance comparable to fine-tuning, using fewer trainable parameters. Several strategies (e.g., Adapters, prefix tuning, BitFit, and LoRA) have been proposed. However, their designs are hand-crafted separately, and it remains unclear whether certain design patterns exist for parameter-efficient fine-tuning. Thus, we present a parameter-efficient fine-tuning design paradigm and discover design patterns that are applicable to different experimental settings. Instead of focusing on designing another individual tuning strategy, we introduce parame"},"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":"2301.01821","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-04T21:00:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"48b864ce8b8dd44dbf58fcecbe43d295fe2898f13af91196cda39596530b1936","abstract_canon_sha256":"b875f62149c6da29736e1a3e42478407e816b78f47081bc3a81b6d8d078048db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:30:46.247405Z","signature_b64":"7P2NHsw6sXH5EPUaFynDf/aQ7IKFiJZP3CzjUokpVtg576fyEECsGshH+xqX2GpZrOwUfD/gbd29FOCBMqhwCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6a88a543fb8fb08a87cbf855060593d794ed1cf3994d81d7a16751221d50b4c","last_reissued_at":"2026-07-05T05:30:46.246870Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:30:46.246870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parameter-Efficient Fine-Tuning Design Spaces","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alex Smola, Aston Zhang, Diyi Yang, Jiaao Chen, Mu Li, Xingjian Shi","submitted_at":"2023-01-04T21:00:18Z","abstract_excerpt":"Parameter-efficient fine-tuning aims to achieve performance comparable to fine-tuning, using fewer trainable parameters. Several strategies (e.g., Adapters, prefix tuning, BitFit, and LoRA) have been proposed. However, their designs are hand-crafted separately, and it remains unclear whether certain design patterns exist for parameter-efficient fine-tuning. Thus, we present a parameter-efficient fine-tuning design paradigm and discover design patterns that are applicable to different experimental settings. Instead of focusing on designing another individual tuning strategy, we introduce parame"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.01821","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/2301.01821/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":"2301.01821","created_at":"2026-07-05T05:30:46.246934+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.01821v1","created_at":"2026-07-05T05:30:46.246934+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.01821","created_at":"2026-07-05T05:30:46.246934+00:00"},{"alias_kind":"pith_short_12","alias_value":"42UIUVB7XD5Q","created_at":"2026-07-05T05:30:46.246934+00:00"},{"alias_kind":"pith_short_16","alias_value":"42UIUVB7XD5QRKD4","created_at":"2026-07-05T05:30:46.246934+00:00"},{"alias_kind":"pith_short_8","alias_value":"42UIUVB7","created_at":"2026-07-05T05:30:46.246934+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2501.05465","citing_title":"Small Language Models (SLMs) Can Still Pack a Punch: A survey (updated 2026)","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2403.14608","citing_title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","ref_index":98,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/42UIUVB7XD5QRKD4X6CVAYCZHV","json":"https://pith.science/pith/42UIUVB7XD5QRKD4X6CVAYCZHV.json","graph_json":"https://pith.science/api/pith-number/42UIUVB7XD5QRKD4X6CVAYCZHV/graph.json","events_json":"https://pith.science/api/pith-number/42UIUVB7XD5QRKD4X6CVAYCZHV/events.json","paper":"https://pith.science/paper/42UIUVB7"},"agent_actions":{"view_html":"https://pith.science/pith/42UIUVB7XD5QRKD4X6CVAYCZHV","download_json":"https://pith.science/pith/42UIUVB7XD5QRKD4X6CVAYCZHV.json","view_paper":"https://pith.science/paper/42UIUVB7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.01821&json=true","fetch_graph":"https://pith.science/api/pith-number/42UIUVB7XD5QRKD4X6CVAYCZHV/graph.json","fetch_events":"https://pith.science/api/pith-number/42UIUVB7XD5QRKD4X6CVAYCZHV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/42UIUVB7XD5QRKD4X6CVAYCZHV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/42UIUVB7XD5QRKD4X6CVAYCZHV/action/storage_attestation","attest_author":"https://pith.science/pith/42UIUVB7XD5QRKD4X6CVAYCZHV/action/author_attestation","sign_citation":"https://pith.science/pith/42UIUVB7XD5QRKD4X6CVAYCZHV/action/citation_signature","submit_replication":"https://pith.science/pith/42UIUVB7XD5QRKD4X6CVAYCZHV/action/replication_record"}},"created_at":"2026-07-05T05:30:46.246934+00:00","updated_at":"2026-07-05T05:30:46.246934+00:00"}