{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MXIXUY25X77ZCVCRPST2VUESRH","short_pith_number":"pith:MXIXUY25","schema_version":"1.0","canonical_sha256":"65d17a635dbfff9154517ca7aad09289f9e42a2133136c417aea54517376be41","source":{"kind":"arxiv","id":"2605.28819","version":1},"attestation_state":"computed","paper":{"title":"PEFT-Arena: Understanding Parameter-Efficient Finetuning from a Stability-Plasticity Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Bernhard Sch\\\"olkopf, Jiale Kang, Ruotian Peng, Weiyang Liu, Yandong Wen, Yangyi Huang, Zeju Qiu","submitted_at":"2026-05-27T17:59:51Z","abstract_excerpt":"Parameter-efficient finetuning (PEFT) has become the standard approach for adapting large language models, yet evaluations largely emphasize downstream accuracy while overlooking the retention of pretrained capabilities. We argue that PEFT should be assessed through the stability-plasticity dilemma: the trade-off between target-task adaptation and resistance to forgetting. We introduce PEFT-Arena, a benchmark that jointly measures downstream performance and general capability retention. Across methods, we find distinct stability-plasticity profiles; under comparable parameter budgets, orthogon"},"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":"2605.28819","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T17:59:51Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"5f13d893b3115ab4395503b9e203d529e29b8f5543d54c9d41b53e97cf7fee33","abstract_canon_sha256":"f898429bd3755b13516af218dd55cbf5188483b1d6ee5126d5571d714a115e09"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T02:05:04.643499Z","signature_b64":"GOvUNODlGY9oce6WWt2YlJZXQJr3Id477DGJ5gPdhjg2q46QaRduhk/j34ywEhu7faQ10J41N5nTen/atADRDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65d17a635dbfff9154517ca7aad09289f9e42a2133136c417aea54517376be41","last_reissued_at":"2026-05-28T02:05:04.643065Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T02:05:04.643065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PEFT-Arena: Understanding Parameter-Efficient Finetuning from a Stability-Plasticity Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Bernhard Sch\\\"olkopf, Jiale Kang, Ruotian Peng, Weiyang Liu, Yandong Wen, Yangyi Huang, Zeju Qiu","submitted_at":"2026-05-27T17:59:51Z","abstract_excerpt":"Parameter-efficient finetuning (PEFT) has become the standard approach for adapting large language models, yet evaluations largely emphasize downstream accuracy while overlooking the retention of pretrained capabilities. We argue that PEFT should be assessed through the stability-plasticity dilemma: the trade-off between target-task adaptation and resistance to forgetting. We introduce PEFT-Arena, a benchmark that jointly measures downstream performance and general capability retention. Across methods, we find distinct stability-plasticity profiles; under comparable parameter budgets, orthogon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28819","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/2605.28819/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":"2605.28819","created_at":"2026-05-28T02:05:04.643131+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28819v1","created_at":"2026-05-28T02:05:04.643131+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28819","created_at":"2026-05-28T02:05:04.643131+00:00"},{"alias_kind":"pith_short_12","alias_value":"MXIXUY25X77Z","created_at":"2026-05-28T02:05:04.643131+00:00"},{"alias_kind":"pith_short_16","alias_value":"MXIXUY25X77ZCVCR","created_at":"2026-05-28T02:05:04.643131+00:00"},{"alias_kind":"pith_short_8","alias_value":"MXIXUY25","created_at":"2026-05-28T02:05:04.643131+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/MXIXUY25X77ZCVCRPST2VUESRH","json":"https://pith.science/pith/MXIXUY25X77ZCVCRPST2VUESRH.json","graph_json":"https://pith.science/api/pith-number/MXIXUY25X77ZCVCRPST2VUESRH/graph.json","events_json":"https://pith.science/api/pith-number/MXIXUY25X77ZCVCRPST2VUESRH/events.json","paper":"https://pith.science/paper/MXIXUY25"},"agent_actions":{"view_html":"https://pith.science/pith/MXIXUY25X77ZCVCRPST2VUESRH","download_json":"https://pith.science/pith/MXIXUY25X77ZCVCRPST2VUESRH.json","view_paper":"https://pith.science/paper/MXIXUY25","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28819&json=true","fetch_graph":"https://pith.science/api/pith-number/MXIXUY25X77ZCVCRPST2VUESRH/graph.json","fetch_events":"https://pith.science/api/pith-number/MXIXUY25X77ZCVCRPST2VUESRH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MXIXUY25X77ZCVCRPST2VUESRH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MXIXUY25X77ZCVCRPST2VUESRH/action/storage_attestation","attest_author":"https://pith.science/pith/MXIXUY25X77ZCVCRPST2VUESRH/action/author_attestation","sign_citation":"https://pith.science/pith/MXIXUY25X77ZCVCRPST2VUESRH/action/citation_signature","submit_replication":"https://pith.science/pith/MXIXUY25X77ZCVCRPST2VUESRH/action/replication_record"}},"created_at":"2026-05-28T02:05:04.643131+00:00","updated_at":"2026-05-28T02:05:04.643131+00:00"}