{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UFJHTHCTPU234AF7YFZIVIRTJA","short_pith_number":"pith:UFJHTHCT","schema_version":"1.0","canonical_sha256":"a152799c537d35be00bfc1728aa233480f2a3889cb287f1ea77d8127f802d88d","source":{"kind":"arxiv","id":"2503.03499","version":2},"attestation_state":"computed","paper":{"title":"State-offset Tuning: State-based Parameter-Efficient Fine-Tuning for State Space Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hyung Il Koo, Kevin Galim, Minjae Lee, Nam Ik Cho, Wonjun Kang, Yuchen Zeng","submitted_at":"2025-03-05T13:44:42Z","abstract_excerpt":"State Space Models (SSMs) have emerged as efficient alternatives to Transformers, mitigating their quadratic computational cost. However, the application of Parameter-Efficient Fine-Tuning (PEFT) methods to SSMs remains largely unexplored. In particular, prompt-based methods like Prompt Tuning and Prefix-Tuning, which are widely used in Transformers, do not perform well on SSMs. To address this, we propose state-based methods as a superior alternative to prompt-based methods. This new family of methods naturally stems from the architectural characteristics of SSMs. State-based methods adjust s"},"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":"2503.03499","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-05T13:44:42Z","cross_cats_sorted":[],"title_canon_sha256":"b1fbaaa7d0116a3395522a3c486ad969ab1e59776576599401530c322a912ec8","abstract_canon_sha256":"da151f2bd49210f94e077155b7d7df843fb8f9388b55b6b53cc66bca13f9e4aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:19.082168Z","signature_b64":"I9q52OGBzNH9UyHhBy3JOqNUckUYdYiEb8L0aQBFXg/b8kk6KbnlAJm/z4uIlfRs6yHurADjJwvqEXDSUHBeAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a152799c537d35be00bfc1728aa233480f2a3889cb287f1ea77d8127f802d88d","last_reissued_at":"2026-07-05T11:18:19.081701Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:19.081701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"State-offset Tuning: State-based Parameter-Efficient Fine-Tuning for State Space Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hyung Il Koo, Kevin Galim, Minjae Lee, Nam Ik Cho, Wonjun Kang, Yuchen Zeng","submitted_at":"2025-03-05T13:44:42Z","abstract_excerpt":"State Space Models (SSMs) have emerged as efficient alternatives to Transformers, mitigating their quadratic computational cost. However, the application of Parameter-Efficient Fine-Tuning (PEFT) methods to SSMs remains largely unexplored. In particular, prompt-based methods like Prompt Tuning and Prefix-Tuning, which are widely used in Transformers, do not perform well on SSMs. To address this, we propose state-based methods as a superior alternative to prompt-based methods. This new family of methods naturally stems from the architectural characteristics of SSMs. State-based methods adjust s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.03499","kind":"arxiv","version":2},"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/2503.03499/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":"2503.03499","created_at":"2026-07-05T11:18:19.081758+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.03499v2","created_at":"2026-07-05T11:18:19.081758+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.03499","created_at":"2026-07-05T11:18:19.081758+00:00"},{"alias_kind":"pith_short_12","alias_value":"UFJHTHCTPU23","created_at":"2026-07-05T11:18:19.081758+00:00"},{"alias_kind":"pith_short_16","alias_value":"UFJHTHCTPU234AF7","created_at":"2026-07-05T11:18:19.081758+00:00"},{"alias_kind":"pith_short_8","alias_value":"UFJHTHCT","created_at":"2026-07-05T11:18:19.081758+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.01168","citing_title":"S0 Tuning: Zero-Overhead Adaptation of Hybrid Recurrent-Attention Models","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UFJHTHCTPU234AF7YFZIVIRTJA","json":"https://pith.science/pith/UFJHTHCTPU234AF7YFZIVIRTJA.json","graph_json":"https://pith.science/api/pith-number/UFJHTHCTPU234AF7YFZIVIRTJA/graph.json","events_json":"https://pith.science/api/pith-number/UFJHTHCTPU234AF7YFZIVIRTJA/events.json","paper":"https://pith.science/paper/UFJHTHCT"},"agent_actions":{"view_html":"https://pith.science/pith/UFJHTHCTPU234AF7YFZIVIRTJA","download_json":"https://pith.science/pith/UFJHTHCTPU234AF7YFZIVIRTJA.json","view_paper":"https://pith.science/paper/UFJHTHCT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.03499&json=true","fetch_graph":"https://pith.science/api/pith-number/UFJHTHCTPU234AF7YFZIVIRTJA/graph.json","fetch_events":"https://pith.science/api/pith-number/UFJHTHCTPU234AF7YFZIVIRTJA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UFJHTHCTPU234AF7YFZIVIRTJA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UFJHTHCTPU234AF7YFZIVIRTJA/action/storage_attestation","attest_author":"https://pith.science/pith/UFJHTHCTPU234AF7YFZIVIRTJA/action/author_attestation","sign_citation":"https://pith.science/pith/UFJHTHCTPU234AF7YFZIVIRTJA/action/citation_signature","submit_replication":"https://pith.science/pith/UFJHTHCTPU234AF7YFZIVIRTJA/action/replication_record"}},"created_at":"2026-07-05T11:18:19.081758+00:00","updated_at":"2026-07-05T11:18:19.081758+00:00"}