{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z6IS6F65XHH2DQA5N4IOZF4RK6","short_pith_number":"pith:Z6IS6F65","schema_version":"1.0","canonical_sha256":"cf912f17ddb9cfa1c01d6f10ec97915791a2b3c9b2f2a1be115b08042af6c8d0","source":{"kind":"arxiv","id":"2411.03855","version":3},"attestation_state":"computed","paper":{"title":"MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for Mamba","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Masakazu Yoshimura, Teruaki Hayashi, Yota Maeda","submitted_at":"2024-11-06T11:57:55Z","abstract_excerpt":"An ecosystem of Transformer-based models has been established by building large models with extensive data. Parameter-efficient fine-tuning (PEFT) is a crucial technology for deploying these models to downstream tasks with minimal cost while achieving effective performance. Recently, Mamba, a State Space Model (SSM)-based model, has attracted attention as a potential alternative to Transformers. While many large-scale Mamba-based models have been proposed, efficiently adapting pre-trained Mamba-based models to downstream tasks remains unexplored. In this paper, we conduct an exploratory analys"},"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":"2411.03855","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-06T11:57:55Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"bab6cb8d71a66df331727e9313f4bb30763fe57f46cf578c3eadebed5693c0a0","abstract_canon_sha256":"9cd50f323ea3d33afd3bb69149969b3c03490b0f5af2bb9499a9e896e51afd02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:38.952809Z","signature_b64":"r7Mn6itlZmCS5XD4y9x4vw+Q3Zz/TFbyz740RGGlSVtdUZKXxLrbz92pxmC6N4vNzEysbOUzEyirnhRTMwSTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf912f17ddb9cfa1c01d6f10ec97915791a2b3c9b2f2a1be115b08042af6c8d0","last_reissued_at":"2026-07-05T10:42:38.952340Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:38.952340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for Mamba","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Masakazu Yoshimura, Teruaki Hayashi, Yota Maeda","submitted_at":"2024-11-06T11:57:55Z","abstract_excerpt":"An ecosystem of Transformer-based models has been established by building large models with extensive data. Parameter-efficient fine-tuning (PEFT) is a crucial technology for deploying these models to downstream tasks with minimal cost while achieving effective performance. Recently, Mamba, a State Space Model (SSM)-based model, has attracted attention as a potential alternative to Transformers. While many large-scale Mamba-based models have been proposed, efficiently adapting pre-trained Mamba-based models to downstream tasks remains unexplored. In this paper, we conduct an exploratory analys"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.03855","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/2411.03855/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":"2411.03855","created_at":"2026-07-05T10:42:38.952395+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.03855v3","created_at":"2026-07-05T10:42:38.952395+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.03855","created_at":"2026-07-05T10:42:38.952395+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z6IS6F65XHH2","created_at":"2026-07-05T10:42:38.952395+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z6IS6F65XHH2DQA5","created_at":"2026-07-05T10:42:38.952395+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z6IS6F65","created_at":"2026-07-05T10:42:38.952395+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.01168","citing_title":"S0 Tuning: Zero-Overhead Adaptation of Hybrid Recurrent-Attention Models","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22127","citing_title":"Where Should LoRA Go? Component-Type Placement in Hybrid Language Models","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z6IS6F65XHH2DQA5N4IOZF4RK6","json":"https://pith.science/pith/Z6IS6F65XHH2DQA5N4IOZF4RK6.json","graph_json":"https://pith.science/api/pith-number/Z6IS6F65XHH2DQA5N4IOZF4RK6/graph.json","events_json":"https://pith.science/api/pith-number/Z6IS6F65XHH2DQA5N4IOZF4RK6/events.json","paper":"https://pith.science/paper/Z6IS6F65"},"agent_actions":{"view_html":"https://pith.science/pith/Z6IS6F65XHH2DQA5N4IOZF4RK6","download_json":"https://pith.science/pith/Z6IS6F65XHH2DQA5N4IOZF4RK6.json","view_paper":"https://pith.science/paper/Z6IS6F65","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.03855&json=true","fetch_graph":"https://pith.science/api/pith-number/Z6IS6F65XHH2DQA5N4IOZF4RK6/graph.json","fetch_events":"https://pith.science/api/pith-number/Z6IS6F65XHH2DQA5N4IOZF4RK6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z6IS6F65XHH2DQA5N4IOZF4RK6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z6IS6F65XHH2DQA5N4IOZF4RK6/action/storage_attestation","attest_author":"https://pith.science/pith/Z6IS6F65XHH2DQA5N4IOZF4RK6/action/author_attestation","sign_citation":"https://pith.science/pith/Z6IS6F65XHH2DQA5N4IOZF4RK6/action/citation_signature","submit_replication":"https://pith.science/pith/Z6IS6F65XHH2DQA5N4IOZF4RK6/action/replication_record"}},"created_at":"2026-07-05T10:42:38.952395+00:00","updated_at":"2026-07-05T10:42:38.952395+00:00"}