{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JJOWR5I4VKZISNP5UT3WY76G3O","short_pith_number":"pith:JJOWR5I4","schema_version":"1.0","canonical_sha256":"4a5d68f51caab28935fda4f76c7fc6db919f1ddf336ee660c00bfaed4d8a1f36","source":{"kind":"arxiv","id":"2608.04488","version":1},"attestation_state":"computed","paper":{"title":"Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jurn-Gyu Park, Kuanysh Akhmetzhanov","submitted_at":"2026-08-05T06:20:57Z","abstract_excerpt":"Despite rapid advances in large language models (LLMs), deploying and personalizing them on resource-constrained devices remains impractical due to high VRAM, time, and energy costs. Parameter-Efficient Fine-Tuning (PEFT) of Small Language Models (SLMs) offers a promising alternative, yet few studies compare PEFT methods across architectures using both general and personalization benchmarks while accounting for energy consumption. We compare five fine-tuning approaches (Full Fine-Tuning, LoRA, LoRA+, QLoRA, and BitFit) on four SLMs from two families (Transformer-based: TinyLlama-1.1B, Qwen3-1."},"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":"2608.04488","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-05T06:20:57Z","cross_cats_sorted":[],"title_canon_sha256":"1fb637ec6bc9eef89573bd65b0816220d906911f363d178a6b82878c9d8e912a","abstract_canon_sha256":"cc900cc333bf7a52a7d2b25fab46bb625978bfecc5f26a6e1f1664da99bd4c52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:35:41.993325Z","signature_b64":"ZA/cBRH2tVqwIyHzwKv4D+mZPZiW06LEQCn1L6D8v2euFPolqnuH/KlFW7/2PfT3zXIhUE/nL0zDlmEDRO8uDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a5d68f51caab28935fda4f76c7fc6db919f1ddf336ee660c00bfaed4d8a1f36","last_reissued_at":"2026-08-06T01:35:41.991844Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:35:41.991844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jurn-Gyu Park, Kuanysh Akhmetzhanov","submitted_at":"2026-08-05T06:20:57Z","abstract_excerpt":"Despite rapid advances in large language models (LLMs), deploying and personalizing them on resource-constrained devices remains impractical due to high VRAM, time, and energy costs. Parameter-Efficient Fine-Tuning (PEFT) of Small Language Models (SLMs) offers a promising alternative, yet few studies compare PEFT methods across architectures using both general and personalization benchmarks while accounting for energy consumption. We compare five fine-tuning approaches (Full Fine-Tuning, LoRA, LoRA+, QLoRA, and BitFit) on four SLMs from two families (Transformer-based: TinyLlama-1.1B, Qwen3-1."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04488","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/2608.04488/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":"2608.04488","created_at":"2026-08-06T01:35:41.993730+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.04488v1","created_at":"2026-08-06T01:35:41.993730+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04488","created_at":"2026-08-06T01:35:41.993730+00:00"},{"alias_kind":"pith_short_12","alias_value":"JJOWR5I4VKZI","created_at":"2026-08-06T01:35:41.993730+00:00"},{"alias_kind":"pith_short_16","alias_value":"JJOWR5I4VKZISNP5","created_at":"2026-08-06T01:35:41.993730+00:00"},{"alias_kind":"pith_short_8","alias_value":"JJOWR5I4","created_at":"2026-08-06T01:35:41.993730+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/JJOWR5I4VKZISNP5UT3WY76G3O","json":"https://pith.science/pith/JJOWR5I4VKZISNP5UT3WY76G3O.json","graph_json":"https://pith.science/api/pith-number/JJOWR5I4VKZISNP5UT3WY76G3O/graph.json","events_json":"https://pith.science/api/pith-number/JJOWR5I4VKZISNP5UT3WY76G3O/events.json","paper":"https://pith.science/paper/JJOWR5I4"},"agent_actions":{"view_html":"https://pith.science/pith/JJOWR5I4VKZISNP5UT3WY76G3O","download_json":"https://pith.science/pith/JJOWR5I4VKZISNP5UT3WY76G3O.json","view_paper":"https://pith.science/paper/JJOWR5I4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.04488&json=true","fetch_graph":"https://pith.science/api/pith-number/JJOWR5I4VKZISNP5UT3WY76G3O/graph.json","fetch_events":"https://pith.science/api/pith-number/JJOWR5I4VKZISNP5UT3WY76G3O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JJOWR5I4VKZISNP5UT3WY76G3O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JJOWR5I4VKZISNP5UT3WY76G3O/action/storage_attestation","attest_author":"https://pith.science/pith/JJOWR5I4VKZISNP5UT3WY76G3O/action/author_attestation","sign_citation":"https://pith.science/pith/JJOWR5I4VKZISNP5UT3WY76G3O/action/citation_signature","submit_replication":"https://pith.science/pith/JJOWR5I4VKZISNP5UT3WY76G3O/action/replication_record"}},"created_at":"2026-08-06T01:35:41.993730+00:00","updated_at":"2026-08-06T01:35:41.993730+00:00"}