{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JJOWR5I4VKZISNP5UT3WY76G3O","short_pith_number":"pith:JJOWR5I4","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"},"canonical_sha256":"4a5d68f51caab28935fda4f76c7fc6db919f1ddf336ee660c00bfaed4d8a1f36","source":{"kind":"arxiv","id":"2608.04488","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.04488","created_at":"2026-08-06T01:35:41Z"},{"alias_kind":"arxiv_version","alias_value":"2608.04488v1","created_at":"2026-08-06T01:35:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04488","created_at":"2026-08-06T01:35:41Z"},{"alias_kind":"pith_short_12","alias_value":"JJOWR5I4VKZI","created_at":"2026-08-06T01:35:41Z"},{"alias_kind":"pith_short_16","alias_value":"JJOWR5I4VKZISNP5","created_at":"2026-08-06T01:35:41Z"},{"alias_kind":"pith_short_8","alias_value":"JJOWR5I4","created_at":"2026-08-06T01:35:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JJOWR5I4VKZISNP5UT3WY76G3O","target":"record","payload":{"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"},"canonical_sha256":"4a5d68f51caab28935fda4f76c7fc6db919f1ddf336ee660c00bfaed4d8a1f36","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"},"source_kind":"arxiv","source_id":"2608.04488","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-06T01:35:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jjULzHdzfjbnyT8MsTrPlx3d65hkH9qZ4+vctkle6AHeKnrO38iviRzF9tJ3w9mdnC1OtxG/DBhFiA1Z/s2+Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T00:28:09.032194Z"},"content_sha256":"99f998db8ebdda4cc91971e556134c433e9e5b650bcbddd520b122ea196e46b8","schema_version":"1.0","event_id":"sha256:99f998db8ebdda4cc91971e556134c433e9e5b650bcbddd520b122ea196e46b8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JJOWR5I4VKZISNP5UT3WY76G3O","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-06T01:35:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5rwLvWg10wLG4e+Ok5ZEleHhZXgQyGUtxA6Knp0jo/skhr6b6SzjcJ9wuCM/XU0ZoGXUOovooYWOiM1ikFhTAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T00:28:09.032676Z"},"content_sha256":"74941cb0a79f17a3ce2b7673e0d40639743db6b5e858e29cf8b04ef1ee84f26f","schema_version":"1.0","event_id":"sha256:74941cb0a79f17a3ce2b7673e0d40639743db6b5e858e29cf8b04ef1ee84f26f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JJOWR5I4VKZISNP5UT3WY76G3O/bundle.json","state_url":"https://pith.science/pith/JJOWR5I4VKZISNP5UT3WY76G3O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JJOWR5I4VKZISNP5UT3WY76G3O/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T00:28:09Z","links":{"resolver":"https://pith.science/pith/JJOWR5I4VKZISNP5UT3WY76G3O","bundle":"https://pith.science/pith/JJOWR5I4VKZISNP5UT3WY76G3O/bundle.json","state":"https://pith.science/pith/JJOWR5I4VKZISNP5UT3WY76G3O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JJOWR5I4VKZISNP5UT3WY76G3O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JJOWR5I4VKZISNP5UT3WY76G3O","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"cc900cc333bf7a52a7d2b25fab46bb625978bfecc5f26a6e1f1664da99bd4c52","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-05T06:20:57Z","title_canon_sha256":"1fb637ec6bc9eef89573bd65b0816220d906911f363d178a6b82878c9d8e912a"},"schema_version":"1.0","source":{"id":"2608.04488","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.04488","created_at":"2026-08-06T01:35:41Z"},{"alias_kind":"arxiv_version","alias_value":"2608.04488v1","created_at":"2026-08-06T01:35:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04488","created_at":"2026-08-06T01:35:41Z"},{"alias_kind":"pith_short_12","alias_value":"JJOWR5I4VKZI","created_at":"2026-08-06T01:35:41Z"},{"alias_kind":"pith_short_16","alias_value":"JJOWR5I4VKZISNP5","created_at":"2026-08-06T01:35:41Z"},{"alias_kind":"pith_short_8","alias_value":"JJOWR5I4","created_at":"2026-08-06T01:35:41Z"}],"graph_snapshots":[{"event_id":"sha256:74941cb0a79f17a3ce2b7673e0d40639743db6b5e858e29cf8b04ef1ee84f26f","target":"graph","created_at":"2026-08-06T01:35:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2608.04488/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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.","authors_text":"Jurn-Gyu Park, Kuanysh Akhmetzhanov","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-05T06:20:57Z","title":"Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04488","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:99f998db8ebdda4cc91971e556134c433e9e5b650bcbddd520b122ea196e46b8","target":"record","created_at":"2026-08-06T01:35:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"cc900cc333bf7a52a7d2b25fab46bb625978bfecc5f26a6e1f1664da99bd4c52","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-05T06:20:57Z","title_canon_sha256":"1fb637ec6bc9eef89573bd65b0816220d906911f363d178a6b82878c9d8e912a"},"schema_version":"1.0","source":{"id":"2608.04488","kind":"arxiv","version":1}},"canonical_sha256":"4a5d68f51caab28935fda4f76c7fc6db919f1ddf336ee660c00bfaed4d8a1f36","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a5d68f51caab28935fda4f76c7fc6db919f1ddf336ee660c00bfaed4d8a1f36","first_computed_at":"2026-08-06T01:35:41.991844Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-06T01:35:41.991844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZA/cBRH2tVqwIyHzwKv4D+mZPZiW06LEQCn1L6D8v2euFPolqnuH/KlFW7/2PfT3zXIhUE/nL0zDlmEDRO8uDQ==","signature_status":"signed_v1","signed_at":"2026-08-06T01:35:41.993325Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.04488","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:99f998db8ebdda4cc91971e556134c433e9e5b650bcbddd520b122ea196e46b8","sha256:74941cb0a79f17a3ce2b7673e0d40639743db6b5e858e29cf8b04ef1ee84f26f"],"state_sha256":"33c692209bc0d5cb92fc2733b8b040ad0a3c9dc99dfc9d18c2fa5eacef055a24"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OVNXCejqzKhE239iM0476JpuSFe6yovbtADcq07yvoBFKuA2UUt1t1zfaYrPazIvNyFmz07raDfvWbSP26PFCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T00:28:09.036020Z","bundle_sha256":"54a873b2c2decc4ea34d5362aa7bf29be9e75aa40b0b3d067ac85d64daac0cd8"}}