{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IZBPDOYRUQKYJOM27UOEBALA2H","short_pith_number":"pith:IZBPDOYR","canonical_record":{"source":{"id":"2504.03718","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-29T10:23:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"197613ece241eb7bb81049e9828982c8eb6ed0009c215c80ef78c4123a2a0887","abstract_canon_sha256":"1763bbd692ba21569be672017fb82830e6a9b767b3ea5de9c70ca5f9279b79ba"},"schema_version":"1.0"},"canonical_sha256":"4642f1bb11a41584b99afd1c408160d1c5b9ae119408deea81a7da598f7c7572","source":{"kind":"arxiv","id":"2504.03718","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.03718","created_at":"2026-07-05T10:44:46Z"},{"alias_kind":"arxiv_version","alias_value":"2504.03718v1","created_at":"2026-07-05T10:44:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.03718","created_at":"2026-07-05T10:44:46Z"},{"alias_kind":"pith_short_12","alias_value":"IZBPDOYRUQKY","created_at":"2026-07-05T10:44:46Z"},{"alias_kind":"pith_short_16","alias_value":"IZBPDOYRUQKYJOM2","created_at":"2026-07-05T10:44:46Z"},{"alias_kind":"pith_short_8","alias_value":"IZBPDOYR","created_at":"2026-07-05T10:44:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IZBPDOYRUQKYJOM27UOEBALA2H","target":"record","payload":{"canonical_record":{"source":{"id":"2504.03718","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-29T10:23:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"197613ece241eb7bb81049e9828982c8eb6ed0009c215c80ef78c4123a2a0887","abstract_canon_sha256":"1763bbd692ba21569be672017fb82830e6a9b767b3ea5de9c70ca5f9279b79ba"},"schema_version":"1.0"},"canonical_sha256":"4642f1bb11a41584b99afd1c408160d1c5b9ae119408deea81a7da598f7c7572","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:46.985941Z","signature_b64":"26VD6vL9SvSt3rykQeoFSBhTAp4Hx8r0n0biOYZz0LJKfuFGV0y7fbrOEXh4ma6Y//ijJDobI5Yj+kEv8T9HCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4642f1bb11a41584b99afd1c408160d1c5b9ae119408deea81a7da598f7c7572","last_reissued_at":"2026-07-05T10:44:46.985522Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:46.985522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.03718","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":"2026-07-05T10:44:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PNGEcMC3aayGVDxm8J07EdaRowmt7brDpfVmhrcvYaAtvVFJyPNreiR1lhvHZVVY8qRho7OVofvmcAh+tcdBDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:40:19.032973Z"},"content_sha256":"eeb8f7a7b6e8bdc3454cff6a9e231cdb08322f10516586eb08cb60e61aec4d1b","schema_version":"1.0","event_id":"sha256:eeb8f7a7b6e8bdc3454cff6a9e231cdb08322f10516586eb08cb60e61aec4d1b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IZBPDOYRUQKYJOM27UOEBALA2H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Task-Aware Parameter-Efficient Fine-Tuning of Large Pre-Trained Models at the Edge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Sam Kwong, Senkang Hu, Yanan Ma, Yihang Tao, Yiqin Deng, Yuguang Fang, Zhengru Fang, Zihan Fang","submitted_at":"2025-03-29T10:23:36Z","abstract_excerpt":"Large language models (LLMs) have achieved remarkable success in various tasks, such as decision-making, reasoning, and question answering. They have been widely used in edge devices. However, fine-tuning LLMs to specific tasks at the edge is challenging due to the high computational cost and the limited storage and energy resources at the edge. To address this issue, we propose TaskEdge, a task-aware parameter-efficient fine-tuning framework at the edge, which allocates the most effective parameters to the target task and only updates the task-specific parameters. Specifically, we first desig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.03718","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/2504.03718/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":"2026-07-05T10:44:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"diYgwE2O7ARikAjquz70R/LNFWUyvfFCgdn/uMweBiietR3oVW5d22X5u/qpvj9heFh32smTc0dYbHWiAgG/Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:40:19.033480Z"},"content_sha256":"d8ecf201bb22cad2dd6768864ede28d01bdb43d983f8e159d71ba49e6429178b","schema_version":"1.0","event_id":"sha256:d8ecf201bb22cad2dd6768864ede28d01bdb43d983f8e159d71ba49e6429178b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IZBPDOYRUQKYJOM27UOEBALA2H/bundle.json","state_url":"https://pith.science/pith/IZBPDOYRUQKYJOM27UOEBALA2H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IZBPDOYRUQKYJOM27UOEBALA2H/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":"2026-08-09T02:40:19Z","links":{"resolver":"https://pith.science/pith/IZBPDOYRUQKYJOM27UOEBALA2H","bundle":"https://pith.science/pith/IZBPDOYRUQKYJOM27UOEBALA2H/bundle.json","state":"https://pith.science/pith/IZBPDOYRUQKYJOM27UOEBALA2H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IZBPDOYRUQKYJOM27UOEBALA2H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IZBPDOYRUQKYJOM27UOEBALA2H","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":"1763bbd692ba21569be672017fb82830e6a9b767b3ea5de9c70ca5f9279b79ba","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-29T10:23:36Z","title_canon_sha256":"197613ece241eb7bb81049e9828982c8eb6ed0009c215c80ef78c4123a2a0887"},"schema_version":"1.0","source":{"id":"2504.03718","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.03718","created_at":"2026-07-05T10:44:46Z"},{"alias_kind":"arxiv_version","alias_value":"2504.03718v1","created_at":"2026-07-05T10:44:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.03718","created_at":"2026-07-05T10:44:46Z"},{"alias_kind":"pith_short_12","alias_value":"IZBPDOYRUQKY","created_at":"2026-07-05T10:44:46Z"},{"alias_kind":"pith_short_16","alias_value":"IZBPDOYRUQKYJOM2","created_at":"2026-07-05T10:44:46Z"},{"alias_kind":"pith_short_8","alias_value":"IZBPDOYR","created_at":"2026-07-05T10:44:46Z"}],"graph_snapshots":[{"event_id":"sha256:d8ecf201bb22cad2dd6768864ede28d01bdb43d983f8e159d71ba49e6429178b","target":"graph","created_at":"2026-07-05T10:44:46Z","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/2504.03718/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have achieved remarkable success in various tasks, such as decision-making, reasoning, and question answering. They have been widely used in edge devices. However, fine-tuning LLMs to specific tasks at the edge is challenging due to the high computational cost and the limited storage and energy resources at the edge. To address this issue, we propose TaskEdge, a task-aware parameter-efficient fine-tuning framework at the edge, which allocates the most effective parameters to the target task and only updates the task-specific parameters. Specifically, we first desig","authors_text":"Sam Kwong, Senkang Hu, Yanan Ma, Yihang Tao, Yiqin Deng, Yuguang Fang, Zhengru Fang, Zihan Fang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-29T10:23:36Z","title":"Task-Aware Parameter-Efficient Fine-Tuning of Large Pre-Trained Models at the Edge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.03718","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:eeb8f7a7b6e8bdc3454cff6a9e231cdb08322f10516586eb08cb60e61aec4d1b","target":"record","created_at":"2026-07-05T10:44:46Z","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":"1763bbd692ba21569be672017fb82830e6a9b767b3ea5de9c70ca5f9279b79ba","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-29T10:23:36Z","title_canon_sha256":"197613ece241eb7bb81049e9828982c8eb6ed0009c215c80ef78c4123a2a0887"},"schema_version":"1.0","source":{"id":"2504.03718","kind":"arxiv","version":1}},"canonical_sha256":"4642f1bb11a41584b99afd1c408160d1c5b9ae119408deea81a7da598f7c7572","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4642f1bb11a41584b99afd1c408160d1c5b9ae119408deea81a7da598f7c7572","first_computed_at":"2026-07-05T10:44:46.985522Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:44:46.985522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"26VD6vL9SvSt3rykQeoFSBhTAp4Hx8r0n0biOYZz0LJKfuFGV0y7fbrOEXh4ma6Y//ijJDobI5Yj+kEv8T9HCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:44:46.985941Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.03718","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eeb8f7a7b6e8bdc3454cff6a9e231cdb08322f10516586eb08cb60e61aec4d1b","sha256:d8ecf201bb22cad2dd6768864ede28d01bdb43d983f8e159d71ba49e6429178b"],"state_sha256":"d57cc9e1cff9b358fb7dec116488997cc15cd2333f5b330ca89c778b5c2fa8fe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s/Nm9Ruu/Z1/CUHHvf72BscD+tg+KBRPVR0AvZEvngn/aDdru0h0Fzh0b7zaltTs5ok4YHY0gO8jXzGYnlnaAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T02:40:19.037112Z","bundle_sha256":"08a7feea8cf6b67661ff3035ab383d905542daac57d91c98699acd5c03216542"}}