{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5BN3V5BHPRYP3IFGDV5EGA66V2","short_pith_number":"pith:5BN3V5BH","canonical_record":{"source":{"id":"2406.03792","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-06T07:03:29Z","cross_cats_sorted":[],"title_canon_sha256":"cfc6ace88c588e475e687faca0757b58d275742b4b22d34d13b4b2f78c5934d9","abstract_canon_sha256":"5c30ca2291a671a96bb7029c6e0cb1f8efb43a7bd316b6adbaebadc12ec522fd"},"schema_version":"1.0"},"canonical_sha256":"e85bbaf4277c70fda0a61d7a4303deae9841498fbe399d835ddd72b45322e236","source":{"kind":"arxiv","id":"2406.03792","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.03792","created_at":"2026-07-05T08:28:15Z"},{"alias_kind":"arxiv_version","alias_value":"2406.03792v1","created_at":"2026-07-05T08:28:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03792","created_at":"2026-07-05T08:28:15Z"},{"alias_kind":"pith_short_12","alias_value":"5BN3V5BHPRYP","created_at":"2026-07-05T08:28:15Z"},{"alias_kind":"pith_short_16","alias_value":"5BN3V5BHPRYP3IFG","created_at":"2026-07-05T08:28:15Z"},{"alias_kind":"pith_short_8","alias_value":"5BN3V5BH","created_at":"2026-07-05T08:28:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5BN3V5BHPRYP3IFGDV5EGA66V2","target":"record","payload":{"canonical_record":{"source":{"id":"2406.03792","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-06T07:03:29Z","cross_cats_sorted":[],"title_canon_sha256":"cfc6ace88c588e475e687faca0757b58d275742b4b22d34d13b4b2f78c5934d9","abstract_canon_sha256":"5c30ca2291a671a96bb7029c6e0cb1f8efb43a7bd316b6adbaebadc12ec522fd"},"schema_version":"1.0"},"canonical_sha256":"e85bbaf4277c70fda0a61d7a4303deae9841498fbe399d835ddd72b45322e236","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:15.991221Z","signature_b64":"Wd4Z0KiRdupa8LdpVRHw7CAEmIjYWxvNDf/S1eAQVhOyAvbPXHKT96HWKwX7Vx9B92/S/LT4awo0IkFMWbE1AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e85bbaf4277c70fda0a61d7a4303deae9841498fbe399d835ddd72b45322e236","last_reissued_at":"2026-07-05T08:28:15.990831Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:15.990831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.03792","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":"2026-07-05T08:28:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e5GAOmDoPJW5bSJNLCaiUKHs8I2N4lZax3dqMMQe9J95lg7v+alpnSSOUoF/RfnWz5O5xDlz3hkwOqF4dB0IAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T12:30:45.082796Z"},"content_sha256":"20a9621103ecf194d6ed7ef33b2d2de14b43503de74211f030c8b546555d2a04","schema_version":"1.0","event_id":"sha256:20a9621103ecf194d6ed7ef33b2d2de14b43503de74211f030c8b546555d2a04"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5BN3V5BHPRYP3IFGDV5EGA66V2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Light-PEFT: Lightening Parameter-Efficient Fine-Tuning via Early Pruning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bowen Shen, Naibin Gu, Peng Fu, Weiping Wang, Xiyu Liu, Zheng Lin","submitted_at":"2024-06-06T07:03:29Z","abstract_excerpt":"Parameter-efficient fine-tuning (PEFT) has emerged as the predominant technique for fine-tuning in the era of large language models. However, existing PEFT methods still have inadequate training efficiency. Firstly, the utilization of large-scale foundation models during the training process is excessively redundant for certain fine-tuning tasks. Secondly, as the model size increases, the growth in trainable parameters of empirically added PEFT modules becomes non-negligible and redundant, leading to inefficiency. To achieve task-specific efficient fine-tuning, we propose the Light-PEFT framew"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03792","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/2406.03792/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":"2026-07-05T08:28:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"semczAQS+XWnUpdnatTGkSLTbF+cEhO0pppcLDRH4bkP4iC9RwV5eFnGTOzxxiRRigpJOb7IRikD6eFepqLNDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T12:30:45.083169Z"},"content_sha256":"6fefa64cb1abfb75c2e116bef3220cd79e6a43b6ac2a0269eb09ac64a5451e03","schema_version":"1.0","event_id":"sha256:6fefa64cb1abfb75c2e116bef3220cd79e6a43b6ac2a0269eb09ac64a5451e03"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5BN3V5BHPRYP3IFGDV5EGA66V2/bundle.json","state_url":"https://pith.science/pith/5BN3V5BHPRYP3IFGDV5EGA66V2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5BN3V5BHPRYP3IFGDV5EGA66V2/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":"2026-07-17T12:30:45Z","links":{"resolver":"https://pith.science/pith/5BN3V5BHPRYP3IFGDV5EGA66V2","bundle":"https://pith.science/pith/5BN3V5BHPRYP3IFGDV5EGA66V2/bundle.json","state":"https://pith.science/pith/5BN3V5BHPRYP3IFGDV5EGA66V2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5BN3V5BHPRYP3IFGDV5EGA66V2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5BN3V5BHPRYP3IFGDV5EGA66V2","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":"5c30ca2291a671a96bb7029c6e0cb1f8efb43a7bd316b6adbaebadc12ec522fd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-06T07:03:29Z","title_canon_sha256":"cfc6ace88c588e475e687faca0757b58d275742b4b22d34d13b4b2f78c5934d9"},"schema_version":"1.0","source":{"id":"2406.03792","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.03792","created_at":"2026-07-05T08:28:15Z"},{"alias_kind":"arxiv_version","alias_value":"2406.03792v1","created_at":"2026-07-05T08:28:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03792","created_at":"2026-07-05T08:28:15Z"},{"alias_kind":"pith_short_12","alias_value":"5BN3V5BHPRYP","created_at":"2026-07-05T08:28:15Z"},{"alias_kind":"pith_short_16","alias_value":"5BN3V5BHPRYP3IFG","created_at":"2026-07-05T08:28:15Z"},{"alias_kind":"pith_short_8","alias_value":"5BN3V5BH","created_at":"2026-07-05T08:28:15Z"}],"graph_snapshots":[{"event_id":"sha256:6fefa64cb1abfb75c2e116bef3220cd79e6a43b6ac2a0269eb09ac64a5451e03","target":"graph","created_at":"2026-07-05T08:28:15Z","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/2406.03792/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Parameter-efficient fine-tuning (PEFT) has emerged as the predominant technique for fine-tuning in the era of large language models. However, existing PEFT methods still have inadequate training efficiency. Firstly, the utilization of large-scale foundation models during the training process is excessively redundant for certain fine-tuning tasks. Secondly, as the model size increases, the growth in trainable parameters of empirically added PEFT modules becomes non-negligible and redundant, leading to inefficiency. To achieve task-specific efficient fine-tuning, we propose the Light-PEFT framew","authors_text":"Bowen Shen, Naibin Gu, Peng Fu, Weiping Wang, Xiyu Liu, Zheng Lin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-06T07:03:29Z","title":"Light-PEFT: Lightening Parameter-Efficient Fine-Tuning via Early Pruning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03792","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":"sha256:20a9621103ecf194d6ed7ef33b2d2de14b43503de74211f030c8b546555d2a04","target":"record","created_at":"2026-07-05T08:28:15Z","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":"5c30ca2291a671a96bb7029c6e0cb1f8efb43a7bd316b6adbaebadc12ec522fd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-06T07:03:29Z","title_canon_sha256":"cfc6ace88c588e475e687faca0757b58d275742b4b22d34d13b4b2f78c5934d9"},"schema_version":"1.0","source":{"id":"2406.03792","kind":"arxiv","version":1}},"canonical_sha256":"e85bbaf4277c70fda0a61d7a4303deae9841498fbe399d835ddd72b45322e236","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e85bbaf4277c70fda0a61d7a4303deae9841498fbe399d835ddd72b45322e236","first_computed_at":"2026-07-05T08:28:15.990831Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:15.990831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Wd4Z0KiRdupa8LdpVRHw7CAEmIjYWxvNDf/S1eAQVhOyAvbPXHKT96HWKwX7Vx9B92/S/LT4awo0IkFMWbE1AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:15.991221Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.03792","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20a9621103ecf194d6ed7ef33b2d2de14b43503de74211f030c8b546555d2a04","sha256:6fefa64cb1abfb75c2e116bef3220cd79e6a43b6ac2a0269eb09ac64a5451e03"],"state_sha256":"da567ab4322dc53de528fc658ba36d12ed02385d9dcb4c6ccf5a137f7dd116f4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NoImFPCrkg1plTWBwkWbS74CkQOjQ/x0UvgFbURkuGSUUBPlwGnsqdhOJXdAzsWWU6/TcL77yosR33jV8j3kBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T12:30:45.085728Z","bundle_sha256":"eefde047c9c9354cb646f07d76aec51e596ae953f74f923a1999c360b156afd4"}}