{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YSHYR3XGFAOUKSF74ERLOKLN4W","short_pith_number":"pith:YSHYR3XG","schema_version":"1.0","canonical_sha256":"c48f88eee6281d4548bfe122b7296de5b8cd6b9a4626da1708d598ffe4e72346","source":{"kind":"arxiv","id":"2408.14470","version":3},"attestation_state":"computed","paper":{"title":"Step-by-Step Unmasking for Parameter-Efficient Fine-tuning of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aradhye Agarwal, Ayan Sengupta, Suhas K Ramesh, Tanmoy Chakraborty","submitted_at":"2024-08-26T17:58:53Z","abstract_excerpt":"Fine-tuning large language models (LLMs) on downstream tasks requires substantial computational resources. Selective PEFT, a class of parameter-efficient fine-tuning (PEFT) methodologies, aims to mitigate these computational challenges by selectively fine-tuning only a small fraction of the model parameters. Although parameter-efficient, these techniques often fail to match the performance of fully fine-tuned models, primarily due to inherent biases introduced during parameter selection. Traditional selective PEFT techniques use a fixed set of parameters selected using different importance heu"},"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":"2408.14470","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-26T17:58:53Z","cross_cats_sorted":[],"title_canon_sha256":"d58d7742a8e876d695e99e3e13cb19aa9f39d8e19b985e55db854bdc1053c91c","abstract_canon_sha256":"f85a02e6c33bcd54d3fab653714cdd2507ad5f43a293fad6e8303a64ccaa2b10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:39.148200Z","signature_b64":"7Pcwkca+i66j1SC4vTNSWXjoIK6Tsnw5irocm1sCJ8gB+s+lteYzR7+gx5y3wrij0gYGMoTWTeLgD/5nBux4Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c48f88eee6281d4548bfe122b7296de5b8cd6b9a4626da1708d598ffe4e72346","last_reissued_at":"2026-07-05T11:25:39.147716Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:39.147716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Step-by-Step Unmasking for Parameter-Efficient Fine-tuning of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aradhye Agarwal, Ayan Sengupta, Suhas K Ramesh, Tanmoy Chakraborty","submitted_at":"2024-08-26T17:58:53Z","abstract_excerpt":"Fine-tuning large language models (LLMs) on downstream tasks requires substantial computational resources. Selective PEFT, a class of parameter-efficient fine-tuning (PEFT) methodologies, aims to mitigate these computational challenges by selectively fine-tuning only a small fraction of the model parameters. Although parameter-efficient, these techniques often fail to match the performance of fully fine-tuned models, primarily due to inherent biases introduced during parameter selection. Traditional selective PEFT techniques use a fixed set of parameters selected using different importance heu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14470","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/2408.14470/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":"2408.14470","created_at":"2026-07-05T11:25:39.147773+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.14470v3","created_at":"2026-07-05T11:25:39.147773+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14470","created_at":"2026-07-05T11:25:39.147773+00:00"},{"alias_kind":"pith_short_12","alias_value":"YSHYR3XGFAOU","created_at":"2026-07-05T11:25:39.147773+00:00"},{"alias_kind":"pith_short_16","alias_value":"YSHYR3XGFAOUKSF7","created_at":"2026-07-05T11:25:39.147773+00:00"},{"alias_kind":"pith_short_8","alias_value":"YSHYR3XG","created_at":"2026-07-05T11:25:39.147773+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.16191","citing_title":"GEM: A Scale-Aware and Distribution-Sensitive Sparse Fine-Tuning Framework for Effective Downstream Adaptation","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YSHYR3XGFAOUKSF74ERLOKLN4W","json":"https://pith.science/pith/YSHYR3XGFAOUKSF74ERLOKLN4W.json","graph_json":"https://pith.science/api/pith-number/YSHYR3XGFAOUKSF74ERLOKLN4W/graph.json","events_json":"https://pith.science/api/pith-number/YSHYR3XGFAOUKSF74ERLOKLN4W/events.json","paper":"https://pith.science/paper/YSHYR3XG"},"agent_actions":{"view_html":"https://pith.science/pith/YSHYR3XGFAOUKSF74ERLOKLN4W","download_json":"https://pith.science/pith/YSHYR3XGFAOUKSF74ERLOKLN4W.json","view_paper":"https://pith.science/paper/YSHYR3XG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.14470&json=true","fetch_graph":"https://pith.science/api/pith-number/YSHYR3XGFAOUKSF74ERLOKLN4W/graph.json","fetch_events":"https://pith.science/api/pith-number/YSHYR3XGFAOUKSF74ERLOKLN4W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YSHYR3XGFAOUKSF74ERLOKLN4W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YSHYR3XGFAOUKSF74ERLOKLN4W/action/storage_attestation","attest_author":"https://pith.science/pith/YSHYR3XGFAOUKSF74ERLOKLN4W/action/author_attestation","sign_citation":"https://pith.science/pith/YSHYR3XGFAOUKSF74ERLOKLN4W/action/citation_signature","submit_replication":"https://pith.science/pith/YSHYR3XGFAOUKSF74ERLOKLN4W/action/replication_record"}},"created_at":"2026-07-05T11:25:39.147773+00:00","updated_at":"2026-07-05T11:25:39.147773+00:00"}