{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:L3NLAG7EU2L7CG3RYNC5CCB7NZ","short_pith_number":"pith:L3NLAG7E","schema_version":"1.0","canonical_sha256":"5edab01be4a697f11b71c345d1083f6e57b5e5aa3528d70dfb4b1e1923008bb3","source":{"kind":"arxiv","id":"2512.02764","version":3},"attestation_state":"computed","paper":{"title":"PEFT-Factory: Unified Parameter-Efficient Fine-Tuning of Autoregressive Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"PEFT-Factory supplies one controlled environment that bundles 19 PEFT methods with 27 datasets for reproducible LLM fine-tuning comparisons.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ivan Srba, Maria Bielikova, Robert Belanec","submitted_at":"2025-12-02T13:44:41Z","abstract_excerpt":"Parameter-Efficient Fine-Tuning (PEFT) methods address the increasing size of Large Language Models (LLMs). Currently, many newly introduced PEFT methods are challenging to replicate, deploy, or compare with one another. To address this, we introduce PEFT-Factory, a unified framework for efficient fine-tuning LLMs using both off-the-shelf and custom PEFT methods. While its modular design supports extensibility, it natively provides a representative set of 19 PEFT methods, 27 classification and text generation datasets addressing 12 tasks, and both standard and PEFT-specific evaluation metrics."},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2512.02764","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-02T13:44:41Z","cross_cats_sorted":[],"title_canon_sha256":"79e97e4a54cfde0d432c85ad0b2cd5fe8e27d6bd0b88c4c52d8dc84960a02cae","abstract_canon_sha256":"25bcd70f0aa37135444ef1f29e54eab459bfbbf54815ae8f08a1f92ed2089ae6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:10:11.693754Z","signature_b64":"6EMm3YIymkuIXfvADT/qqgF4ZhHn+4qlc2/wyLw9gP9RsWkkIUi5VOLuEBWZYTLO/X+KQNSkVvHuQCERJffYDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5edab01be4a697f11b71c345d1083f6e57b5e5aa3528d70dfb4b1e1923008bb3","last_reissued_at":"2026-05-18T03:10:11.692840Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:10:11.692840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PEFT-Factory: Unified Parameter-Efficient Fine-Tuning of Autoregressive Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"PEFT-Factory supplies one controlled environment that bundles 19 PEFT methods with 27 datasets for reproducible LLM fine-tuning comparisons.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ivan Srba, Maria Bielikova, Robert Belanec","submitted_at":"2025-12-02T13:44:41Z","abstract_excerpt":"Parameter-Efficient Fine-Tuning (PEFT) methods address the increasing size of Large Language Models (LLMs). Currently, many newly introduced PEFT methods are challenging to replicate, deploy, or compare with one another. To address this, we introduce PEFT-Factory, a unified framework for efficient fine-tuning LLMs using both off-the-shelf and custom PEFT methods. While its modular design supports extensibility, it natively provides a representative set of 19 PEFT methods, 27 classification and text generation datasets addressing 12 tasks, and both standard and PEFT-specific evaluation metrics."},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"we introduce PEFT-Factory, a unified framework for efficient fine-tuning LLMs using both off-the-shelf and custom PEFT methods... providing a ready-to-use, controlled, and stable environment, improving replicability and benchmarking of PEFT methods.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the modular design and native implementations of the 19 PEFT methods actually deliver stable, comparable results across the 27 datasets without hidden implementation differences or post-hoc tuning that would undermine fair benchmarking.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"PEFT-Factory supplies a ready-to-use, extensible codebase that unifies 19 PEFT methods and evaluation pipelines for fine-tuning large autoregressive language models.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"PEFT-Factory supplies one controlled environment that bundles 19 PEFT methods with 27 datasets for reproducible LLM fine-tuning comparisons.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d377483f8cd44b71b31868c0d3a5f5d3961e2f470dbc1322c129569e887c7f84"},"source":{"id":"2512.02764","kind":"arxiv","version":3},"verdict":{"id":"01553cb2-a705-4613-a6eb-d8a4ba39646b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T02:33:14.545638Z","strongest_claim":"we introduce PEFT-Factory, a unified framework for efficient fine-tuning LLMs using both off-the-shelf and custom PEFT methods... providing a ready-to-use, controlled, and stable environment, improving replicability and benchmarking of PEFT methods.","one_line_summary":"PEFT-Factory supplies a ready-to-use, extensible codebase that unifies 19 PEFT methods and evaluation pipelines for fine-tuning large autoregressive language models.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the modular design and native implementations of the 19 PEFT methods actually deliver stable, comparable results across the 27 datasets without hidden implementation differences or post-hoc tuning that would undermine fair benchmarking.","pith_extraction_headline":"PEFT-Factory supplies one controlled environment that bundles 19 PEFT methods with 27 datasets for reproducible LLM fine-tuning comparisons."},"references":{"count":87,"sample":[{"doi":"","year":null,"title":"online\" 'onlinestring :=","work_id":"38c07273-5071-4bbb-b2af-067af11becc7","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"write newline","work_id":"b6ace3ad-bd44-4a95-86ee-c7b73bd4cda2","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"Takuya Akiba, Makoto Shing, Yujin Tang, Qi Sun, and David Ha","work_id":"4acd1abb-5322-43c7-b701-6718c3d52b72","ref_index":3,"cited_arxiv_id":"1906.02569","is_internal_anchor":true},{"doi":"","year":2023,"title":"Lightning AI. 2023. Litgpt. https://github.com/Lightning-AI/litgpt","work_id":"59d15a2d-c9cf-41ed-9fc6-8042e67ed75f","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.18653/v1/n19-1245","year":2019,"title":"M ath QA : Towards interpretable math word problem solving with operation-based formalisms","work_id":"b73d762e-5f33-41a0-a44d-b2e613bffd36","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":87,"snapshot_sha256":"c8ec48fc6dd5569cc96e5444fcbfa82fe3de4f59c2bda37f4bb0daabfe5f25f5","internal_anchors":15},"formal_canon":{"evidence_count":2,"snapshot_sha256":"9c32b958ef19d43943cf76a2e8418b1177678f3cfb9565e584bcbde2b32c50be"},"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":"2512.02764","created_at":"2026-05-18T03:10:11.693027+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.02764v3","created_at":"2026-05-18T03:10:11.693027+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.02764","created_at":"2026-05-18T03:10:11.693027+00:00"},{"alias_kind":"pith_short_12","alias_value":"L3NLAG7EU2L7","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"L3NLAG7EU2L7CG3R","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"L3NLAG7E","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L3NLAG7EU2L7CG3RYNC5CCB7NZ","json":"https://pith.science/pith/L3NLAG7EU2L7CG3RYNC5CCB7NZ.json","graph_json":"https://pith.science/api/pith-number/L3NLAG7EU2L7CG3RYNC5CCB7NZ/graph.json","events_json":"https://pith.science/api/pith-number/L3NLAG7EU2L7CG3RYNC5CCB7NZ/events.json","paper":"https://pith.science/paper/L3NLAG7E"},"agent_actions":{"view_html":"https://pith.science/pith/L3NLAG7EU2L7CG3RYNC5CCB7NZ","download_json":"https://pith.science/pith/L3NLAG7EU2L7CG3RYNC5CCB7NZ.json","view_paper":"https://pith.science/paper/L3NLAG7E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.02764&json=true","fetch_graph":"https://pith.science/api/pith-number/L3NLAG7EU2L7CG3RYNC5CCB7NZ/graph.json","fetch_events":"https://pith.science/api/pith-number/L3NLAG7EU2L7CG3RYNC5CCB7NZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L3NLAG7EU2L7CG3RYNC5CCB7NZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L3NLAG7EU2L7CG3RYNC5CCB7NZ/action/storage_attestation","attest_author":"https://pith.science/pith/L3NLAG7EU2L7CG3RYNC5CCB7NZ/action/author_attestation","sign_citation":"https://pith.science/pith/L3NLAG7EU2L7CG3RYNC5CCB7NZ/action/citation_signature","submit_replication":"https://pith.science/pith/L3NLAG7EU2L7CG3RYNC5CCB7NZ/action/replication_record"}},"created_at":"2026-05-18T03:10:11.693027+00:00","updated_at":"2026-05-18T03:10:11.693027+00:00"}