{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:F2XV7NX477HLBBH5OKPE5CCXUM","short_pith_number":"pith:F2XV7NX4","schema_version":"1.0","canonical_sha256":"2eaf5fb6fcffceb084fd729e4e8857a32a053a71273320e0082f7bbeddc8636a","source":{"kind":"arxiv","id":"2212.10650","version":1},"attestation_state":"computed","paper":{"title":"KronA: Parameter Efficient Tuning with Kronecker Adapter","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ali Edalati, Ivan Kobyzev, James J. Clark, Marzieh Tahaei, Mehdi Rezagholizadeh, Vahid Partovi Nia","submitted_at":"2022-12-20T20:56:52Z","abstract_excerpt":"Fine-tuning a Pre-trained Language Model (PLM) on a specific downstream task has been a well-known paradigm in Natural Language Processing. However, with the ever-growing size of PLMs, training the entire model on several downstream tasks becomes very expensive and resource-hungry. Recently, different Parameter Efficient Tuning (PET) techniques are proposed to improve the efficiency of fine-tuning PLMs. One popular category of PET methods is the low-rank adaptation methods which insert learnable truncated SVD modules into the original model either sequentially or in parallel. However, low-rank"},"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":"2212.10650","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T20:56:52Z","cross_cats_sorted":[],"title_canon_sha256":"7f317407fe29aa58209cfb3dfbb41160d31d14ff7e426b57bd2b173279c0feaa","abstract_canon_sha256":"2c4ae5025578220f6ecc55c0a905addb107a413208c834b5267685d74567e79f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:27:10.418904Z","signature_b64":"ErzoQmzRFx9x1ZbjNfs3HOhtMiCznMxoAEg0Z2LcGXQe1sQwhSVn77sPJeomAE59ZrNtoFmmQqmiu6KX8kcYCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2eaf5fb6fcffceb084fd729e4e8857a32a053a71273320e0082f7bbeddc8636a","last_reissued_at":"2026-07-05T05:27:10.418498Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:27:10.418498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KronA: Parameter Efficient Tuning with Kronecker Adapter","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ali Edalati, Ivan Kobyzev, James J. Clark, Marzieh Tahaei, Mehdi Rezagholizadeh, Vahid Partovi Nia","submitted_at":"2022-12-20T20:56:52Z","abstract_excerpt":"Fine-tuning a Pre-trained Language Model (PLM) on a specific downstream task has been a well-known paradigm in Natural Language Processing. However, with the ever-growing size of PLMs, training the entire model on several downstream tasks becomes very expensive and resource-hungry. Recently, different Parameter Efficient Tuning (PET) techniques are proposed to improve the efficiency of fine-tuning PLMs. One popular category of PET methods is the low-rank adaptation methods which insert learnable truncated SVD modules into the original model either sequentially or in parallel. However, low-rank"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10650","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/2212.10650/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":"2212.10650","created_at":"2026-07-05T05:27:10.418554+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.10650v1","created_at":"2026-07-05T05:27:10.418554+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10650","created_at":"2026-07-05T05:27:10.418554+00:00"},{"alias_kind":"pith_short_12","alias_value":"F2XV7NX477HL","created_at":"2026-07-05T05:27:10.418554+00:00"},{"alias_kind":"pith_short_16","alias_value":"F2XV7NX477HLBBH5","created_at":"2026-07-05T05:27:10.418554+00:00"},{"alias_kind":"pith_short_8","alias_value":"F2XV7NX4","created_at":"2026-07-05T05:27:10.418554+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08565","citing_title":"EinSort: Sorting is All We Need for Tensorizing LLM","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28819","citing_title":"PEFT-Arena: Understanding Parameter-Efficient Finetuning from a Stability-Plasticity Perspective","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2501.05465","citing_title":"Small Language Models (SLMs) Can Still Pack a Punch: A survey (updated 2026)","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2506.18493","citing_title":"ShowFlow: From Robust Single Concept to Condition-Free Multi-Concept Generation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2403.14608","citing_title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10649","citing_title":"SpectralLoRA: Is Low-Frequency Structure Sufficient for LoRA Adaptation? A Spectral Analysis of Weight Updates","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F2XV7NX477HLBBH5OKPE5CCXUM","json":"https://pith.science/pith/F2XV7NX477HLBBH5OKPE5CCXUM.json","graph_json":"https://pith.science/api/pith-number/F2XV7NX477HLBBH5OKPE5CCXUM/graph.json","events_json":"https://pith.science/api/pith-number/F2XV7NX477HLBBH5OKPE5CCXUM/events.json","paper":"https://pith.science/paper/F2XV7NX4"},"agent_actions":{"view_html":"https://pith.science/pith/F2XV7NX477HLBBH5OKPE5CCXUM","download_json":"https://pith.science/pith/F2XV7NX477HLBBH5OKPE5CCXUM.json","view_paper":"https://pith.science/paper/F2XV7NX4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.10650&json=true","fetch_graph":"https://pith.science/api/pith-number/F2XV7NX477HLBBH5OKPE5CCXUM/graph.json","fetch_events":"https://pith.science/api/pith-number/F2XV7NX477HLBBH5OKPE5CCXUM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F2XV7NX477HLBBH5OKPE5CCXUM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F2XV7NX477HLBBH5OKPE5CCXUM/action/storage_attestation","attest_author":"https://pith.science/pith/F2XV7NX477HLBBH5OKPE5CCXUM/action/author_attestation","sign_citation":"https://pith.science/pith/F2XV7NX477HLBBH5OKPE5CCXUM/action/citation_signature","submit_replication":"https://pith.science/pith/F2XV7NX477HLBBH5OKPE5CCXUM/action/replication_record"}},"created_at":"2026-07-05T05:27:10.418554+00:00","updated_at":"2026-07-05T05:27:10.418554+00:00"}