{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3RBEX6JIIU5FFRUT53VEMG2AKP","short_pith_number":"pith:3RBEX6JI","schema_version":"1.0","canonical_sha256":"dc424bf928453a52c693eeea461b4053d025900d083d9e5df4f12be71f0f1a2d","source":{"kind":"arxiv","id":"2406.09117","version":1},"attestation_state":"computed","paper":{"title":"PC-LoRA: Low-Rank Adaptation for Progressive Model Compression with Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haewon Park, Injoon Hwang, Jooyoung Yang, SunJae Maeng, Youngwan Lee","submitted_at":"2024-06-13T13:44:31Z","abstract_excerpt":"Low-rank adaption (LoRA) is a prominent method that adds a small number of learnable parameters to the frozen pre-trained weights for parameter-efficient fine-tuning. Prompted by the question, ``Can we make its representation enough with LoRA weights solely at the final phase of finetuning without the pre-trained weights?'' In this work, we introduce Progressive Compression LoRA~(PC-LoRA), which utilizes low-rank adaptation (LoRA) to simultaneously perform model compression and fine-tuning. The PC-LoRA method gradually removes the pre-trained weights during the training process, eventually lea"},"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":"2406.09117","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T13:44:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c1c8502d4bedd38b8c679ac8ed407f942612092363b1604495fe10f9396ba7e7","abstract_canon_sha256":"b1d1016ab3ef3d424ba5ca192976fabfed5fbc3d11b6244d60879b4a922fbd64"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:28.322528Z","signature_b64":"feNWfFtSxrOI8GdPfg1seyzfah5JMHbUaEkOk4tGJFygsGke+UNguaqE2TS1NNHbFLvVIHcQwhytjnHyrr9aAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc424bf928453a52c693eeea461b4053d025900d083d9e5df4f12be71f0f1a2d","last_reissued_at":"2026-07-05T08:31:28.321936Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:28.321936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PC-LoRA: Low-Rank Adaptation for Progressive Model Compression with Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haewon Park, Injoon Hwang, Jooyoung Yang, SunJae Maeng, Youngwan Lee","submitted_at":"2024-06-13T13:44:31Z","abstract_excerpt":"Low-rank adaption (LoRA) is a prominent method that adds a small number of learnable parameters to the frozen pre-trained weights for parameter-efficient fine-tuning. Prompted by the question, ``Can we make its representation enough with LoRA weights solely at the final phase of finetuning without the pre-trained weights?'' In this work, we introduce Progressive Compression LoRA~(PC-LoRA), which utilizes low-rank adaptation (LoRA) to simultaneously perform model compression and fine-tuning. The PC-LoRA method gradually removes the pre-trained weights during the training process, eventually lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09117","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/2406.09117/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":"2406.09117","created_at":"2026-07-05T08:31:28.322032+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.09117v1","created_at":"2026-07-05T08:31:28.322032+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09117","created_at":"2026-07-05T08:31:28.322032+00:00"},{"alias_kind":"pith_short_12","alias_value":"3RBEX6JIIU5F","created_at":"2026-07-05T08:31:28.322032+00:00"},{"alias_kind":"pith_short_16","alias_value":"3RBEX6JIIU5FFRUT","created_at":"2026-07-05T08:31:28.322032+00:00"},{"alias_kind":"pith_short_8","alias_value":"3RBEX6JI","created_at":"2026-07-05T08:31:28.322032+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08565","citing_title":"EinSort: Sorting is All We Need for Tensorizing LLM","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02829","citing_title":"Compress Then Adapt? No, Do It Together via Task-aware Union of Subspaces","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3RBEX6JIIU5FFRUT53VEMG2AKP","json":"https://pith.science/pith/3RBEX6JIIU5FFRUT53VEMG2AKP.json","graph_json":"https://pith.science/api/pith-number/3RBEX6JIIU5FFRUT53VEMG2AKP/graph.json","events_json":"https://pith.science/api/pith-number/3RBEX6JIIU5FFRUT53VEMG2AKP/events.json","paper":"https://pith.science/paper/3RBEX6JI"},"agent_actions":{"view_html":"https://pith.science/pith/3RBEX6JIIU5FFRUT53VEMG2AKP","download_json":"https://pith.science/pith/3RBEX6JIIU5FFRUT53VEMG2AKP.json","view_paper":"https://pith.science/paper/3RBEX6JI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.09117&json=true","fetch_graph":"https://pith.science/api/pith-number/3RBEX6JIIU5FFRUT53VEMG2AKP/graph.json","fetch_events":"https://pith.science/api/pith-number/3RBEX6JIIU5FFRUT53VEMG2AKP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3RBEX6JIIU5FFRUT53VEMG2AKP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3RBEX6JIIU5FFRUT53VEMG2AKP/action/storage_attestation","attest_author":"https://pith.science/pith/3RBEX6JIIU5FFRUT53VEMG2AKP/action/author_attestation","sign_citation":"https://pith.science/pith/3RBEX6JIIU5FFRUT53VEMG2AKP/action/citation_signature","submit_replication":"https://pith.science/pith/3RBEX6JIIU5FFRUT53VEMG2AKP/action/replication_record"}},"created_at":"2026-07-05T08:31:28.322032+00:00","updated_at":"2026-07-05T08:31:28.322032+00:00"}