{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DM2KMFTCWBELHKWRHRBHPFG45N","short_pith_number":"pith:DM2KMFTC","schema_version":"1.0","canonical_sha256":"1b34a61662b048b3aad13c427794dceb616af8191a2c04cffadf6845ab2a7948","source":{"kind":"arxiv","id":"2501.19090","version":3},"attestation_state":"computed","paper":{"title":"Pivoting Factorization: A Compact Meta Low-Rank Representation of Sparsity for Efficient Inference in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Carlo Vittorio Cannistraci, Jialin Zhao, Yingtao Zhang","submitted_at":"2025-01-31T12:36:31Z","abstract_excerpt":"The rapid growth of Large Language Models has driven demand for effective model compression techniques to reduce memory and computation costs. Low-rank pruning has gained attention for its GPU compatibility across all densities. However, low-rank pruning struggles to match the performance of semi-structured pruning, often doubling perplexity at similar densities. In this paper, we propose Pivoting Factorization (PIFA), a novel lossless meta low-rank representation that unsupervisedly learns a compact form of any low-rank representation, effectively eliminating redundant information. PIFA ident"},"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":"2501.19090","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-31T12:36:31Z","cross_cats_sorted":[],"title_canon_sha256":"adfd67542982dfbd3bf2ae19ac72aa28ac4e9836b96a89c2c0262a479bcc6288","abstract_canon_sha256":"65a9a5daa88f386016aea36fb6a412855526d41dd06e638c25974f4aecc77474"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:59.200389Z","signature_b64":"qYBPInyUPS30hvoYBe1ro0zLOnnHTSUJfK2M/sfGgM5ZhVYs7zRkAo2v2ur+dAjF0p+o5krKIkeV0ASP2L71CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b34a61662b048b3aad13c427794dceb616af8191a2c04cffadf6845ab2a7948","last_reissued_at":"2026-07-05T11:52:59.199947Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:59.199947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pivoting Factorization: A Compact Meta Low-Rank Representation of Sparsity for Efficient Inference in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Carlo Vittorio Cannistraci, Jialin Zhao, Yingtao Zhang","submitted_at":"2025-01-31T12:36:31Z","abstract_excerpt":"The rapid growth of Large Language Models has driven demand for effective model compression techniques to reduce memory and computation costs. Low-rank pruning has gained attention for its GPU compatibility across all densities. However, low-rank pruning struggles to match the performance of semi-structured pruning, often doubling perplexity at similar densities. In this paper, we propose Pivoting Factorization (PIFA), a novel lossless meta low-rank representation that unsupervisedly learns a compact form of any low-rank representation, effectively eliminating redundant information. PIFA ident"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.19090","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/2501.19090/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":"2501.19090","created_at":"2026-07-05T11:52:59.200002+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.19090v3","created_at":"2026-07-05T11:52:59.200002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.19090","created_at":"2026-07-05T11:52:59.200002+00:00"},{"alias_kind":"pith_short_12","alias_value":"DM2KMFTCWBEL","created_at":"2026-07-05T11:52:59.200002+00:00"},{"alias_kind":"pith_short_16","alias_value":"DM2KMFTCWBELHKWR","created_at":"2026-07-05T11:52:59.200002+00:00"},{"alias_kind":"pith_short_8","alias_value":"DM2KMFTC","created_at":"2026-07-05T11:52:59.200002+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DM2KMFTCWBELHKWRHRBHPFG45N","json":"https://pith.science/pith/DM2KMFTCWBELHKWRHRBHPFG45N.json","graph_json":"https://pith.science/api/pith-number/DM2KMFTCWBELHKWRHRBHPFG45N/graph.json","events_json":"https://pith.science/api/pith-number/DM2KMFTCWBELHKWRHRBHPFG45N/events.json","paper":"https://pith.science/paper/DM2KMFTC"},"agent_actions":{"view_html":"https://pith.science/pith/DM2KMFTCWBELHKWRHRBHPFG45N","download_json":"https://pith.science/pith/DM2KMFTCWBELHKWRHRBHPFG45N.json","view_paper":"https://pith.science/paper/DM2KMFTC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.19090&json=true","fetch_graph":"https://pith.science/api/pith-number/DM2KMFTCWBELHKWRHRBHPFG45N/graph.json","fetch_events":"https://pith.science/api/pith-number/DM2KMFTCWBELHKWRHRBHPFG45N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DM2KMFTCWBELHKWRHRBHPFG45N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DM2KMFTCWBELHKWRHRBHPFG45N/action/storage_attestation","attest_author":"https://pith.science/pith/DM2KMFTCWBELHKWRHRBHPFG45N/action/author_attestation","sign_citation":"https://pith.science/pith/DM2KMFTCWBELHKWRHRBHPFG45N/action/citation_signature","submit_replication":"https://pith.science/pith/DM2KMFTCWBELHKWRHRBHPFG45N/action/replication_record"}},"created_at":"2026-07-05T11:52:59.200002+00:00","updated_at":"2026-07-05T11:52:59.200002+00:00"}