{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4W5EPPKRVJKMVP6WO6RSRBV7RU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3afeb79aac793c21f28cf3fb4d6384e0f49ea79706a2528374b5c91e08d3d47a","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-29T08:42:30Z","title_canon_sha256":"8d77466e9b708ccd6cecc586690d004e1e4661237c3410366423b51e45ad0f01"},"schema_version":"1.0","source":{"id":"2405.18886","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18886","created_at":"2026-07-05T09:30:15Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18886v2","created_at":"2026-07-05T09:30:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18886","created_at":"2026-07-05T09:30:15Z"},{"alias_kind":"pith_short_12","alias_value":"4W5EPPKRVJKM","created_at":"2026-07-05T09:30:15Z"},{"alias_kind":"pith_short_16","alias_value":"4W5EPPKRVJKMVP6W","created_at":"2026-07-05T09:30:15Z"},{"alias_kind":"pith_short_8","alias_value":"4W5EPPKR","created_at":"2026-07-05T09:30:15Z"}],"graph_snapshots":[{"event_id":"sha256:65795c679f7770dcea70b94703e6767b8f4ce1d249b3aa54db92f7f31c6e83a1","target":"graph","created_at":"2026-07-05T09:30:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2405.18886/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The prohibitive sizes of Large Language Models (LLMs) today make it difficult to deploy them on memory-constrained edge devices. This work introduces $\\rm CALDERA$ -- a new post-training LLM compression algorithm that harnesses the inherent low-rank structure of a weight matrix $\\mathbf{W}$ by approximating it via a low-rank, low-precision decomposition as $\\mathbf{W} \\approx \\mathbf{Q} + \\mathbf{L}\\mathbf{R}$. Here, $\\mathbf{L}$ and $\\mathbf{R}$ are low rank factors, and the entries of $\\mathbf{Q}$, $\\mathbf{L}$ and $\\mathbf{R}$ are quantized. The model is compressed by substituting each laye","authors_text":"Andrea J. Goldsmith, Mert Pilanci, Naomi Sagan, Rajarshi Saha, Varun Srivastava","cross_cats":["cs.AI","math.OC","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-29T08:42:30Z","title":"Compressing Large Language Models using Low Rank and Low Precision Decomposition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18886","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:478634b2da51434e4d3e81312e8ca73ce2a91a5b5092793dea8e29a9f27b3632","target":"record","created_at":"2026-07-05T09:30:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3afeb79aac793c21f28cf3fb4d6384e0f49ea79706a2528374b5c91e08d3d47a","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-29T08:42:30Z","title_canon_sha256":"8d77466e9b708ccd6cecc586690d004e1e4661237c3410366423b51e45ad0f01"},"schema_version":"1.0","source":{"id":"2405.18886","kind":"arxiv","version":2}},"canonical_sha256":"e5ba47bd51aa54cabfd677a32886bf8d100a3d4c5a6c8aa796c07fc0ceb2bafe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e5ba47bd51aa54cabfd677a32886bf8d100a3d4c5a6c8aa796c07fc0ceb2bafe","first_computed_at":"2026-07-05T09:30:15.528069Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:30:15.528069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IMBEuBqNQh/Kw9dRQeJqHwi/8AG+6aHw838XCtcznCIkiLG2AOGGIIvb5Hg5B7T+8CZfutjOFahYs03vJiceDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:30:15.528616Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.18886","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:478634b2da51434e4d3e81312e8ca73ce2a91a5b5092793dea8e29a9f27b3632","sha256:65795c679f7770dcea70b94703e6767b8f4ce1d249b3aa54db92f7f31c6e83a1"],"state_sha256":"3d9ef9f588a6dfaab36bb4e89cc67914f98bc424e47367f4f9cea212df7e3de8"}