{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BFJLOAP54USTGBFE2FWPBJSMLD","short_pith_number":"pith:BFJLOAP5","canonical_record":{"source":{"id":"2407.21118","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-30T18:19:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"76a1374c7de699cc9c1887c9c00ee66aaa96826201b59d4fba9be4e0c3fb6bc3","abstract_canon_sha256":"70b07c65f43d88a06f5dc469a1fe41ee99dd354264195866245f6f987557d31b"},"schema_version":"1.0"},"canonical_sha256":"0952b701fde5253304a4d16cf0a64c58c63f4a61608d5a1fb81b670ec53b0d2e","source":{"kind":"arxiv","id":"2407.21118","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.21118","created_at":"2026-07-05T09:30:19Z"},{"alias_kind":"arxiv_version","alias_value":"2407.21118v2","created_at":"2026-07-05T09:30:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21118","created_at":"2026-07-05T09:30:19Z"},{"alias_kind":"pith_short_12","alias_value":"BFJLOAP54UST","created_at":"2026-07-05T09:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"BFJLOAP54USTGBFE","created_at":"2026-07-05T09:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"BFJLOAP5","created_at":"2026-07-05T09:30:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BFJLOAP54USTGBFE2FWPBJSMLD","target":"record","payload":{"canonical_record":{"source":{"id":"2407.21118","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-30T18:19:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"76a1374c7de699cc9c1887c9c00ee66aaa96826201b59d4fba9be4e0c3fb6bc3","abstract_canon_sha256":"70b07c65f43d88a06f5dc469a1fe41ee99dd354264195866245f6f987557d31b"},"schema_version":"1.0"},"canonical_sha256":"0952b701fde5253304a4d16cf0a64c58c63f4a61608d5a1fb81b670ec53b0d2e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:19.636354Z","signature_b64":"QfP+ewPDpkO3IMgcvtEE8SwIkJ1wO+ZJLWeYEnZjEKsxe+vF2qtxSlooX3hQ3mMMMH/QTs8jKKLP/djFazxBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0952b701fde5253304a4d16cf0a64c58c63f4a61608d5a1fb81b670ec53b0d2e","last_reissued_at":"2026-07-05T09:30:19.635801Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:19.635801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.21118","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:30:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7xHDsNf9L9qyuvaIq+XRNHJ99lt7lq/rPSMhwzhBkyLjcRU0lwR8W4uY3hNesSzP6yGmI0kslTs5hlo86r4iCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:40:31.240818Z"},"content_sha256":"6c5b3dfb6fa05f9931263fcb4297ae200b2190ee2d6d10c0a627f9d0e1e08ef5","schema_version":"1.0","event_id":"sha256:6c5b3dfb6fa05f9931263fcb4297ae200b2190ee2d6d10c0a627f9d0e1e08ef5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BFJLOAP54USTGBFE2FWPBJSMLD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Palu: Compressing KV-Cache with Low-Rank Projection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Chi-Chih Chang, Chien-Yu Lin, Chong-Yan Chen, Kai-Chiang Wu, Luis Ceze, Mohamed S. Abdelfattah, Ning-Chi Huang, Pei-Shuo Wang, Wei-Cheng Lin, Yu-Fang Hu","submitted_at":"2024-07-30T18:19:38Z","abstract_excerpt":"Post-training KV-Cache compression methods typically either sample a subset of effectual tokens or quantize the data into lower numerical bit width. However, these methods cannot exploit redundancy in the hidden dimension of the KV tensors. This paper presents a hidden dimension compression approach called Palu, a KV-Cache compression framework that utilizes low-rank projection to reduce inference-time LLM memory usage. Palu decomposes the linear layers into low-rank matrices, caches compressed intermediate states, and reconstructs the full keys and values on the fly. To improve accuracy, comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21118","kind":"arxiv","version":2},"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/2407.21118/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:30:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZuF7PhSnLBiSASzPdyp9tmbnL3Qv5DbXPERySM8Hlc7XQ2sXNDB7rBg2peJDSmBw2F9r2cw7U/buEly3nXptAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:40:31.241191Z"},"content_sha256":"b73b8551adad6eb7cf4144b7d0a739edd9a25e3556bdfdaa7d6194c28e1038c8","schema_version":"1.0","event_id":"sha256:b73b8551adad6eb7cf4144b7d0a739edd9a25e3556bdfdaa7d6194c28e1038c8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BFJLOAP54USTGBFE2FWPBJSMLD/bundle.json","state_url":"https://pith.science/pith/BFJLOAP54USTGBFE2FWPBJSMLD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BFJLOAP54USTGBFE2FWPBJSMLD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T20:40:31Z","links":{"resolver":"https://pith.science/pith/BFJLOAP54USTGBFE2FWPBJSMLD","bundle":"https://pith.science/pith/BFJLOAP54USTGBFE2FWPBJSMLD/bundle.json","state":"https://pith.science/pith/BFJLOAP54USTGBFE2FWPBJSMLD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BFJLOAP54USTGBFE2FWPBJSMLD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BFJLOAP54USTGBFE2FWPBJSMLD","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":"70b07c65f43d88a06f5dc469a1fe41ee99dd354264195866245f6f987557d31b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-30T18:19:38Z","title_canon_sha256":"76a1374c7de699cc9c1887c9c00ee66aaa96826201b59d4fba9be4e0c3fb6bc3"},"schema_version":"1.0","source":{"id":"2407.21118","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.21118","created_at":"2026-07-05T09:30:19Z"},{"alias_kind":"arxiv_version","alias_value":"2407.21118v2","created_at":"2026-07-05T09:30:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21118","created_at":"2026-07-05T09:30:19Z"},{"alias_kind":"pith_short_12","alias_value":"BFJLOAP54UST","created_at":"2026-07-05T09:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"BFJLOAP54USTGBFE","created_at":"2026-07-05T09:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"BFJLOAP5","created_at":"2026-07-05T09:30:19Z"}],"graph_snapshots":[{"event_id":"sha256:b73b8551adad6eb7cf4144b7d0a739edd9a25e3556bdfdaa7d6194c28e1038c8","target":"graph","created_at":"2026-07-05T09:30:19Z","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/2407.21118/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Post-training KV-Cache compression methods typically either sample a subset of effectual tokens or quantize the data into lower numerical bit width. However, these methods cannot exploit redundancy in the hidden dimension of the KV tensors. This paper presents a hidden dimension compression approach called Palu, a KV-Cache compression framework that utilizes low-rank projection to reduce inference-time LLM memory usage. Palu decomposes the linear layers into low-rank matrices, caches compressed intermediate states, and reconstructs the full keys and values on the fly. To improve accuracy, comp","authors_text":"Chi-Chih Chang, Chien-Yu Lin, Chong-Yan Chen, Kai-Chiang Wu, Luis Ceze, Mohamed S. Abdelfattah, Ning-Chi Huang, Pei-Shuo Wang, Wei-Cheng Lin, Yu-Fang Hu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-30T18:19:38Z","title":"Palu: Compressing KV-Cache with Low-Rank Projection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21118","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":"sha256:6c5b3dfb6fa05f9931263fcb4297ae200b2190ee2d6d10c0a627f9d0e1e08ef5","target":"record","created_at":"2026-07-05T09:30:19Z","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":"70b07c65f43d88a06f5dc469a1fe41ee99dd354264195866245f6f987557d31b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-30T18:19:38Z","title_canon_sha256":"76a1374c7de699cc9c1887c9c00ee66aaa96826201b59d4fba9be4e0c3fb6bc3"},"schema_version":"1.0","source":{"id":"2407.21118","kind":"arxiv","version":2}},"canonical_sha256":"0952b701fde5253304a4d16cf0a64c58c63f4a61608d5a1fb81b670ec53b0d2e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0952b701fde5253304a4d16cf0a64c58c63f4a61608d5a1fb81b670ec53b0d2e","first_computed_at":"2026-07-05T09:30:19.635801Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:30:19.635801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QfP+ewPDpkO3IMgcvtEE8SwIkJ1wO+ZJLWeYEnZjEKsxe+vF2qtxSlooX3hQ3mMMMH/QTs8jKKLP/djFazxBDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:30:19.636354Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.21118","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c5b3dfb6fa05f9931263fcb4297ae200b2190ee2d6d10c0a627f9d0e1e08ef5","sha256:b73b8551adad6eb7cf4144b7d0a739edd9a25e3556bdfdaa7d6194c28e1038c8"],"state_sha256":"3268553183eebcf1ce96a1c7508a0964f8dd70fef7d37dda9f02b6fe1d8c77e6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BkpvDL/3W6JR3x8zIz++qkj5ziafhrcR950a23Ok6RXhRd0I/iu4IuGKGtrqIBSDPWqWL1klJtDTRKzkU2/9Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:40:31.243157Z","bundle_sha256":"18113db8732897a961cac6dfa82dd86ae5e0e5ec444e1541d224b578d656a1dc"}}