{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SYPGCTTZXWEUPMGRZ42IJPODYY","short_pith_number":"pith:SYPGCTTZ","canonical_record":{"source":{"id":"2410.18517","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-24T08:06:41Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ed53764df283a9d7833e3bb4f767d6f3bb9cb119c266564bcdded11ccc3b6253","abstract_canon_sha256":"0a04e21b442d9560b815f60a8c02c4d03ae9e37a396c13ea1feca09d808d2446"},"schema_version":"1.0"},"canonical_sha256":"961e614e79bd8947b0d1cf3484bdc3c6079a3152bad4b5caf4588a226c8918f8","source":{"kind":"arxiv","id":"2410.18517","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.18517","created_at":"2026-07-05T09:25:09Z"},{"alias_kind":"arxiv_version","alias_value":"2410.18517v1","created_at":"2026-07-05T09:25:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18517","created_at":"2026-07-05T09:25:09Z"},{"alias_kind":"pith_short_12","alias_value":"SYPGCTTZXWEU","created_at":"2026-07-05T09:25:09Z"},{"alias_kind":"pith_short_16","alias_value":"SYPGCTTZXWEUPMGR","created_at":"2026-07-05T09:25:09Z"},{"alias_kind":"pith_short_8","alias_value":"SYPGCTTZ","created_at":"2026-07-05T09:25:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SYPGCTTZXWEUPMGRZ42IJPODYY","target":"record","payload":{"canonical_record":{"source":{"id":"2410.18517","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-24T08:06:41Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ed53764df283a9d7833e3bb4f767d6f3bb9cb119c266564bcdded11ccc3b6253","abstract_canon_sha256":"0a04e21b442d9560b815f60a8c02c4d03ae9e37a396c13ea1feca09d808d2446"},"schema_version":"1.0"},"canonical_sha256":"961e614e79bd8947b0d1cf3484bdc3c6079a3152bad4b5caf4588a226c8918f8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:09.508799Z","signature_b64":"Ax1G/VtB7dPdFA2A70YfTy7W+Sbs2yuFEvelyGDH0LQo5knLE204mIruTamqMjgNpQa0+xrjebq34HehHUbuCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"961e614e79bd8947b0d1cf3484bdc3c6079a3152bad4b5caf4588a226c8918f8","last_reissued_at":"2026-07-05T09:25:09.508246Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:09.508246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.18517","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:25:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ITuiEys7ZNhKJMv7QgJtTqLhswnDFE/dlylLN2U3W2UqD4Qc1k5tnZiSG8hmYPcwd/7ZMXNwsWZ5NddcA9KUBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T22:51:01.143061Z"},"content_sha256":"a99f039a11a584742e43a0323f33b1e2a0bace45246675ac1cfdcb8461fafc3c","schema_version":"1.0","event_id":"sha256:a99f039a11a584742e43a0323f33b1e2a0bace45246675ac1cfdcb8461fafc3c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SYPGCTTZXWEUPMGRZ42IJPODYY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Dongjie Yang, Hai Zhao, Libo Qin, Qiguang Chen, Yifei Yang, Zhi Chen, Zouying Cao","submitted_at":"2024-10-24T08:06:41Z","abstract_excerpt":"The development of large language models (LLMs) has significantly expanded model sizes, resulting in substantial GPU memory requirements during inference. The key and value storage of the attention map in the KV (key-value) cache accounts for more than 80\\% of this memory consumption. Nowadays, most existing KV cache compression methods focus on intra-layer compression within a single Transformer layer but few works consider layer-wise compression. In this paper, we propose a plug-and-play method called \\textit{KVSharer}, which shares the KV cache between layers to achieve layer-wise compressi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18517","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/2410.18517/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":"2026-07-05T09:25:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bmOOCLSc1G9mWQWpn5/tL2N5txNyKInrvIwpt+wqTdsRDxbWLi6H6h9PPtCRaRlTBQ5V0SJlYgpy7Z8I1ZGIBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T22:51:01.143559Z"},"content_sha256":"e4a7d4e1622865e3ea64152bfade2474a149397d2959cdaa8615503df9ec6663","schema_version":"1.0","event_id":"sha256:e4a7d4e1622865e3ea64152bfade2474a149397d2959cdaa8615503df9ec6663"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SYPGCTTZXWEUPMGRZ42IJPODYY/bundle.json","state_url":"https://pith.science/pith/SYPGCTTZXWEUPMGRZ42IJPODYY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SYPGCTTZXWEUPMGRZ42IJPODYY/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":"2026-08-06T22:51:01Z","links":{"resolver":"https://pith.science/pith/SYPGCTTZXWEUPMGRZ42IJPODYY","bundle":"https://pith.science/pith/SYPGCTTZXWEUPMGRZ42IJPODYY/bundle.json","state":"https://pith.science/pith/SYPGCTTZXWEUPMGRZ42IJPODYY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SYPGCTTZXWEUPMGRZ42IJPODYY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SYPGCTTZXWEUPMGRZ42IJPODYY","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":"0a04e21b442d9560b815f60a8c02c4d03ae9e37a396c13ea1feca09d808d2446","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-24T08:06:41Z","title_canon_sha256":"ed53764df283a9d7833e3bb4f767d6f3bb9cb119c266564bcdded11ccc3b6253"},"schema_version":"1.0","source":{"id":"2410.18517","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.18517","created_at":"2026-07-05T09:25:09Z"},{"alias_kind":"arxiv_version","alias_value":"2410.18517v1","created_at":"2026-07-05T09:25:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18517","created_at":"2026-07-05T09:25:09Z"},{"alias_kind":"pith_short_12","alias_value":"SYPGCTTZXWEU","created_at":"2026-07-05T09:25:09Z"},{"alias_kind":"pith_short_16","alias_value":"SYPGCTTZXWEUPMGR","created_at":"2026-07-05T09:25:09Z"},{"alias_kind":"pith_short_8","alias_value":"SYPGCTTZ","created_at":"2026-07-05T09:25:09Z"}],"graph_snapshots":[{"event_id":"sha256:e4a7d4e1622865e3ea64152bfade2474a149397d2959cdaa8615503df9ec6663","target":"graph","created_at":"2026-07-05T09:25:09Z","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/2410.18517/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The development of large language models (LLMs) has significantly expanded model sizes, resulting in substantial GPU memory requirements during inference. The key and value storage of the attention map in the KV (key-value) cache accounts for more than 80\\% of this memory consumption. Nowadays, most existing KV cache compression methods focus on intra-layer compression within a single Transformer layer but few works consider layer-wise compression. In this paper, we propose a plug-and-play method called \\textit{KVSharer}, which shares the KV cache between layers to achieve layer-wise compressi","authors_text":"Dongjie Yang, Hai Zhao, Libo Qin, Qiguang Chen, Yifei Yang, Zhi Chen, Zouying Cao","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-24T08:06:41Z","title":"KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18517","kind":"arxiv","version":1},"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:a99f039a11a584742e43a0323f33b1e2a0bace45246675ac1cfdcb8461fafc3c","target":"record","created_at":"2026-07-05T09:25:09Z","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":"0a04e21b442d9560b815f60a8c02c4d03ae9e37a396c13ea1feca09d808d2446","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-24T08:06:41Z","title_canon_sha256":"ed53764df283a9d7833e3bb4f767d6f3bb9cb119c266564bcdded11ccc3b6253"},"schema_version":"1.0","source":{"id":"2410.18517","kind":"arxiv","version":1}},"canonical_sha256":"961e614e79bd8947b0d1cf3484bdc3c6079a3152bad4b5caf4588a226c8918f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"961e614e79bd8947b0d1cf3484bdc3c6079a3152bad4b5caf4588a226c8918f8","first_computed_at":"2026-07-05T09:25:09.508246Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:25:09.508246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ax1G/VtB7dPdFA2A70YfTy7W+Sbs2yuFEvelyGDH0LQo5knLE204mIruTamqMjgNpQa0+xrjebq34HehHUbuCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:25:09.508799Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.18517","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a99f039a11a584742e43a0323f33b1e2a0bace45246675ac1cfdcb8461fafc3c","sha256:e4a7d4e1622865e3ea64152bfade2474a149397d2959cdaa8615503df9ec6663"],"state_sha256":"3da58772071145eb3f5302c86f0b33ca8538298c9abaf655f8414e9a9c9f76cb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gy/t9tzNDLNHpXgqGFjFAmdHfxPe0Oj3oimNJxMcyfbw09+brFT4+Ta7wHqibeTLeSBJnhDN3xn9plhnSokSAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T22:51:01.147336Z","bundle_sha256":"e765900eda8523463983187a4ae1bba0770cbee2c3ecde2273ac030228fda0b0"}}