{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QZ7V2MTHY4JJZF5VGQQHAP6ULF","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":"0b60b902de83feeaac69205ec1eca7bcee34452679042e9d4ca72e10799e7e94","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T17:59:52Z","title_canon_sha256":"42d3fe9b4c3b09880a1c30d07c0ee069f575519702ce819ae496a98a7ed428f2"},"schema_version":"1.0","source":{"id":"2410.01805","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01805","created_at":"2026-07-05T10:07:27Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01805v2","created_at":"2026-07-05T10:07:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01805","created_at":"2026-07-05T10:07:27Z"},{"alias_kind":"pith_short_12","alias_value":"QZ7V2MTHY4JJ","created_at":"2026-07-05T10:07:27Z"},{"alias_kind":"pith_short_16","alias_value":"QZ7V2MTHY4JJZF5V","created_at":"2026-07-05T10:07:27Z"},{"alias_kind":"pith_short_8","alias_value":"QZ7V2MTH","created_at":"2026-07-05T10:07:27Z"}],"graph_snapshots":[{"event_id":"sha256:a71ed548b46e0e6550c2ca6dd8314d0d500ff6d88b6a66dca03aa35f98e752ca","target":"graph","created_at":"2026-07-05T10:07:27Z","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/2410.01805/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scaling the input context length of a large language model (LLM) incurs a significant increase in computation cost and memory footprint to maintain the attention key-value (KV) cache. Existing KV cache compression methods suffer from inefficient compression strategies and limited memory reduction effects, making it difficult for LLMs to conduct long-context inference on consumer-grade devices, especially when inferring long-context stream input. Such obstacles prevent consumer-grade devices from supporting more complex applications, creating challenges for the democratization of LLMs. To overc","authors_text":"Binhang Yuan, Chaojun Xiao, Xu Han, Yuxiang Huang, Zhiyuan Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T17:59:52Z","title":"Locret: Enhancing Eviction in Long-Context LLM Inference with Trained Retaining Heads on Consumer-Grade Devices"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01805","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:b2b7d4c9b09c0ba94c74e449a000db5f0b2ab70d62b2d97844290c05dfe93ce2","target":"record","created_at":"2026-07-05T10:07:27Z","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":"0b60b902de83feeaac69205ec1eca7bcee34452679042e9d4ca72e10799e7e94","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T17:59:52Z","title_canon_sha256":"42d3fe9b4c3b09880a1c30d07c0ee069f575519702ce819ae496a98a7ed428f2"},"schema_version":"1.0","source":{"id":"2410.01805","kind":"arxiv","version":2}},"canonical_sha256":"867f5d3267c7129c97b53420703fd4595dab637199a68d87a6ba825f10d6c031","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"867f5d3267c7129c97b53420703fd4595dab637199a68d87a6ba825f10d6c031","first_computed_at":"2026-07-05T10:07:27.684443Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:07:27.684443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7zhSOCslk7dxnDCWaupXfg88I8Jay3pKCxK2P4xlDec0JVKU4U5PgwzvONYy7D/jn59QfF33Kl10KCrAlfoZCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:07:27.684905Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.01805","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2b7d4c9b09c0ba94c74e449a000db5f0b2ab70d62b2d97844290c05dfe93ce2","sha256:a71ed548b46e0e6550c2ca6dd8314d0d500ff6d88b6a66dca03aa35f98e752ca"],"state_sha256":"96df40f75fa51ea4f1d80cc3f945dde2c5c26850ea648a31a77d5bccdb8ed82c"}