{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QZ7V2MTHY4JJZF5VGQQHAP6ULF","short_pith_number":"pith:QZ7V2MTH","schema_version":"1.0","canonical_sha256":"867f5d3267c7129c97b53420703fd4595dab637199a68d87a6ba825f10d6c031","source":{"kind":"arxiv","id":"2410.01805","version":2},"attestation_state":"computed","paper":{"title":"Locret: Enhancing Eviction in Long-Context LLM Inference with Trained Retaining Heads on Consumer-Grade Devices","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Binhang Yuan, Chaojun Xiao, Xu Han, Yuxiang Huang, Zhiyuan Liu","submitted_at":"2024-10-02T17:59:52Z","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"},"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":"2410.01805","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T17:59:52Z","cross_cats_sorted":[],"title_canon_sha256":"42d3fe9b4c3b09880a1c30d07c0ee069f575519702ce819ae496a98a7ed428f2","abstract_canon_sha256":"0b60b902de83feeaac69205ec1eca7bcee34452679042e9d4ca72e10799e7e94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:07:27.684905Z","signature_b64":"7zhSOCslk7dxnDCWaupXfg88I8Jay3pKCxK2P4xlDec0JVKU4U5PgwzvONYy7D/jn59QfF33Kl10KCrAlfoZCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"867f5d3267c7129c97b53420703fd4595dab637199a68d87a6ba825f10d6c031","last_reissued_at":"2026-07-05T10:07:27.684443Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:07:27.684443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Locret: Enhancing Eviction in Long-Context LLM Inference with Trained Retaining Heads on Consumer-Grade Devices","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Binhang Yuan, Chaojun Xiao, Xu Han, Yuxiang Huang, Zhiyuan Liu","submitted_at":"2024-10-02T17:59:52Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01805","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/2410.01805/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":"2410.01805","created_at":"2026-07-05T10:07:27.684501+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.01805v2","created_at":"2026-07-05T10:07:27.684501+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01805","created_at":"2026-07-05T10:07:27.684501+00:00"},{"alias_kind":"pith_short_12","alias_value":"QZ7V2MTHY4JJ","created_at":"2026-07-05T10:07:27.684501+00:00"},{"alias_kind":"pith_short_16","alias_value":"QZ7V2MTHY4JJZF5V","created_at":"2026-07-05T10:07:27.684501+00:00"},{"alias_kind":"pith_short_8","alias_value":"QZ7V2MTH","created_at":"2026-07-05T10:07:27.684501+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25475","citing_title":"IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM Inference","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QZ7V2MTHY4JJZF5VGQQHAP6ULF","json":"https://pith.science/pith/QZ7V2MTHY4JJZF5VGQQHAP6ULF.json","graph_json":"https://pith.science/api/pith-number/QZ7V2MTHY4JJZF5VGQQHAP6ULF/graph.json","events_json":"https://pith.science/api/pith-number/QZ7V2MTHY4JJZF5VGQQHAP6ULF/events.json","paper":"https://pith.science/paper/QZ7V2MTH"},"agent_actions":{"view_html":"https://pith.science/pith/QZ7V2MTHY4JJZF5VGQQHAP6ULF","download_json":"https://pith.science/pith/QZ7V2MTHY4JJZF5VGQQHAP6ULF.json","view_paper":"https://pith.science/paper/QZ7V2MTH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.01805&json=true","fetch_graph":"https://pith.science/api/pith-number/QZ7V2MTHY4JJZF5VGQQHAP6ULF/graph.json","fetch_events":"https://pith.science/api/pith-number/QZ7V2MTHY4JJZF5VGQQHAP6ULF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QZ7V2MTHY4JJZF5VGQQHAP6ULF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QZ7V2MTHY4JJZF5VGQQHAP6ULF/action/storage_attestation","attest_author":"https://pith.science/pith/QZ7V2MTHY4JJZF5VGQQHAP6ULF/action/author_attestation","sign_citation":"https://pith.science/pith/QZ7V2MTHY4JJZF5VGQQHAP6ULF/action/citation_signature","submit_replication":"https://pith.science/pith/QZ7V2MTHY4JJZF5VGQQHAP6ULF/action/replication_record"}},"created_at":"2026-07-05T10:07:27.684501+00:00","updated_at":"2026-07-05T10:07:27.684501+00:00"}