{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QZ7V2MTHY4JJZF5VGQQHAP6ULF","short_pith_number":"pith:QZ7V2MTH","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"},"canonical_sha256":"867f5d3267c7129c97b53420703fd4595dab637199a68d87a6ba825f10d6c031","source":{"kind":"arxiv","id":"2410.01805","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QZ7V2MTHY4JJZF5VGQQHAP6ULF","target":"record","payload":{"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"},"canonical_sha256":"867f5d3267c7129c97b53420703fd4595dab637199a68d87a6ba825f10d6c031","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"},"source_kind":"arxiv","source_id":"2410.01805","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":"2026-07-05T10:07:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NlUMudEDKgJnbhwMB4YNvuLWFyzCfNcbFfL6xznty7FlDDWd3BBXzgC0xm8nMCM/86iCt2zZC4qOjaj1v7WoDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:31:27.011023Z"},"content_sha256":"b2b7d4c9b09c0ba94c74e449a000db5f0b2ab70d62b2d97844290c05dfe93ce2","schema_version":"1.0","event_id":"sha256:b2b7d4c9b09c0ba94c74e449a000db5f0b2ab70d62b2d97844290c05dfe93ce2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QZ7V2MTHY4JJZF5VGQQHAP6ULF","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:07:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g209HfOlqFvnIT35vyJcsObIlNuy3PM4k6FjN2oGRDvfGpompMRIi15vgbjjYdk0TSd4RhSQjhNsmBWJy3S7BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:31:27.011552Z"},"content_sha256":"a71ed548b46e0e6550c2ca6dd8314d0d500ff6d88b6a66dca03aa35f98e752ca","schema_version":"1.0","event_id":"sha256:a71ed548b46e0e6550c2ca6dd8314d0d500ff6d88b6a66dca03aa35f98e752ca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QZ7V2MTHY4JJZF5VGQQHAP6ULF/bundle.json","state_url":"https://pith.science/pith/QZ7V2MTHY4JJZF5VGQQHAP6ULF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QZ7V2MTHY4JJZF5VGQQHAP6ULF/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":"2026-08-08T12:31:27Z","links":{"resolver":"https://pith.science/pith/QZ7V2MTHY4JJZF5VGQQHAP6ULF","bundle":"https://pith.science/pith/QZ7V2MTHY4JJZF5VGQQHAP6ULF/bundle.json","state":"https://pith.science/pith/QZ7V2MTHY4JJZF5VGQQHAP6ULF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QZ7V2MTHY4JJZF5VGQQHAP6ULF/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I9T66p8mBdeUrYrkUj8fQEWYTF+CceTDY+sHxKxWn5apbvKhObf8UFwtLjS/cerPdbxc4wCt6m23pnUMa7GNAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:31:27.016393Z","bundle_sha256":"e343cec4f813c2e94d1afb275230efabe662420c030d2178a777cad8a5dcbd06"}}