{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:46JVBM74ZEMMPP7PMFYYP6LMPN","short_pith_number":"pith:46JVBM74","canonical_record":{"source":{"id":"2312.11514","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-12T18:57:08Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e6bf99ac86993acf29ba676c3385ac647f2975d0e550d5369015a9d38d9b8fb0","abstract_canon_sha256":"bb9d88d62cbdf82435c6d4da7319c19524c296e9ddeb5267dd63d44dad8a7734"},"schema_version":"1.0"},"canonical_sha256":"e79350b3fcc918c7bfef617187f96c7b5201c576aa6f362c985d5191acdbd012","source":{"kind":"arxiv","id":"2312.11514","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.11514","created_at":"2026-07-05T08:50:26Z"},{"alias_kind":"arxiv_version","alias_value":"2312.11514v3","created_at":"2026-07-05T08:50:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11514","created_at":"2026-07-05T08:50:26Z"},{"alias_kind":"pith_short_12","alias_value":"46JVBM74ZEMM","created_at":"2026-07-05T08:50:26Z"},{"alias_kind":"pith_short_16","alias_value":"46JVBM74ZEMMPP7P","created_at":"2026-07-05T08:50:26Z"},{"alias_kind":"pith_short_8","alias_value":"46JVBM74","created_at":"2026-07-05T08:50:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:46JVBM74ZEMMPP7PMFYYP6LMPN","target":"record","payload":{"canonical_record":{"source":{"id":"2312.11514","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-12T18:57:08Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e6bf99ac86993acf29ba676c3385ac647f2975d0e550d5369015a9d38d9b8fb0","abstract_canon_sha256":"bb9d88d62cbdf82435c6d4da7319c19524c296e9ddeb5267dd63d44dad8a7734"},"schema_version":"1.0"},"canonical_sha256":"e79350b3fcc918c7bfef617187f96c7b5201c576aa6f362c985d5191acdbd012","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:26.426922Z","signature_b64":"ho1JQWwVjqwcDcLcpAoMEZaGrunj27dx84dmzJAYTYRXssoJiM8uVAEv7TQhbtGuz4asf1CfgMuO7D5qSfIODw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e79350b3fcc918c7bfef617187f96c7b5201c576aa6f362c985d5191acdbd012","last_reissued_at":"2026-07-05T08:50:26.426499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:26.426499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.11514","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:50:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xrWqebMGMIyUIIiOWF6loyh9JWHV7qH+1TFt8bKkCfikj4oj/UIFCyEXugexGDuWolrLflizliFaeK2sZfRUCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:47:55.352163Z"},"content_sha256":"7646ba6ac55e3db1e5ad7d95905fbad42e20f535bb84c17670d7711f1299ca6e","schema_version":"1.0","event_id":"sha256:7646ba6ac55e3db1e5ad7d95905fbad42e20f535bb84c17670d7711f1299ca6e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:46JVBM74ZEMMPP7PMFYYP6LMPN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM in a flash: Efficient Large Language Model Inference with Limited Memory","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Carlo C Del Mundo, Dmitry Belenko, Iman Mirzadeh, Karen Khatamifard, Keivan Alizadeh, Mehrdad Farajtabar, Minsik Cho, Mohammad Rastegari","submitted_at":"2023-12-12T18:57:08Z","abstract_excerpt":"Large language models (LLMs) are central to modern natural language processing, delivering exceptional performance in various tasks. However, their substantial computational and memory requirements present challenges, especially for devices with limited DRAM capacity. This paper tackles the challenge of efficiently running LLMs that exceed the available DRAM capacity by storing the model parameters in flash memory, but bringing them on demand to DRAM. Our method involves constructing an inference cost model that takes into account the characteristics of flash memory, guiding us to optimize in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11514","kind":"arxiv","version":3},"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/2312.11514/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":"2026-07-05T08:50:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v1mNdREAv+MUswzPXH0VbXMoDakkEEE/mWn+mI49dBhE1pIzhaypTKA3nAiZ9LC4D3dD3KmJROxhTIbDB/VTAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:47:55.352545Z"},"content_sha256":"c0ccece61a6f844bd9a9017745ae5e84aeeb68967dcf9e8368af174be5b6231a","schema_version":"1.0","event_id":"sha256:c0ccece61a6f844bd9a9017745ae5e84aeeb68967dcf9e8368af174be5b6231a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/46JVBM74ZEMMPP7PMFYYP6LMPN/bundle.json","state_url":"https://pith.science/pith/46JVBM74ZEMMPP7PMFYYP6LMPN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/46JVBM74ZEMMPP7PMFYYP6LMPN/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":"2026-07-09T02:47:55Z","links":{"resolver":"https://pith.science/pith/46JVBM74ZEMMPP7PMFYYP6LMPN","bundle":"https://pith.science/pith/46JVBM74ZEMMPP7PMFYYP6LMPN/bundle.json","state":"https://pith.science/pith/46JVBM74ZEMMPP7PMFYYP6LMPN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/46JVBM74ZEMMPP7PMFYYP6LMPN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:46JVBM74ZEMMPP7PMFYYP6LMPN","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":"bb9d88d62cbdf82435c6d4da7319c19524c296e9ddeb5267dd63d44dad8a7734","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-12T18:57:08Z","title_canon_sha256":"e6bf99ac86993acf29ba676c3385ac647f2975d0e550d5369015a9d38d9b8fb0"},"schema_version":"1.0","source":{"id":"2312.11514","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.11514","created_at":"2026-07-05T08:50:26Z"},{"alias_kind":"arxiv_version","alias_value":"2312.11514v3","created_at":"2026-07-05T08:50:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11514","created_at":"2026-07-05T08:50:26Z"},{"alias_kind":"pith_short_12","alias_value":"46JVBM74ZEMM","created_at":"2026-07-05T08:50:26Z"},{"alias_kind":"pith_short_16","alias_value":"46JVBM74ZEMMPP7P","created_at":"2026-07-05T08:50:26Z"},{"alias_kind":"pith_short_8","alias_value":"46JVBM74","created_at":"2026-07-05T08:50:26Z"}],"graph_snapshots":[{"event_id":"sha256:c0ccece61a6f844bd9a9017745ae5e84aeeb68967dcf9e8368af174be5b6231a","target":"graph","created_at":"2026-07-05T08:50:26Z","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/2312.11514/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are central to modern natural language processing, delivering exceptional performance in various tasks. However, their substantial computational and memory requirements present challenges, especially for devices with limited DRAM capacity. This paper tackles the challenge of efficiently running LLMs that exceed the available DRAM capacity by storing the model parameters in flash memory, but bringing them on demand to DRAM. Our method involves constructing an inference cost model that takes into account the characteristics of flash memory, guiding us to optimize in ","authors_text":"Carlo C Del Mundo, Dmitry Belenko, Iman Mirzadeh, Karen Khatamifard, Keivan Alizadeh, Mehrdad Farajtabar, Minsik Cho, Mohammad Rastegari","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-12T18:57:08Z","title":"LLM in a flash: Efficient Large Language Model Inference with Limited Memory"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11514","kind":"arxiv","version":3},"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":"sha256:7646ba6ac55e3db1e5ad7d95905fbad42e20f535bb84c17670d7711f1299ca6e","target":"record","created_at":"2026-07-05T08:50:26Z","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":"bb9d88d62cbdf82435c6d4da7319c19524c296e9ddeb5267dd63d44dad8a7734","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-12T18:57:08Z","title_canon_sha256":"e6bf99ac86993acf29ba676c3385ac647f2975d0e550d5369015a9d38d9b8fb0"},"schema_version":"1.0","source":{"id":"2312.11514","kind":"arxiv","version":3}},"canonical_sha256":"e79350b3fcc918c7bfef617187f96c7b5201c576aa6f362c985d5191acdbd012","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e79350b3fcc918c7bfef617187f96c7b5201c576aa6f362c985d5191acdbd012","first_computed_at":"2026-07-05T08:50:26.426499Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:50:26.426499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ho1JQWwVjqwcDcLcpAoMEZaGrunj27dx84dmzJAYTYRXssoJiM8uVAEv7TQhbtGuz4asf1CfgMuO7D5qSfIODw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:50:26.426922Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.11514","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7646ba6ac55e3db1e5ad7d95905fbad42e20f535bb84c17670d7711f1299ca6e","sha256:c0ccece61a6f844bd9a9017745ae5e84aeeb68967dcf9e8368af174be5b6231a"],"state_sha256":"5025bf3bc2870040b857eb4d37239da3063dba1a3ff32d7d1839ba3ea1196747"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I3nqFMtJwPDkrfCASxLr4JEntSgc1rrSBCycg8awANmvZrHFovH1nvhmo6iUA5l04hh3H9B424f4lkn/fzHPAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T02:47:55.354546Z","bundle_sha256":"be3ab66a6cbd7c9180d6df106aab5f4ffa8a4e77c00d5badb8d9570c4954694c"}}