{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WVB23FYORAZOABQYBGPFXNNSSW","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":"3b6156659dd838c13099565742c731ef53c29cca71edb5d9369cc609e7c51f97","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.OS","submitted_at":"2025-03-04T20:08:03Z","title_canon_sha256":"c793121406c141caba09be0e39d859569fd940dae76640dd4b4b2135726eb3b8"},"schema_version":"1.0","source":{"id":"2503.03777","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.03777","created_at":"2026-07-05T10:25:20Z"},{"alias_kind":"arxiv_version","alias_value":"2503.03777v1","created_at":"2026-07-05T10:25:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.03777","created_at":"2026-07-05T10:25:20Z"},{"alias_kind":"pith_short_12","alias_value":"WVB23FYORAZO","created_at":"2026-07-05T10:25:20Z"},{"alias_kind":"pith_short_16","alias_value":"WVB23FYORAZOABQY","created_at":"2026-07-05T10:25:20Z"},{"alias_kind":"pith_short_8","alias_value":"WVB23FYO","created_at":"2026-07-05T10:25:20Z"}],"graph_snapshots":[{"event_id":"sha256:f3293445c6236e5b1bbdef01943580de7cd11afa186b3e68c0ae3e3778de0365","target":"graph","created_at":"2026-07-05T10:25:20Z","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/2503.03777/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) face challenges for on-device inference due to high memory demands. Traditional methods to reduce memory usage often compromise performance and lack adaptability. We propose FlexInfer, an optimized offloading framework for on-device inference, addressing these issues with techniques like asynchronous prefetching, balanced memory locking, and flexible tensor preservation. These strategies enhance memory efficiency and mitigate I/O bottlenecks, ensuring high performance within user-specified resource constraints. Experiments demonstrate that FlexInfer significantly i","authors_text":"Arina Kharlamova, Chun Jason Xue, Hongchao Du, Nan Guan, Shangyu Wu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.OS","submitted_at":"2025-03-04T20:08:03Z","title":"FlexInfer: Breaking Memory Constraint via Flexible and Efficient Offloading for On-Device LLM Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.03777","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":"sha256:0fdf67b79e1933aaa0f2a06c4c6dd41f82b0dab81bc310ef09ffdd09b8d681b3","target":"record","created_at":"2026-07-05T10:25:20Z","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":"3b6156659dd838c13099565742c731ef53c29cca71edb5d9369cc609e7c51f97","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.OS","submitted_at":"2025-03-04T20:08:03Z","title_canon_sha256":"c793121406c141caba09be0e39d859569fd940dae76640dd4b4b2135726eb3b8"},"schema_version":"1.0","source":{"id":"2503.03777","kind":"arxiv","version":1}},"canonical_sha256":"b543ad970e8832e00618099e5bb5b29584ae3f120023aa09dcdf3f40754707b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b543ad970e8832e00618099e5bb5b29584ae3f120023aa09dcdf3f40754707b6","first_computed_at":"2026-07-05T10:25:20.938334Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:25:20.938334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"heKD8cfjJh81m7QXLzX/3hsnRt2r4+V4/VzezMY3rJRnUjOUS6vuFF7RmJWyHUmFZJinKfGO3Ie8u9Za6T/ZDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:25:20.938906Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.03777","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0fdf67b79e1933aaa0f2a06c4c6dd41f82b0dab81bc310ef09ffdd09b8d681b3","sha256:f3293445c6236e5b1bbdef01943580de7cd11afa186b3e68c0ae3e3778de0365"],"state_sha256":"9bbe1c2d9d16ca935976e73c42530553aabb13dec7c471876eb0f732d3a37402"}