{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:55LXYXN7BC4DD7G72O3JA54G2K","short_pith_number":"pith:55LXYXN7","schema_version":"1.0","canonical_sha256":"ef577c5dbf08b831fcdfd3b6907786d2acbc5e39eadcbe7a8fc419279414ea97","source":{"kind":"arxiv","id":"2502.07578","version":3},"attestation_state":"computed","paper":{"title":"PIM Is All You Need: A CXL-Enabled GPU-Free System for Large Language Model Inference","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Alireza Khadem, Ning Liang, Onur Mutlu, Ravi Iyer, Reetuparna Das, Sumanth Umesh, Xavier Servot, Yufeng Gu","submitted_at":"2025-02-11T14:25:20Z","abstract_excerpt":"Large Language Model (LLM) inference uses an autoregressive manner to generate one token at a time, which exhibits notably lower operational intensity compared to earlier Machine Learning (ML) models such as encoder-only transformers and Convolutional Neural Networks. At the same time, LLMs possess large parameter sizes and use key-value caches to store context information. Modern LLMs support context windows with up to 1 million tokens to generate versatile text, audio, and video content. A large key-value cache unique to each prompt requires a large memory capacity, limiting the inference ba"},"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":"2502.07578","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AR","submitted_at":"2025-02-11T14:25:20Z","cross_cats_sorted":[],"title_canon_sha256":"80eeee482982fda2217df5949d5a8fda038ac2a8780c63c1bee6cedd923e7d5d","abstract_canon_sha256":"72cd0cf14a737ef1fd7a9fcbd9923a4fd30ef6cab2149406e38edb7a300b5470"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:55.822277Z","signature_b64":"Gj08hniHu0Tb70KeONBBskct539GzZUKBmOmN4OB1nUfZZfjwQgqfHnKr4JM9sW1sRvadZ53hu8A9xWOe3+BDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef577c5dbf08b831fcdfd3b6907786d2acbc5e39eadcbe7a8fc419279414ea97","last_reissued_at":"2026-07-05T10:57:55.821745Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:55.821745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PIM Is All You Need: A CXL-Enabled GPU-Free System for Large Language Model Inference","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Alireza Khadem, Ning Liang, Onur Mutlu, Ravi Iyer, Reetuparna Das, Sumanth Umesh, Xavier Servot, Yufeng Gu","submitted_at":"2025-02-11T14:25:20Z","abstract_excerpt":"Large Language Model (LLM) inference uses an autoregressive manner to generate one token at a time, which exhibits notably lower operational intensity compared to earlier Machine Learning (ML) models such as encoder-only transformers and Convolutional Neural Networks. At the same time, LLMs possess large parameter sizes and use key-value caches to store context information. Modern LLMs support context windows with up to 1 million tokens to generate versatile text, audio, and video content. A large key-value cache unique to each prompt requires a large memory capacity, limiting the inference ba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07578","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/2502.07578/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":"2502.07578","created_at":"2026-07-05T10:57:55.821812+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.07578v3","created_at":"2026-07-05T10:57:55.821812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07578","created_at":"2026-07-05T10:57:55.821812+00:00"},{"alias_kind":"pith_short_12","alias_value":"55LXYXN7BC4D","created_at":"2026-07-05T10:57:55.821812+00:00"},{"alias_kind":"pith_short_16","alias_value":"55LXYXN7BC4DD7G7","created_at":"2026-07-05T10:57:55.821812+00:00"},{"alias_kind":"pith_short_8","alias_value":"55LXYXN7","created_at":"2026-07-05T10:57:55.821812+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/55LXYXN7BC4DD7G72O3JA54G2K","json":"https://pith.science/pith/55LXYXN7BC4DD7G72O3JA54G2K.json","graph_json":"https://pith.science/api/pith-number/55LXYXN7BC4DD7G72O3JA54G2K/graph.json","events_json":"https://pith.science/api/pith-number/55LXYXN7BC4DD7G72O3JA54G2K/events.json","paper":"https://pith.science/paper/55LXYXN7"},"agent_actions":{"view_html":"https://pith.science/pith/55LXYXN7BC4DD7G72O3JA54G2K","download_json":"https://pith.science/pith/55LXYXN7BC4DD7G72O3JA54G2K.json","view_paper":"https://pith.science/paper/55LXYXN7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.07578&json=true","fetch_graph":"https://pith.science/api/pith-number/55LXYXN7BC4DD7G72O3JA54G2K/graph.json","fetch_events":"https://pith.science/api/pith-number/55LXYXN7BC4DD7G72O3JA54G2K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/55LXYXN7BC4DD7G72O3JA54G2K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/55LXYXN7BC4DD7G72O3JA54G2K/action/storage_attestation","attest_author":"https://pith.science/pith/55LXYXN7BC4DD7G72O3JA54G2K/action/author_attestation","sign_citation":"https://pith.science/pith/55LXYXN7BC4DD7G72O3JA54G2K/action/citation_signature","submit_replication":"https://pith.science/pith/55LXYXN7BC4DD7G72O3JA54G2K/action/replication_record"}},"created_at":"2026-07-05T10:57:55.821812+00:00","updated_at":"2026-07-05T10:57:55.821812+00:00"}