{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BM7B6KJSRKUMD6ZKRTLDOGXV7W","short_pith_number":"pith:BM7B6KJS","schema_version":"1.0","canonical_sha256":"0b3e1f29328aa8c1fb2a8cd6371af5fdad948983ec32af5f410902aa28e165c4","source":{"kind":"arxiv","id":"2501.14733","version":1},"attestation_state":"computed","paper":{"title":"LLM as HPC Expert: Extending RAG Architecture for HPC Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DC","authors_text":"Johan Barth\\'elemy, Patrick Kin Man Tung, Yusuke Miyashita","submitted_at":"2024-12-09T02:55:30Z","abstract_excerpt":"High-Performance Computing (HPC) is crucial for performing advanced computational tasks, yet their complexity often challenges users, particularly those unfamiliar with HPC-specific commands and workflows. This paper introduces Hypothetical Command Embeddings (HyCE), a novel method that extends Retrieval-Augmented Generation (RAG) by integrating real-time, user-specific HPC data, enhancing accessibility to these systems. HyCE enriches large language models (LLM) with real-time, user-specific HPC information, addressing the limitations of fine-tuned models on such data. We evaluate HyCE using a"},"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":"2501.14733","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-12-09T02:55:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ac03962a88d0ba6f3e19a40fdf891a4684cb3ef2ce07938281a2a5543f6d17be","abstract_canon_sha256":"2e577cc7337057b3471e027f7b11c17d9726599171e38111a2ed50c6328cff24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:17.341131Z","signature_b64":"bYV4f7sYdMR4G1Wl0EVl78A8xAVFzXDz7eKxpFcgk4x0nigKu8zsklBgJb5t7nmjP+0ELO2iEZ66MrByqDHEBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b3e1f29328aa8c1fb2a8cd6371af5fdad948983ec32af5f410902aa28e165c4","last_reissued_at":"2026-07-05T10:05:17.340552Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:17.340552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM as HPC Expert: Extending RAG Architecture for HPC Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DC","authors_text":"Johan Barth\\'elemy, Patrick Kin Man Tung, Yusuke Miyashita","submitted_at":"2024-12-09T02:55:30Z","abstract_excerpt":"High-Performance Computing (HPC) is crucial for performing advanced computational tasks, yet their complexity often challenges users, particularly those unfamiliar with HPC-specific commands and workflows. This paper introduces Hypothetical Command Embeddings (HyCE), a novel method that extends Retrieval-Augmented Generation (RAG) by integrating real-time, user-specific HPC data, enhancing accessibility to these systems. HyCE enriches large language models (LLM) with real-time, user-specific HPC information, addressing the limitations of fine-tuned models on such data. We evaluate HyCE using a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14733","kind":"arxiv","version":1},"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/2501.14733/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":"2501.14733","created_at":"2026-07-05T10:05:17.340620+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.14733v1","created_at":"2026-07-05T10:05:17.340620+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14733","created_at":"2026-07-05T10:05:17.340620+00:00"},{"alias_kind":"pith_short_12","alias_value":"BM7B6KJSRKUM","created_at":"2026-07-05T10:05:17.340620+00:00"},{"alias_kind":"pith_short_16","alias_value":"BM7B6KJSRKUMD6ZK","created_at":"2026-07-05T10:05:17.340620+00:00"},{"alias_kind":"pith_short_8","alias_value":"BM7B6KJS","created_at":"2026-07-05T10:05:17.340620+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16347","citing_title":"HPC-LLM: Practical Domain Adaptation and Retrieval-Augmented Generation for HPC Support","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BM7B6KJSRKUMD6ZKRTLDOGXV7W","json":"https://pith.science/pith/BM7B6KJSRKUMD6ZKRTLDOGXV7W.json","graph_json":"https://pith.science/api/pith-number/BM7B6KJSRKUMD6ZKRTLDOGXV7W/graph.json","events_json":"https://pith.science/api/pith-number/BM7B6KJSRKUMD6ZKRTLDOGXV7W/events.json","paper":"https://pith.science/paper/BM7B6KJS"},"agent_actions":{"view_html":"https://pith.science/pith/BM7B6KJSRKUMD6ZKRTLDOGXV7W","download_json":"https://pith.science/pith/BM7B6KJSRKUMD6ZKRTLDOGXV7W.json","view_paper":"https://pith.science/paper/BM7B6KJS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.14733&json=true","fetch_graph":"https://pith.science/api/pith-number/BM7B6KJSRKUMD6ZKRTLDOGXV7W/graph.json","fetch_events":"https://pith.science/api/pith-number/BM7B6KJSRKUMD6ZKRTLDOGXV7W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BM7B6KJSRKUMD6ZKRTLDOGXV7W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BM7B6KJSRKUMD6ZKRTLDOGXV7W/action/storage_attestation","attest_author":"https://pith.science/pith/BM7B6KJSRKUMD6ZKRTLDOGXV7W/action/author_attestation","sign_citation":"https://pith.science/pith/BM7B6KJSRKUMD6ZKRTLDOGXV7W/action/citation_signature","submit_replication":"https://pith.science/pith/BM7B6KJSRKUMD6ZKRTLDOGXV7W/action/replication_record"}},"created_at":"2026-07-05T10:05:17.340620+00:00","updated_at":"2026-07-05T10:05:17.340620+00:00"}