{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:D7BYA3RY6S4WM7ERD42TO76WQM","short_pith_number":"pith:D7BYA3RY","schema_version":"1.0","canonical_sha256":"1fc3806e38f4b9667c911f35377fd683308d87ee2f47207e4341381270544d80","source":{"kind":"arxiv","id":"2401.16445","version":3},"attestation_state":"computed","paper":{"title":"OMPGPT: A Generative Pre-trained Transformer Model for OpenMP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","cs.LG"],"primary_cat":"cs.SE","authors_text":"Ali Jannesari, Arijit Bhattacharjee, Gal Oren, Le Chen, Nesreen Ahmed, Niranjan Hasabnis, Vy Vo","submitted_at":"2024-01-28T06:06:59Z","abstract_excerpt":"Large language models (LLMs)such as ChatGPT have significantly advanced the field of Natural Language Processing (NLP). This trend led to the development of code-based large language models such as StarCoder, WizardCoder, and CodeLlama, which are trained extensively on vast repositories of code and programming languages. While the generic abilities of these code LLMs are useful for many programmers in tasks like code generation, the area of high-performance computing (HPC) has a narrower set of requirements that make a smaller and more domain-specific model a smarter choice. This paper present"},"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":"2401.16445","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-01-28T06:06:59Z","cross_cats_sorted":["cs.DC","cs.LG"],"title_canon_sha256":"dd3a7e1522ef41276fe027a43f32f34de6bb52665eeb5f2c6ac815e1d7abf031","abstract_canon_sha256":"ec8a573686fa11aa32a80ebaaddc4e6464a4b4a53f246ef66cf1fadc1a606a81"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:32:05.363906Z","signature_b64":"0Y5QcyXjkryDBqN71tTQNEbXmySKKcNFlyDIZ6So/YPq280CkkOk0qWv2UxUOThKCl72ilhZ2HmhOtqbRsf/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1fc3806e38f4b9667c911f35377fd683308d87ee2f47207e4341381270544d80","last_reissued_at":"2026-07-05T09:32:05.363422Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:32:05.363422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OMPGPT: A Generative Pre-trained Transformer Model for OpenMP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","cs.LG"],"primary_cat":"cs.SE","authors_text":"Ali Jannesari, Arijit Bhattacharjee, Gal Oren, Le Chen, Nesreen Ahmed, Niranjan Hasabnis, Vy Vo","submitted_at":"2024-01-28T06:06:59Z","abstract_excerpt":"Large language models (LLMs)such as ChatGPT have significantly advanced the field of Natural Language Processing (NLP). This trend led to the development of code-based large language models such as StarCoder, WizardCoder, and CodeLlama, which are trained extensively on vast repositories of code and programming languages. While the generic abilities of these code LLMs are useful for many programmers in tasks like code generation, the area of high-performance computing (HPC) has a narrower set of requirements that make a smaller and more domain-specific model a smarter choice. This paper present"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.16445","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/2401.16445/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":"2401.16445","created_at":"2026-07-05T09:32:05.363480+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.16445v3","created_at":"2026-07-05T09:32:05.363480+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.16445","created_at":"2026-07-05T09:32:05.363480+00:00"},{"alias_kind":"pith_short_12","alias_value":"D7BYA3RY6S4W","created_at":"2026-07-05T09:32:05.363480+00:00"},{"alias_kind":"pith_short_16","alias_value":"D7BYA3RY6S4WM7ER","created_at":"2026-07-05T09:32:05.363480+00:00"},{"alias_kind":"pith_short_8","alias_value":"D7BYA3RY","created_at":"2026-07-05T09:32:05.363480+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00883","citing_title":"Accelerating Latency-Critical Applications with AI-Powered Semi-Automatic Fine-Grained Parallelization on SMT Processors","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D7BYA3RY6S4WM7ERD42TO76WQM","json":"https://pith.science/pith/D7BYA3RY6S4WM7ERD42TO76WQM.json","graph_json":"https://pith.science/api/pith-number/D7BYA3RY6S4WM7ERD42TO76WQM/graph.json","events_json":"https://pith.science/api/pith-number/D7BYA3RY6S4WM7ERD42TO76WQM/events.json","paper":"https://pith.science/paper/D7BYA3RY"},"agent_actions":{"view_html":"https://pith.science/pith/D7BYA3RY6S4WM7ERD42TO76WQM","download_json":"https://pith.science/pith/D7BYA3RY6S4WM7ERD42TO76WQM.json","view_paper":"https://pith.science/paper/D7BYA3RY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.16445&json=true","fetch_graph":"https://pith.science/api/pith-number/D7BYA3RY6S4WM7ERD42TO76WQM/graph.json","fetch_events":"https://pith.science/api/pith-number/D7BYA3RY6S4WM7ERD42TO76WQM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D7BYA3RY6S4WM7ERD42TO76WQM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D7BYA3RY6S4WM7ERD42TO76WQM/action/storage_attestation","attest_author":"https://pith.science/pith/D7BYA3RY6S4WM7ERD42TO76WQM/action/author_attestation","sign_citation":"https://pith.science/pith/D7BYA3RY6S4WM7ERD42TO76WQM/action/citation_signature","submit_replication":"https://pith.science/pith/D7BYA3RY6S4WM7ERD42TO76WQM/action/replication_record"}},"created_at":"2026-07-05T09:32:05.363480+00:00","updated_at":"2026-07-05T09:32:05.363480+00:00"}