{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JE7SWHCBVYPH2TPFQRX6VTU2FD","short_pith_number":"pith:JE7SWHCB","schema_version":"1.0","canonical_sha256":"493f2b1c41ae1e7d4de5846feace9a28f2c723165e0f24a9f07eb8022ffe42cd","source":{"kind":"arxiv","id":"2312.13322","version":3},"attestation_state":"computed","paper":{"title":"MonoCoder: Domain-Specific Code Language Model for HPC Codes and Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SE"],"primary_cat":"cs.PL","authors_text":"Abdul Wasay, Gal Oren, Guy Tamir, Mihai Capota, Nadav Schneider, Nesreen Ahmed, Neva Krien, Niranjan Hasabnis, Tal Kadosh, Ted Willke, Timothy Mattson, Vy A. Vo, Yuval Pinter","submitted_at":"2023-12-20T15:11:06Z","abstract_excerpt":"With easier access to powerful compute resources, there is a growing trend in AI for software development to develop large language models (LLMs) to address a variety of programming tasks. Even LLMs applied to tasks from the high-performance computing (HPC) domain are huge in size and demand expensive compute resources for training. This is partly because LLMs for HPC tasks are obtained by finetuning existing LLMs that support several natural and/or programming languages. We found this design choice confusing - why do we need LLMs trained on natural languages and programming languages unrelate"},"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":"2312.13322","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.PL","submitted_at":"2023-12-20T15:11:06Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SE"],"title_canon_sha256":"ce45af9bbb74eb1759184e2ff965817696cdcb291b6b130feb3a4f843761743e","abstract_canon_sha256":"4d7c81c29b53ee6a797c9c1b145e5cfffb07661a85e88b5e037b5384d85707b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:18.952516Z","signature_b64":"1qziMc+daS76Pw3RQEGszI1bYJujaMhuGg3KXnrRQ26aV4bxeCCo3oB4C8IscSeu6lcCaWwm5y/h00iwm/4WAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"493f2b1c41ae1e7d4de5846feace9a28f2c723165e0f24a9f07eb8022ffe42cd","last_reissued_at":"2026-07-05T09:09:18.952092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:18.952092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MonoCoder: Domain-Specific Code Language Model for HPC Codes and Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SE"],"primary_cat":"cs.PL","authors_text":"Abdul Wasay, Gal Oren, Guy Tamir, Mihai Capota, Nadav Schneider, Nesreen Ahmed, Neva Krien, Niranjan Hasabnis, Tal Kadosh, Ted Willke, Timothy Mattson, Vy A. Vo, Yuval Pinter","submitted_at":"2023-12-20T15:11:06Z","abstract_excerpt":"With easier access to powerful compute resources, there is a growing trend in AI for software development to develop large language models (LLMs) to address a variety of programming tasks. Even LLMs applied to tasks from the high-performance computing (HPC) domain are huge in size and demand expensive compute resources for training. This is partly because LLMs for HPC tasks are obtained by finetuning existing LLMs that support several natural and/or programming languages. We found this design choice confusing - why do we need LLMs trained on natural languages and programming languages unrelate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.13322","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/2312.13322/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":"2312.13322","created_at":"2026-07-05T09:09:18.952148+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.13322v3","created_at":"2026-07-05T09:09:18.952148+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.13322","created_at":"2026-07-05T09:09:18.952148+00:00"},{"alias_kind":"pith_short_12","alias_value":"JE7SWHCBVYPH","created_at":"2026-07-05T09:09:18.952148+00:00"},{"alias_kind":"pith_short_16","alias_value":"JE7SWHCBVYPH2TPF","created_at":"2026-07-05T09:09:18.952148+00:00"},{"alias_kind":"pith_short_8","alias_value":"JE7SWHCB","created_at":"2026-07-05T09:09:18.952148+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/JE7SWHCBVYPH2TPFQRX6VTU2FD","json":"https://pith.science/pith/JE7SWHCBVYPH2TPFQRX6VTU2FD.json","graph_json":"https://pith.science/api/pith-number/JE7SWHCBVYPH2TPFQRX6VTU2FD/graph.json","events_json":"https://pith.science/api/pith-number/JE7SWHCBVYPH2TPFQRX6VTU2FD/events.json","paper":"https://pith.science/paper/JE7SWHCB"},"agent_actions":{"view_html":"https://pith.science/pith/JE7SWHCBVYPH2TPFQRX6VTU2FD","download_json":"https://pith.science/pith/JE7SWHCBVYPH2TPFQRX6VTU2FD.json","view_paper":"https://pith.science/paper/JE7SWHCB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.13322&json=true","fetch_graph":"https://pith.science/api/pith-number/JE7SWHCBVYPH2TPFQRX6VTU2FD/graph.json","fetch_events":"https://pith.science/api/pith-number/JE7SWHCBVYPH2TPFQRX6VTU2FD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JE7SWHCBVYPH2TPFQRX6VTU2FD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JE7SWHCBVYPH2TPFQRX6VTU2FD/action/storage_attestation","attest_author":"https://pith.science/pith/JE7SWHCBVYPH2TPFQRX6VTU2FD/action/author_attestation","sign_citation":"https://pith.science/pith/JE7SWHCBVYPH2TPFQRX6VTU2FD/action/citation_signature","submit_replication":"https://pith.science/pith/JE7SWHCBVYPH2TPFQRX6VTU2FD/action/replication_record"}},"created_at":"2026-07-05T09:09:18.952148+00:00","updated_at":"2026-07-05T09:09:18.952148+00:00"}