{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3IS46TPLCHQLO5QIUE2F3TCKGD","short_pith_number":"pith:3IS46TPL","schema_version":"1.0","canonical_sha256":"da25cf4deb11e0b77608a1345dcc4a30e15f0fda9b62310275f1568fe3000792","source":{"kind":"arxiv","id":"2509.10790","version":1},"attestation_state":"computed","paper":{"title":"GoldenTransformer: A Modular Fault Injection Framework for Transformer Robustness Research","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Luke Howard","submitted_at":"2025-09-13T02:52:08Z","abstract_excerpt":"Transformers have become the foundation for a wide range of state--of--the--art models across natural language processing, computer vision, and other machine learning domains. Despite their widespread deployment, the robustness of these models under fault conditions remains underexplored. We present GoldenTransformer, a modular and extensible fault injection framework designed to evaluate the resiliency of Large Language Models to induced hardware faults. GoldenTransformer offers a unified Python-based platform for injecting diverse classes of faults--such as weight corruption, activation inje"},"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":"2509.10790","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-13T02:52:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"543e4c7931c915c31125099f8219cae1f21552d05159276ac05ccc1becfcf732","abstract_canon_sha256":"95386f959c44f040466a7515b622c13bd0e9d643848f31cc9aac292294a7ade4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:11:28.077276Z","signature_b64":"JzePijXpoP/UTZXYcD8EQcbB8uMzEKd/6wHBuqgnU0BbwtDIG17Cse26Bau1yEnfp1tnl3ORkVuLK+2B1UAQAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da25cf4deb11e0b77608a1345dcc4a30e15f0fda9b62310275f1568fe3000792","last_reissued_at":"2026-07-05T12:11:28.076701Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:11:28.076701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GoldenTransformer: A Modular Fault Injection Framework for Transformer Robustness Research","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Luke Howard","submitted_at":"2025-09-13T02:52:08Z","abstract_excerpt":"Transformers have become the foundation for a wide range of state--of--the--art models across natural language processing, computer vision, and other machine learning domains. Despite their widespread deployment, the robustness of these models under fault conditions remains underexplored. We present GoldenTransformer, a modular and extensible fault injection framework designed to evaluate the resiliency of Large Language Models to induced hardware faults. GoldenTransformer offers a unified Python-based platform for injecting diverse classes of faults--such as weight corruption, activation inje"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.10790","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/2509.10790/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":"2509.10790","created_at":"2026-07-05T12:11:28.076761+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.10790v1","created_at":"2026-07-05T12:11:28.076761+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.10790","created_at":"2026-07-05T12:11:28.076761+00:00"},{"alias_kind":"pith_short_12","alias_value":"3IS46TPLCHQL","created_at":"2026-07-05T12:11:28.076761+00:00"},{"alias_kind":"pith_short_16","alias_value":"3IS46TPLCHQLO5QI","created_at":"2026-07-05T12:11:28.076761+00:00"},{"alias_kind":"pith_short_8","alias_value":"3IS46TPL","created_at":"2026-07-05T12:11:28.076761+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/3IS46TPLCHQLO5QIUE2F3TCKGD","json":"https://pith.science/pith/3IS46TPLCHQLO5QIUE2F3TCKGD.json","graph_json":"https://pith.science/api/pith-number/3IS46TPLCHQLO5QIUE2F3TCKGD/graph.json","events_json":"https://pith.science/api/pith-number/3IS46TPLCHQLO5QIUE2F3TCKGD/events.json","paper":"https://pith.science/paper/3IS46TPL"},"agent_actions":{"view_html":"https://pith.science/pith/3IS46TPLCHQLO5QIUE2F3TCKGD","download_json":"https://pith.science/pith/3IS46TPLCHQLO5QIUE2F3TCKGD.json","view_paper":"https://pith.science/paper/3IS46TPL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.10790&json=true","fetch_graph":"https://pith.science/api/pith-number/3IS46TPLCHQLO5QIUE2F3TCKGD/graph.json","fetch_events":"https://pith.science/api/pith-number/3IS46TPLCHQLO5QIUE2F3TCKGD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3IS46TPLCHQLO5QIUE2F3TCKGD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3IS46TPLCHQLO5QIUE2F3TCKGD/action/storage_attestation","attest_author":"https://pith.science/pith/3IS46TPLCHQLO5QIUE2F3TCKGD/action/author_attestation","sign_citation":"https://pith.science/pith/3IS46TPLCHQLO5QIUE2F3TCKGD/action/citation_signature","submit_replication":"https://pith.science/pith/3IS46TPLCHQLO5QIUE2F3TCKGD/action/replication_record"}},"created_at":"2026-07-05T12:11:28.076761+00:00","updated_at":"2026-07-05T12:11:28.076761+00:00"}