{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SMRC6RPWKX7HKSSXVXI4HA4WKY","short_pith_number":"pith:SMRC6RPW","schema_version":"1.0","canonical_sha256":"93222f45f655fe754a57add1c383965635ea85d14ea4b6f2f96a72c61ac2442d","source":{"kind":"arxiv","id":"2507.00742","version":1},"attestation_state":"computed","paper":{"title":"Evaluating LLMs and Prompting Strategies for Automated Hardware Diagnosis from Textual User-Reports","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Carlos Caminha, Felipe T. Brito, Iago C. Chaves, Javam C. Machado, Maria de Lourdes M. Silva, Victor A. E. Farias","submitted_at":"2025-07-01T13:46:00Z","abstract_excerpt":"Computer manufacturers offer platforms for users to describe device faults using textual reports such as \"My screen is flickering\". Identifying the faulty component from the report is essential for automating tests and improving user experience. However, such reports are often ambiguous and lack detail, making this task challenging. Large Language Models (LLMs) have shown promise in addressing such issues. This study evaluates 27 open-source models (1B-72B parameters) and 2 proprietary LLMs using four prompting strategies: Zero-Shot, Few-Shot, Chain-of-Thought (CoT), and CoT+Few-Shot (CoT+FS)."},"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":"2507.00742","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-01T13:46:00Z","cross_cats_sorted":[],"title_canon_sha256":"9eeed8cfd7f6637e309475fccaf6dd3d90f32266ffa631cde37b274a3370e206","abstract_canon_sha256":"ff337d20266c2aeeb9dfcecf921d4f27973c5754d8cf4d923871c4d0c9c53e94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:13.809976Z","signature_b64":"aBZ6/vUEwq8L3GBOb7Oz8P9wS//0Qcr4s3BpEv9FijonsfukOn7Q+429bDGdme4pcH40nj0mOjnaEzTyegc2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93222f45f655fe754a57add1c383965635ea85d14ea4b6f2f96a72c61ac2442d","last_reissued_at":"2026-07-05T11:30:13.809526Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:13.809526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating LLMs and Prompting Strategies for Automated Hardware Diagnosis from Textual User-Reports","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Carlos Caminha, Felipe T. Brito, Iago C. Chaves, Javam C. Machado, Maria de Lourdes M. Silva, Victor A. E. Farias","submitted_at":"2025-07-01T13:46:00Z","abstract_excerpt":"Computer manufacturers offer platforms for users to describe device faults using textual reports such as \"My screen is flickering\". Identifying the faulty component from the report is essential for automating tests and improving user experience. However, such reports are often ambiguous and lack detail, making this task challenging. Large Language Models (LLMs) have shown promise in addressing such issues. This study evaluates 27 open-source models (1B-72B parameters) and 2 proprietary LLMs using four prompting strategies: Zero-Shot, Few-Shot, Chain-of-Thought (CoT), and CoT+Few-Shot (CoT+FS)."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00742","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/2507.00742/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":"2507.00742","created_at":"2026-07-05T11:30:13.809585+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00742v1","created_at":"2026-07-05T11:30:13.809585+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00742","created_at":"2026-07-05T11:30:13.809585+00:00"},{"alias_kind":"pith_short_12","alias_value":"SMRC6RPWKX7H","created_at":"2026-07-05T11:30:13.809585+00:00"},{"alias_kind":"pith_short_16","alias_value":"SMRC6RPWKX7HKSSX","created_at":"2026-07-05T11:30:13.809585+00:00"},{"alias_kind":"pith_short_8","alias_value":"SMRC6RPW","created_at":"2026-07-05T11:30:13.809585+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.04848","citing_title":"Large Language Models Reasoning Abilities Under Non-Ideal Conditions After RL-Fine-Tuning","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SMRC6RPWKX7HKSSXVXI4HA4WKY","json":"https://pith.science/pith/SMRC6RPWKX7HKSSXVXI4HA4WKY.json","graph_json":"https://pith.science/api/pith-number/SMRC6RPWKX7HKSSXVXI4HA4WKY/graph.json","events_json":"https://pith.science/api/pith-number/SMRC6RPWKX7HKSSXVXI4HA4WKY/events.json","paper":"https://pith.science/paper/SMRC6RPW"},"agent_actions":{"view_html":"https://pith.science/pith/SMRC6RPWKX7HKSSXVXI4HA4WKY","download_json":"https://pith.science/pith/SMRC6RPWKX7HKSSXVXI4HA4WKY.json","view_paper":"https://pith.science/paper/SMRC6RPW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00742&json=true","fetch_graph":"https://pith.science/api/pith-number/SMRC6RPWKX7HKSSXVXI4HA4WKY/graph.json","fetch_events":"https://pith.science/api/pith-number/SMRC6RPWKX7HKSSXVXI4HA4WKY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SMRC6RPWKX7HKSSXVXI4HA4WKY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SMRC6RPWKX7HKSSXVXI4HA4WKY/action/storage_attestation","attest_author":"https://pith.science/pith/SMRC6RPWKX7HKSSXVXI4HA4WKY/action/author_attestation","sign_citation":"https://pith.science/pith/SMRC6RPWKX7HKSSXVXI4HA4WKY/action/citation_signature","submit_replication":"https://pith.science/pith/SMRC6RPWKX7HKSSXVXI4HA4WKY/action/replication_record"}},"created_at":"2026-07-05T11:30:13.809585+00:00","updated_at":"2026-07-05T11:30:13.809585+00:00"}