{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WK65H44CDXQZP3DQZLOI4ZXDHJ","short_pith_number":"pith:WK65H44C","schema_version":"1.0","canonical_sha256":"b2bdd3f3821de197ec70cadc8e66e33a69f380730ad9db70bbeeccfcfcbdea0a","source":{"kind":"arxiv","id":"2503.16537","version":1},"attestation_state":"computed","paper":{"title":"Do Multimodal Large Language Models Understand Welding?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Corey Angst, Grigorii Khvatskii, Maria Gibbs, Nitesh V. Chawla, Robert Landers, Yong Suk Lee","submitted_at":"2025-03-18T19:07:56Z","abstract_excerpt":"This paper examines the performance of Multimodal LLMs (MLLMs) in skilled production work, with a focus on welding. Using a novel data set of real-world and online weld images, annotated by a domain expert, we evaluate the performance of two state-of-the-art MLLMs in assessing weld acceptability across three contexts: RV \\& Marine, Aeronautical, and Farming. While both models perform better on online images, likely due to prior exposure or memorization, they also perform relatively well on unseen, real-world weld images. Additionally, we introduce WeldPrompt, a prompting strategy that combines"},"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":"2503.16537","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-18T19:07:56Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"ab97a7b77d781ccd1d52bcab556b9c76f934df7e67e767bb623ca2a296a6fcb5","abstract_canon_sha256":"e92aabaed5652d9e42afb52090964d84d1b36409fbf2e8ebba9412b472d8c5dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:43.383515Z","signature_b64":"JHIZhKHndr9hHPzMlTbWkt8xHQ5+Ps/9Ry1Pm717T6v2Wa7qV9Lg1lHCFspa631a2D0WKr8jmsfGr9vyF/OgAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2bdd3f3821de197ec70cadc8e66e33a69f380730ad9db70bbeeccfcfcbdea0a","last_reissued_at":"2026-07-05T10:36:43.383010Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:43.383010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do Multimodal Large Language Models Understand Welding?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Corey Angst, Grigorii Khvatskii, Maria Gibbs, Nitesh V. Chawla, Robert Landers, Yong Suk Lee","submitted_at":"2025-03-18T19:07:56Z","abstract_excerpt":"This paper examines the performance of Multimodal LLMs (MLLMs) in skilled production work, with a focus on welding. Using a novel data set of real-world and online weld images, annotated by a domain expert, we evaluate the performance of two state-of-the-art MLLMs in assessing weld acceptability across three contexts: RV \\& Marine, Aeronautical, and Farming. While both models perform better on online images, likely due to prior exposure or memorization, they also perform relatively well on unseen, real-world weld images. Additionally, we introduce WeldPrompt, a prompting strategy that combines"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16537","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/2503.16537/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":"2503.16537","created_at":"2026-07-05T10:36:43.383066+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.16537v1","created_at":"2026-07-05T10:36:43.383066+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16537","created_at":"2026-07-05T10:36:43.383066+00:00"},{"alias_kind":"pith_short_12","alias_value":"WK65H44CDXQZ","created_at":"2026-07-05T10:36:43.383066+00:00"},{"alias_kind":"pith_short_16","alias_value":"WK65H44CDXQZP3DQ","created_at":"2026-07-05T10:36:43.383066+00:00"},{"alias_kind":"pith_short_8","alias_value":"WK65H44C","created_at":"2026-07-05T10:36:43.383066+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/WK65H44CDXQZP3DQZLOI4ZXDHJ","json":"https://pith.science/pith/WK65H44CDXQZP3DQZLOI4ZXDHJ.json","graph_json":"https://pith.science/api/pith-number/WK65H44CDXQZP3DQZLOI4ZXDHJ/graph.json","events_json":"https://pith.science/api/pith-number/WK65H44CDXQZP3DQZLOI4ZXDHJ/events.json","paper":"https://pith.science/paper/WK65H44C"},"agent_actions":{"view_html":"https://pith.science/pith/WK65H44CDXQZP3DQZLOI4ZXDHJ","download_json":"https://pith.science/pith/WK65H44CDXQZP3DQZLOI4ZXDHJ.json","view_paper":"https://pith.science/paper/WK65H44C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.16537&json=true","fetch_graph":"https://pith.science/api/pith-number/WK65H44CDXQZP3DQZLOI4ZXDHJ/graph.json","fetch_events":"https://pith.science/api/pith-number/WK65H44CDXQZP3DQZLOI4ZXDHJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WK65H44CDXQZP3DQZLOI4ZXDHJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WK65H44CDXQZP3DQZLOI4ZXDHJ/action/storage_attestation","attest_author":"https://pith.science/pith/WK65H44CDXQZP3DQZLOI4ZXDHJ/action/author_attestation","sign_citation":"https://pith.science/pith/WK65H44CDXQZP3DQZLOI4ZXDHJ/action/citation_signature","submit_replication":"https://pith.science/pith/WK65H44CDXQZP3DQZLOI4ZXDHJ/action/replication_record"}},"created_at":"2026-07-05T10:36:43.383066+00:00","updated_at":"2026-07-05T10:36:43.383066+00:00"}