{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CADQ37HCYPWTJERGK2J7GZFCW6","short_pith_number":"pith:CADQ37HC","schema_version":"1.0","canonical_sha256":"10070dfce2c3ed3492265693f364a2b7b6d5dc4d4669b6418776f2df1f48aba0","source":{"kind":"arxiv","id":"2509.21079","version":2},"attestation_state":"computed","paper":{"title":"SoM-1K: A Thousand-Problem Benchmark Dataset for Strength of Materials","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiachen Liu, Jingwen Zhou, Lu Cheng, Qixin Wan, Ran Cao, Wanting Wang, Ziheng Geng, Zilong Wang","submitted_at":"2025-09-25T12:28:22Z","abstract_excerpt":"Foundation models have shown remarkable capabilities in various domains, but their performance on complex, multimodal engineering problems remains largely unexplored. We introduce SoM-1K, the first large-scale multimodal benchmark dataset dedicated to evaluating foundation models on problems in the strength of materials (SoM). The dataset, which contains 1,065 annotated SoM problems, mirrors real-world engineering tasks by including both textual problem statements and schematic diagrams. Due to the limited capabilities of current foundation models in understanding complicated visual informatio"},"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":"2509.21079","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-25T12:28:22Z","cross_cats_sorted":[],"title_canon_sha256":"c4949f6f7b396875bdeb90db44f2cc60b3b65fc354a5fa1baa5c6a092950d3c5","abstract_canon_sha256":"57b2ee5e5c43699536cdf887448af3897d2aa8b5bfe307cd736060382ad4494e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T00:35:59.115085Z","signature_b64":"WTmdnysriSjh8Cp/bZ+JeDZ01S7tKzOXyKZ6crkJJH8WWRzAA4L5FMm6l9Fs8csKTXJgDaIeDoamw7RKKEw9CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10070dfce2c3ed3492265693f364a2b7b6d5dc4d4669b6418776f2df1f48aba0","last_reissued_at":"2026-08-04T00:35:59.113467Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T00:35:59.113467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SoM-1K: A Thousand-Problem Benchmark Dataset for Strength of Materials","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiachen Liu, Jingwen Zhou, Lu Cheng, Qixin Wan, Ran Cao, Wanting Wang, Ziheng Geng, Zilong Wang","submitted_at":"2025-09-25T12:28:22Z","abstract_excerpt":"Foundation models have shown remarkable capabilities in various domains, but their performance on complex, multimodal engineering problems remains largely unexplored. We introduce SoM-1K, the first large-scale multimodal benchmark dataset dedicated to evaluating foundation models on problems in the strength of materials (SoM). The dataset, which contains 1,065 annotated SoM problems, mirrors real-world engineering tasks by including both textual problem statements and schematic diagrams. Due to the limited capabilities of current foundation models in understanding complicated visual informatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.21079","kind":"arxiv","version":2},"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/2509.21079/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":"2509.21079","created_at":"2026-08-04T00:35:59.114624+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.21079v2","created_at":"2026-08-04T00:35:59.114624+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.21079","created_at":"2026-08-04T00:35:59.114624+00:00"},{"alias_kind":"pith_short_12","alias_value":"CADQ37HCYPWT","created_at":"2026-08-04T00:35:59.114624+00:00"},{"alias_kind":"pith_short_16","alias_value":"CADQ37HCYPWTJERG","created_at":"2026-08-04T00:35:59.114624+00:00"},{"alias_kind":"pith_short_8","alias_value":"CADQ37HC","created_at":"2026-08-04T00:35:59.114624+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"2606.12025","citing_title":"Human-Enhanced Loop Modeling (HELM): Agent-Based Finite Element Modeling of Concrete Bridge Barriers","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2606.06525","citing_title":"Agentic Large Language Models for Automated Structural Analysis of 3D Frame Systems","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2606.12040","citing_title":"A Lightweight Multi-Agent Framework for Automated Concrete Barrier Design","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2511.14159","citing_title":"MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMs","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09866","citing_title":"Automating Structural Analysis Across Multiple Software Platforms Using Large Language Models","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CADQ37HCYPWTJERGK2J7GZFCW6","json":"https://pith.science/pith/CADQ37HCYPWTJERGK2J7GZFCW6.json","graph_json":"https://pith.science/api/pith-number/CADQ37HCYPWTJERGK2J7GZFCW6/graph.json","events_json":"https://pith.science/api/pith-number/CADQ37HCYPWTJERGK2J7GZFCW6/events.json","paper":"https://pith.science/paper/CADQ37HC"},"agent_actions":{"view_html":"https://pith.science/pith/CADQ37HCYPWTJERGK2J7GZFCW6","download_json":"https://pith.science/pith/CADQ37HCYPWTJERGK2J7GZFCW6.json","view_paper":"https://pith.science/paper/CADQ37HC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.21079&json=true","fetch_graph":"https://pith.science/api/pith-number/CADQ37HCYPWTJERGK2J7GZFCW6/graph.json","fetch_events":"https://pith.science/api/pith-number/CADQ37HCYPWTJERGK2J7GZFCW6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CADQ37HCYPWTJERGK2J7GZFCW6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CADQ37HCYPWTJERGK2J7GZFCW6/action/storage_attestation","attest_author":"https://pith.science/pith/CADQ37HCYPWTJERGK2J7GZFCW6/action/author_attestation","sign_citation":"https://pith.science/pith/CADQ37HCYPWTJERGK2J7GZFCW6/action/citation_signature","submit_replication":"https://pith.science/pith/CADQ37HCYPWTJERGK2J7GZFCW6/action/replication_record"}},"created_at":"2026-08-04T00:35:59.114624+00:00","updated_at":"2026-08-04T00:35:59.114624+00:00"}