{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5DXYWQPWG5PUA4TYDUCJ3QM62A","short_pith_number":"pith:5DXYWQPW","schema_version":"1.0","canonical_sha256":"e8ef8b41f6375f4072781d049dc19ed0230e4a7b5f13bb157c1ef429064453b3","source":{"kind":"arxiv","id":"2602.22971","version":2},"attestation_state":"computed","paper":{"title":"SPM-Bench: Benchmarking Large Language Models for Scanning Probe Microscopy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ben Wang, Bing Zhao, Chengliang Xu, Hu Wei, Lin Qu, Peiyao Xiao, Xiaogang Li, Xinyi Gao, Zeyu Wang, Zichao Chen","submitted_at":"2026-02-26T13:08:56Z","abstract_excerpt":"As LLMs achieved breakthroughs in general reasoning, their proficiency in specialized scientific domains reveals pronounced gaps in existing benchmarks due to data contamination, insufficient complexity, and prohibitive human labor costs. Here we present SPM-Bench, an original, PhD-level multimodal benchmark specifically designed for scanning probe microscopy (SPM). We propose a fully automated data synthesis pipeline that ensures both high authority and low-cost. By employing Anchor-Gated Sieve (AGS) technology, we efficiently extract high-value image-text pairs from arXiv and journal papers "},"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":"2602.22971","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-26T13:08:56Z","cross_cats_sorted":[],"title_canon_sha256":"07ceb48348819c300598ac3abf95b9cbf53077a078c250c75632653f829a6d16","abstract_canon_sha256":"05ec87a9832dcb02fcbddbb6e16101d90797c6a36bc6291f84a163f0892e4742"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:02:35.859959Z","signature_b64":"A2O55s9qjlAett5QXoU785eYBUkF5lrjHgXVCABBOmkPau1jjRxW89bjY+OQCKuL19P9R27a0twdTtgE3aNeAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8ef8b41f6375f4072781d049dc19ed0230e4a7b5f13bb157c1ef429064453b3","last_reissued_at":"2026-06-01T01:02:35.858905Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:02:35.858905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPM-Bench: Benchmarking Large Language Models for Scanning Probe Microscopy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ben Wang, Bing Zhao, Chengliang Xu, Hu Wei, Lin Qu, Peiyao Xiao, Xiaogang Li, Xinyi Gao, Zeyu Wang, Zichao Chen","submitted_at":"2026-02-26T13:08:56Z","abstract_excerpt":"As LLMs achieved breakthroughs in general reasoning, their proficiency in specialized scientific domains reveals pronounced gaps in existing benchmarks due to data contamination, insufficient complexity, and prohibitive human labor costs. Here we present SPM-Bench, an original, PhD-level multimodal benchmark specifically designed for scanning probe microscopy (SPM). We propose a fully automated data synthesis pipeline that ensures both high authority and low-cost. By employing Anchor-Gated Sieve (AGS) technology, we efficiently extract high-value image-text pairs from arXiv and journal papers "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.22971","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/2602.22971/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":"2602.22971","created_at":"2026-06-01T01:02:35.859018+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.22971v2","created_at":"2026-06-01T01:02:35.859018+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.22971","created_at":"2026-06-01T01:02:35.859018+00:00"},{"alias_kind":"pith_short_12","alias_value":"5DXYWQPWG5PU","created_at":"2026-06-01T01:02:35.859018+00:00"},{"alias_kind":"pith_short_16","alias_value":"5DXYWQPWG5PUA4TY","created_at":"2026-06-01T01:02:35.859018+00:00"},{"alias_kind":"pith_short_8","alias_value":"5DXYWQPW","created_at":"2026-06-01T01:02:35.859018+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/5DXYWQPWG5PUA4TYDUCJ3QM62A","json":"https://pith.science/pith/5DXYWQPWG5PUA4TYDUCJ3QM62A.json","graph_json":"https://pith.science/api/pith-number/5DXYWQPWG5PUA4TYDUCJ3QM62A/graph.json","events_json":"https://pith.science/api/pith-number/5DXYWQPWG5PUA4TYDUCJ3QM62A/events.json","paper":"https://pith.science/paper/5DXYWQPW"},"agent_actions":{"view_html":"https://pith.science/pith/5DXYWQPWG5PUA4TYDUCJ3QM62A","download_json":"https://pith.science/pith/5DXYWQPWG5PUA4TYDUCJ3QM62A.json","view_paper":"https://pith.science/paper/5DXYWQPW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.22971&json=true","fetch_graph":"https://pith.science/api/pith-number/5DXYWQPWG5PUA4TYDUCJ3QM62A/graph.json","fetch_events":"https://pith.science/api/pith-number/5DXYWQPWG5PUA4TYDUCJ3QM62A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5DXYWQPWG5PUA4TYDUCJ3QM62A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5DXYWQPWG5PUA4TYDUCJ3QM62A/action/storage_attestation","attest_author":"https://pith.science/pith/5DXYWQPWG5PUA4TYDUCJ3QM62A/action/author_attestation","sign_citation":"https://pith.science/pith/5DXYWQPWG5PUA4TYDUCJ3QM62A/action/citation_signature","submit_replication":"https://pith.science/pith/5DXYWQPWG5PUA4TYDUCJ3QM62A/action/replication_record"}},"created_at":"2026-06-01T01:02:35.859018+00:00","updated_at":"2026-06-01T01:02:35.859018+00:00"}