{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YUBM5JEIQLJ4PIL64Y3PYRJILF","short_pith_number":"pith:YUBM5JEI","schema_version":"1.0","canonical_sha256":"c502cea48882d3c7a17ee636fc45285948cd0d142f37621ba7d883c63dce8892","source":{"kind":"arxiv","id":"2602.18008","version":2},"attestation_state":"computed","paper":{"title":"Are LLMs Ready for Neural-integrated Mechanistic Modeling? A Benchmark and Agentic Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Aiying Zhang, Anil Vullikanti, Mengxuan Hu, Prasanna Balachandran, Rituparna Datta, Sheng Li, Shunshun Liu, Zihan Guan","submitted_at":"2026-02-20T05:46:54Z","abstract_excerpt":"Large language models (LLMs) have shown promise in constructing mechanistic models from data. However, existing evaluations largely focus on simplified settings and fail to capture the complexity of real-world scientific modeling. In practice, such modeling often involves neural-integrated formulations, where a mechanistic model component and a neural network component are jointly constructed, leading to a significantly more complex search space. Motivated by this gap, we introduce the Neural-Integrated Mechanistic Modeling (NIMM) benchmark, which evaluates LLM-generated neural-integrated mech"},"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":"2602.18008","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-20T05:46:54Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"44415ab952a2e62c837caf031d359cfdaf9f1a059bf8f572bf1c80053f29a919","abstract_canon_sha256":"1871be0180b91e47d79db723c9b80738238a0fe097a7c744f706cae20e91f64d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:15.900747Z","signature_b64":"3dDYYSQmKH/7nd69+iwxKNtSVQL0+JKycvOQBeQ6q15P6QjUa9LMgkqEh+1TLh+AFRcBvkb97+i3AuQ6EShsDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c502cea48882d3c7a17ee636fc45285948cd0d142f37621ba7d883c63dce8892","last_reissued_at":"2026-06-02T01:04:15.900252Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:15.900252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are LLMs Ready for Neural-integrated Mechanistic Modeling? A Benchmark and Agentic Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Aiying Zhang, Anil Vullikanti, Mengxuan Hu, Prasanna Balachandran, Rituparna Datta, Sheng Li, Shunshun Liu, Zihan Guan","submitted_at":"2026-02-20T05:46:54Z","abstract_excerpt":"Large language models (LLMs) have shown promise in constructing mechanistic models from data. However, existing evaluations largely focus on simplified settings and fail to capture the complexity of real-world scientific modeling. In practice, such modeling often involves neural-integrated formulations, where a mechanistic model component and a neural network component are jointly constructed, leading to a significantly more complex search space. Motivated by this gap, we introduce the Neural-Integrated Mechanistic Modeling (NIMM) benchmark, which evaluates LLM-generated neural-integrated mech"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.18008","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/2602.18008/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":"2602.18008","created_at":"2026-06-02T01:04:15.900327+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.18008v2","created_at":"2026-06-02T01:04:15.900327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.18008","created_at":"2026-06-02T01:04:15.900327+00:00"},{"alias_kind":"pith_short_12","alias_value":"YUBM5JEIQLJ4","created_at":"2026-06-02T01:04:15.900327+00:00"},{"alias_kind":"pith_short_16","alias_value":"YUBM5JEIQLJ4PIL6","created_at":"2026-06-02T01:04:15.900327+00:00"},{"alias_kind":"pith_short_8","alias_value":"YUBM5JEI","created_at":"2026-06-02T01:04:15.900327+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/YUBM5JEIQLJ4PIL64Y3PYRJILF","json":"https://pith.science/pith/YUBM5JEIQLJ4PIL64Y3PYRJILF.json","graph_json":"https://pith.science/api/pith-number/YUBM5JEIQLJ4PIL64Y3PYRJILF/graph.json","events_json":"https://pith.science/api/pith-number/YUBM5JEIQLJ4PIL64Y3PYRJILF/events.json","paper":"https://pith.science/paper/YUBM5JEI"},"agent_actions":{"view_html":"https://pith.science/pith/YUBM5JEIQLJ4PIL64Y3PYRJILF","download_json":"https://pith.science/pith/YUBM5JEIQLJ4PIL64Y3PYRJILF.json","view_paper":"https://pith.science/paper/YUBM5JEI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.18008&json=true","fetch_graph":"https://pith.science/api/pith-number/YUBM5JEIQLJ4PIL64Y3PYRJILF/graph.json","fetch_events":"https://pith.science/api/pith-number/YUBM5JEIQLJ4PIL64Y3PYRJILF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YUBM5JEIQLJ4PIL64Y3PYRJILF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YUBM5JEIQLJ4PIL64Y3PYRJILF/action/storage_attestation","attest_author":"https://pith.science/pith/YUBM5JEIQLJ4PIL64Y3PYRJILF/action/author_attestation","sign_citation":"https://pith.science/pith/YUBM5JEIQLJ4PIL64Y3PYRJILF/action/citation_signature","submit_replication":"https://pith.science/pith/YUBM5JEIQLJ4PIL64Y3PYRJILF/action/replication_record"}},"created_at":"2026-06-02T01:04:15.900327+00:00","updated_at":"2026-06-02T01:04:15.900327+00:00"}