{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3NJV7XAMQJJKCREOFHRHHPOBX2","short_pith_number":"pith:3NJV7XAM","schema_version":"1.0","canonical_sha256":"db535fdc0c8252a1448e29e273bdc1be929b2d403404204156f5bd8d714291f5","source":{"kind":"arxiv","id":"2604.02688","version":3},"attestation_state":"computed","paper":{"title":"MatClaw: An Autonomous Code-First LLM Agent for End-to-End Materials Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"An LLM agent autonomously handles end-to-end materials simulations by writing and executing its own code.","cross_cats":["cs.SE"],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Boris I. Yakobson, Chenmu Zhang","submitted_at":"2026-04-03T03:32:15Z","abstract_excerpt":"Existing LLM agents for computational materials science are constrained by pipeline-bounded architectures tied to specific simulation codes and by dependence on manually written tool functions that grow with task scope. We present MatClaw, a code-first agent that writes and executes Python directly, composing any installed domain library to orchestrate multi-code workflows on remote HPC clusters without predefined tool functions. To sustain coherent execution across multi-day workflows, MatClaw uses a four-layer memory architecture that prevents progressive context loss, and retrieval-augmente"},"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":true},"canonical_record":{"source":{"id":"2604.02688","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-04-03T03:32:15Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"c7391626a220789d9a07287e4e521a0d37280c66d39af60731b3e6894997c545","abstract_canon_sha256":"cf167e88bd4cae09aea4f8311e12590b9fb0e72a8171d607d8004efca7de0cb9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:18.655547Z","signature_b64":"durj2x/Xe0KXofYnek16IZ5aSIlelNlZ7KL46EhQkk3EdcpweiU0KE1G9hK6Mgc7n3aR88ycDSzzM6BHilkxCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db535fdc0c8252a1448e29e273bdc1be929b2d403404204156f5bd8d714291f5","last_reissued_at":"2026-05-25T02:01:18.654495Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:18.654495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MatClaw: An Autonomous Code-First LLM Agent for End-to-End Materials Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"An LLM agent autonomously handles end-to-end materials simulations by writing and executing its own code.","cross_cats":["cs.SE"],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Boris I. Yakobson, Chenmu Zhang","submitted_at":"2026-04-03T03:32:15Z","abstract_excerpt":"Existing LLM agents for computational materials science are constrained by pipeline-bounded architectures tied to specific simulation codes and by dependence on manually written tool functions that grow with task scope. We present MatClaw, a code-first agent that writes and executes Python directly, composing any installed domain library to orchestrate multi-code workflows on remote HPC clusters without predefined tool functions. To sustain coherent execution across multi-day workflows, MatClaw uses a four-layer memory architecture that prevents progressive context loss, and retrieval-augmente"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our results demonstrate that the gap between guided and fully autonomous computational materials research is narrower than ever before: LLMs already handle code generation and scientific interpretation reliably, and the rapid improvement in their capabilities will accelerate materials discovery beyond what manual workflows can achieve.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the tacit domain knowledge gaps (simulation timescales, equilibration protocols, sampling strategies) can be consistently bridged by literature self-learning and expert-specified constraints without introducing systematic errors or requiring extensive ongoing human oversight.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MatClaw is a code-first LLM agent that autonomously executes end-to-end materials workflows by generating and running Python scripts on remote clusters, achieving reliable code generation via memory architecture and RAG while requiring guided interventions for tacit knowledge.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"An LLM agent autonomously handles end-to-end materials simulations by writing and executing its own code.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c87d9f093a7b5ff3773f46f84f9863c250f96afe67a6bd39a99d800e9c5376d8"},"source":{"id":"2604.02688","kind":"arxiv","version":3},"verdict":{"id":"12603f99-00e8-4f8a-8ada-ddeff33bddd4","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T18:58:38.223961Z","strongest_claim":"Our results demonstrate that the gap between guided and fully autonomous computational materials research is narrower than ever before: LLMs already handle code generation and scientific interpretation reliably, and the rapid improvement in their capabilities will accelerate materials discovery beyond what manual workflows can achieve.","one_line_summary":"MatClaw is a code-first LLM agent that autonomously executes end-to-end materials workflows by generating and running Python scripts on remote clusters, achieving reliable code generation via memory architecture and RAG while requiring guided interventions for tacit knowledge.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the tacit domain knowledge gaps (simulation timescales, equilibration protocols, sampling strategies) can be consistently bridged by literature self-learning and expert-specified constraints without introducing systematic errors or requiring extensive ongoing human oversight.","pith_extraction_headline":"An LLM agent autonomously handles end-to-end materials simulations by writing and executing its own code."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.02688/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":2,"snapshot_sha256":"266d830691709531415121b10072912a3c1df0c75e8e780509e311fc45f438dd"},"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":"2604.02688","created_at":"2026-05-25T02:01:18.654642+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.02688v3","created_at":"2026-05-25T02:01:18.654642+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.02688","created_at":"2026-05-25T02:01:18.654642+00:00"},{"alias_kind":"pith_short_12","alias_value":"3NJV7XAMQJJK","created_at":"2026-05-25T02:01:18.654642+00:00"},{"alias_kind":"pith_short_16","alias_value":"3NJV7XAMQJJKCREO","created_at":"2026-05-25T02:01:18.654642+00:00"},{"alias_kind":"pith_short_8","alias_value":"3NJV7XAM","created_at":"2026-05-25T02:01:18.654642+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.13618","citing_title":"OpenAaaS: An Open Agent-as-a-Service Framework for Distributed Materials-Informatics Research","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3NJV7XAMQJJKCREOFHRHHPOBX2","json":"https://pith.science/pith/3NJV7XAMQJJKCREOFHRHHPOBX2.json","graph_json":"https://pith.science/api/pith-number/3NJV7XAMQJJKCREOFHRHHPOBX2/graph.json","events_json":"https://pith.science/api/pith-number/3NJV7XAMQJJKCREOFHRHHPOBX2/events.json","paper":"https://pith.science/paper/3NJV7XAM"},"agent_actions":{"view_html":"https://pith.science/pith/3NJV7XAMQJJKCREOFHRHHPOBX2","download_json":"https://pith.science/pith/3NJV7XAMQJJKCREOFHRHHPOBX2.json","view_paper":"https://pith.science/paper/3NJV7XAM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.02688&json=true","fetch_graph":"https://pith.science/api/pith-number/3NJV7XAMQJJKCREOFHRHHPOBX2/graph.json","fetch_events":"https://pith.science/api/pith-number/3NJV7XAMQJJKCREOFHRHHPOBX2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3NJV7XAMQJJKCREOFHRHHPOBX2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3NJV7XAMQJJKCREOFHRHHPOBX2/action/storage_attestation","attest_author":"https://pith.science/pith/3NJV7XAMQJJKCREOFHRHHPOBX2/action/author_attestation","sign_citation":"https://pith.science/pith/3NJV7XAMQJJKCREOFHRHHPOBX2/action/citation_signature","submit_replication":"https://pith.science/pith/3NJV7XAMQJJKCREOFHRHHPOBX2/action/replication_record"}},"created_at":"2026-05-25T02:01:18.654642+00:00","updated_at":"2026-05-25T02:01:18.654642+00:00"}