{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GOYFWDAD3E3T6FGKW2B5N5PKGT","short_pith_number":"pith:GOYFWDAD","schema_version":"1.0","canonical_sha256":"33b05b0c03d9373f14cab683d6f5ea34fd76809e0dfc0f3e045f495e41af498f","source":{"kind":"arxiv","id":"2606.20729","version":1},"attestation_state":"computed","paper":{"title":"LLM-Guided Test-Time Discovery of Quantum-Chemical Approximation Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.mtrl-sci","cs.AI","cs.LG"],"primary_cat":"physics.chem-ph","authors_text":"Masaki Adachi, Masaya Hagai, Shuhei Kurita, Tomoya Murata, Yuta Suzuki","submitted_at":"2026-06-17T05:58:58Z","abstract_excerpt":"Quantum chemistry simulations underpin modern materials discovery, yet their impact is limited by steep computational cost and dependence on fixed approximation schemes. Foundation models, such as machine-learned interatomic potentials, have accelerated parts of this workflow, but their reliance on large-scale pretraining restricts adaptability at the frontier of chemical space, where methodological innovation and sparse data are the norm. Agentic AI systems can automate existing simulation pipelines, yet they remain constrained by the predefined tools and algorithms they orchestrate. In respo"},"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":"2606.20729","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.chem-ph","submitted_at":"2026-06-17T05:58:58Z","cross_cats_sorted":["cond-mat.mtrl-sci","cs.AI","cs.LG"],"title_canon_sha256":"0397ad6f8529e6be6642520476d2309535ae3ea8c0d1c625387cc570868c17bb","abstract_canon_sha256":"b3b53d18ec584dfcd854edefd6d35b9d77d30892927b4fd8f26001721599dc5d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T00:11:54.943378Z","signature_b64":"Badz57FivgRFUplXNkofbaxiNjB1RONXIS71QlSFYP3nhslXK0KN9LohB80L/GP/4ixwgvGJ2GeY1eTwLTlLDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33b05b0c03d9373f14cab683d6f5ea34fd76809e0dfc0f3e045f495e41af498f","last_reissued_at":"2026-06-23T00:11:54.942947Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T00:11:54.942947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-Guided Test-Time Discovery of Quantum-Chemical Approximation Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.mtrl-sci","cs.AI","cs.LG"],"primary_cat":"physics.chem-ph","authors_text":"Masaki Adachi, Masaya Hagai, Shuhei Kurita, Tomoya Murata, Yuta Suzuki","submitted_at":"2026-06-17T05:58:58Z","abstract_excerpt":"Quantum chemistry simulations underpin modern materials discovery, yet their impact is limited by steep computational cost and dependence on fixed approximation schemes. Foundation models, such as machine-learned interatomic potentials, have accelerated parts of this workflow, but their reliance on large-scale pretraining restricts adaptability at the frontier of chemical space, where methodological innovation and sparse data are the norm. Agentic AI systems can automate existing simulation pipelines, yet they remain constrained by the predefined tools and algorithms they orchestrate. In respo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20729","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/2606.20729/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":"2606.20729","created_at":"2026-06-23T00:11:54.943015+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20729v1","created_at":"2026-06-23T00:11:54.943015+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20729","created_at":"2026-06-23T00:11:54.943015+00:00"},{"alias_kind":"pith_short_12","alias_value":"GOYFWDAD3E3T","created_at":"2026-06-23T00:11:54.943015+00:00"},{"alias_kind":"pith_short_16","alias_value":"GOYFWDAD3E3T6FGK","created_at":"2026-06-23T00:11:54.943015+00:00"},{"alias_kind":"pith_short_8","alias_value":"GOYFWDAD","created_at":"2026-06-23T00:11:54.943015+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/GOYFWDAD3E3T6FGKW2B5N5PKGT","json":"https://pith.science/pith/GOYFWDAD3E3T6FGKW2B5N5PKGT.json","graph_json":"https://pith.science/api/pith-number/GOYFWDAD3E3T6FGKW2B5N5PKGT/graph.json","events_json":"https://pith.science/api/pith-number/GOYFWDAD3E3T6FGKW2B5N5PKGT/events.json","paper":"https://pith.science/paper/GOYFWDAD"},"agent_actions":{"view_html":"https://pith.science/pith/GOYFWDAD3E3T6FGKW2B5N5PKGT","download_json":"https://pith.science/pith/GOYFWDAD3E3T6FGKW2B5N5PKGT.json","view_paper":"https://pith.science/paper/GOYFWDAD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20729&json=true","fetch_graph":"https://pith.science/api/pith-number/GOYFWDAD3E3T6FGKW2B5N5PKGT/graph.json","fetch_events":"https://pith.science/api/pith-number/GOYFWDAD3E3T6FGKW2B5N5PKGT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GOYFWDAD3E3T6FGKW2B5N5PKGT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GOYFWDAD3E3T6FGKW2B5N5PKGT/action/storage_attestation","attest_author":"https://pith.science/pith/GOYFWDAD3E3T6FGKW2B5N5PKGT/action/author_attestation","sign_citation":"https://pith.science/pith/GOYFWDAD3E3T6FGKW2B5N5PKGT/action/citation_signature","submit_replication":"https://pith.science/pith/GOYFWDAD3E3T6FGKW2B5N5PKGT/action/replication_record"}},"created_at":"2026-06-23T00:11:54.943015+00:00","updated_at":"2026-06-23T00:11:54.943015+00:00"}