{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OIAKLQP7KKIKBO6T5QR4NXWX3L","short_pith_number":"pith:OIAKLQP7","schema_version":"1.0","canonical_sha256":"7200a5c1ff5290a0bbd3ec23c6ded7dadd5ebb7c3e7af438e837b501550da6f6","source":{"kind":"arxiv","id":"2406.17295","version":3},"attestation_state":"computed","paper":{"title":"Less can be more for predicting properties with large language models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Kevin Maik Jablonka, Nawaf Alampara, Santiago Miret","submitted_at":"2024-06-25T05:45:07Z","abstract_excerpt":"Predicting properties from coordinate-category data -- sets of vectors paired with categorical information -- is fundamental to computational science. In materials science, this challenge manifests as predicting properties like formation energies or elastic moduli from crystal structures comprising atomic positions (vectors) and element types (categorical information). While large language models (LLMs) have increasingly been applied to such tasks, with researchers encoding structural data as text, optimal strategies for achieving reliable predictions remain elusive. Here, we report fundamenta"},"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":"2406.17295","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2024-06-25T05:45:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"08d6c70c9693c79c59c7b5f1998b5ab3e3a24622b9ed4bc24c5597262dc3dddd","abstract_canon_sha256":"26f242ba1234c34203e7e6e72d0665ef8501fc3d26093e5056a92df0de8e24c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:58.596242Z","signature_b64":"izu7qUyiSOXERsztFp24NE9kDkrQ+RtssblsABHkQz2PKnf+zm7AqSvUPZhiXQSmXcdsqrNudoYB3EA/tCepDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7200a5c1ff5290a0bbd3ec23c6ded7dadd5ebb7c3e7af438e837b501550da6f6","last_reissued_at":"2026-07-05T11:33:58.595778Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:58.595778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Less can be more for predicting properties with large language models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Kevin Maik Jablonka, Nawaf Alampara, Santiago Miret","submitted_at":"2024-06-25T05:45:07Z","abstract_excerpt":"Predicting properties from coordinate-category data -- sets of vectors paired with categorical information -- is fundamental to computational science. In materials science, this challenge manifests as predicting properties like formation energies or elastic moduli from crystal structures comprising atomic positions (vectors) and element types (categorical information). While large language models (LLMs) have increasingly been applied to such tasks, with researchers encoding structural data as text, optimal strategies for achieving reliable predictions remain elusive. Here, we report fundamenta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17295","kind":"arxiv","version":3},"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/2406.17295/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":"2406.17295","created_at":"2026-07-05T11:33:58.595836+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.17295v3","created_at":"2026-07-05T11:33:58.595836+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17295","created_at":"2026-07-05T11:33:58.595836+00:00"},{"alias_kind":"pith_short_12","alias_value":"OIAKLQP7KKIK","created_at":"2026-07-05T11:33:58.595836+00:00"},{"alias_kind":"pith_short_16","alias_value":"OIAKLQP7KKIKBO6T","created_at":"2026-07-05T11:33:58.595836+00:00"},{"alias_kind":"pith_short_8","alias_value":"OIAKLQP7","created_at":"2026-07-05T11:33:58.595836+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21395","citing_title":"Atomistic Language Models Understand and Generate Materials","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07712","citing_title":"MatMind: A Structure-Activity Knowledge-Driven Generative Foundation Model for Materials Science","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03515","citing_title":"Scale-Dependent Input Representation and Confidence Estimation for LLMs in Materials Property Prediction","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27709","citing_title":"Conditional Generative Models Enable Targeted Exploration of MAX Phase Design Space","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OIAKLQP7KKIKBO6T5QR4NXWX3L","json":"https://pith.science/pith/OIAKLQP7KKIKBO6T5QR4NXWX3L.json","graph_json":"https://pith.science/api/pith-number/OIAKLQP7KKIKBO6T5QR4NXWX3L/graph.json","events_json":"https://pith.science/api/pith-number/OIAKLQP7KKIKBO6T5QR4NXWX3L/events.json","paper":"https://pith.science/paper/OIAKLQP7"},"agent_actions":{"view_html":"https://pith.science/pith/OIAKLQP7KKIKBO6T5QR4NXWX3L","download_json":"https://pith.science/pith/OIAKLQP7KKIKBO6T5QR4NXWX3L.json","view_paper":"https://pith.science/paper/OIAKLQP7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.17295&json=true","fetch_graph":"https://pith.science/api/pith-number/OIAKLQP7KKIKBO6T5QR4NXWX3L/graph.json","fetch_events":"https://pith.science/api/pith-number/OIAKLQP7KKIKBO6T5QR4NXWX3L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OIAKLQP7KKIKBO6T5QR4NXWX3L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OIAKLQP7KKIKBO6T5QR4NXWX3L/action/storage_attestation","attest_author":"https://pith.science/pith/OIAKLQP7KKIKBO6T5QR4NXWX3L/action/author_attestation","sign_citation":"https://pith.science/pith/OIAKLQP7KKIKBO6T5QR4NXWX3L/action/citation_signature","submit_replication":"https://pith.science/pith/OIAKLQP7KKIKBO6T5QR4NXWX3L/action/replication_record"}},"created_at":"2026-07-05T11:33:58.595836+00:00","updated_at":"2026-07-05T11:33:58.595836+00:00"}