{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HRI3DTVYYIGURSF74PCQA4ACQR","short_pith_number":"pith:HRI3DTVY","schema_version":"1.0","canonical_sha256":"3c51b1ceb8c20d48c8bfe3c5007002846a992e79b49d05c893585fd16cc812c2","source":{"kind":"arxiv","id":"2301.08813","version":1},"attestation_state":"computed","paper":{"title":"Representations of Materials for Machine Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Aik Rui Tan, Jaclyn R. Lunger, James Damewood, Jessica Karaguesian, Jiayu Peng, Mingrou Xie, Rafael G\\'omez-Bombarelli","submitted_at":"2023-01-20T22:05:54Z","abstract_excerpt":"High-throughput data generation methods and machine learning (ML) algorithms have given rise to a new era of computational materials science by learning relationships among composition, structure, and properties and by exploiting such relations for design. However, to build these connections, materials data must be translated into a numerical form, called a representation, that can be processed by a machine learning model. Datasets in materials science vary in format (ranging from images to spectra), size, and fidelity. Predictive models vary in scope and property of interests. Here, we review"},"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":"2301.08813","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2023-01-20T22:05:54Z","cross_cats_sorted":[],"title_canon_sha256":"890a00307c645a656c00d6c7624b8fec0b1f06451ddf58afc5c985e2e99d1a9c","abstract_canon_sha256":"64cd45ca6b160d7ae1d0fcf00e839c07067463d94b2ed7fffe798f63b785207b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:34:53.096032Z","signature_b64":"SNxH2KxphqVypuFIaQUTeGcEsjTyuBUj143lAmBhWMx97uyyIUXu0nw5xTGa3q/nBucRFs9+LD+JmAiibsfYBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c51b1ceb8c20d48c8bfe3c5007002846a992e79b49d05c893585fd16cc812c2","last_reissued_at":"2026-07-05T05:34:53.095516Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:34:53.095516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Representations of Materials for Machine Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Aik Rui Tan, Jaclyn R. Lunger, James Damewood, Jessica Karaguesian, Jiayu Peng, Mingrou Xie, Rafael G\\'omez-Bombarelli","submitted_at":"2023-01-20T22:05:54Z","abstract_excerpt":"High-throughput data generation methods and machine learning (ML) algorithms have given rise to a new era of computational materials science by learning relationships among composition, structure, and properties and by exploiting such relations for design. However, to build these connections, materials data must be translated into a numerical form, called a representation, that can be processed by a machine learning model. Datasets in materials science vary in format (ranging from images to spectra), size, and fidelity. Predictive models vary in scope and property of interests. Here, we review"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.08813","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/2301.08813/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":"2301.08813","created_at":"2026-07-05T05:34:53.095593+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.08813v1","created_at":"2026-07-05T05:34:53.095593+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.08813","created_at":"2026-07-05T05:34:53.095593+00:00"},{"alias_kind":"pith_short_12","alias_value":"HRI3DTVYYIGU","created_at":"2026-07-05T05:34:53.095593+00:00"},{"alias_kind":"pith_short_16","alias_value":"HRI3DTVYYIGURSF7","created_at":"2026-07-05T05:34:53.095593+00:00"},{"alias_kind":"pith_short_8","alias_value":"HRI3DTVY","created_at":"2026-07-05T05:34:53.095593+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/HRI3DTVYYIGURSF74PCQA4ACQR","json":"https://pith.science/pith/HRI3DTVYYIGURSF74PCQA4ACQR.json","graph_json":"https://pith.science/api/pith-number/HRI3DTVYYIGURSF74PCQA4ACQR/graph.json","events_json":"https://pith.science/api/pith-number/HRI3DTVYYIGURSF74PCQA4ACQR/events.json","paper":"https://pith.science/paper/HRI3DTVY"},"agent_actions":{"view_html":"https://pith.science/pith/HRI3DTVYYIGURSF74PCQA4ACQR","download_json":"https://pith.science/pith/HRI3DTVYYIGURSF74PCQA4ACQR.json","view_paper":"https://pith.science/paper/HRI3DTVY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.08813&json=true","fetch_graph":"https://pith.science/api/pith-number/HRI3DTVYYIGURSF74PCQA4ACQR/graph.json","fetch_events":"https://pith.science/api/pith-number/HRI3DTVYYIGURSF74PCQA4ACQR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HRI3DTVYYIGURSF74PCQA4ACQR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HRI3DTVYYIGURSF74PCQA4ACQR/action/storage_attestation","attest_author":"https://pith.science/pith/HRI3DTVYYIGURSF74PCQA4ACQR/action/author_attestation","sign_citation":"https://pith.science/pith/HRI3DTVYYIGURSF74PCQA4ACQR/action/citation_signature","submit_replication":"https://pith.science/pith/HRI3DTVYYIGURSF74PCQA4ACQR/action/replication_record"}},"created_at":"2026-07-05T05:34:53.095593+00:00","updated_at":"2026-07-05T05:34:53.095593+00:00"}