{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:6VJOCTFI2BCSM4TO47GTSIXDIB","short_pith_number":"pith:6VJOCTFI","schema_version":"1.0","canonical_sha256":"f552e14ca8d04526726ee7cd3922e34065dd6aca68e980d4556aafaa9017ce30","source":{"kind":"arxiv","id":"2010.00532","version":2},"attestation_state":"computed","paper":{"title":"Machine learning with persistent homology and chemical word embeddings improves prediction accuracy and interpretability in metal-organic frameworks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.AT","physics.comp-ph"],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Aditi S. Krishnapriyan, Dmitriy Morozov, Jens Hummelsh{\\o}j, Joseph Montoya, Maciej Haranczyk","submitted_at":"2020-10-01T16:31:46Z","abstract_excerpt":"Machine learning has emerged as a powerful approach in materials discovery. Its major challenge is selecting features that create interpretable representations of materials, useful across multiple prediction tasks. We introduce an end-to-end machine learning model that automatically generates descriptors that capture a complex representation of a material's structure and chemistry. This approach builds on computational topology techniques (namely, persistent homology) and word embeddings from natural language processing. It automatically encapsulates geometric and chemical information directly"},"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":"2010.00532","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2020-10-01T16:31:46Z","cross_cats_sorted":["cs.LG","math.AT","physics.comp-ph"],"title_canon_sha256":"d79a0f69750b3924d0c71cc8683325f23f8b35952829b056f13bbb17b950bad1","abstract_canon_sha256":"d5c427a2af2634218ebc0488a8a7b160728c0e1434d2c0d031d87bb668822f6c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:28:06.083458Z","signature_b64":"wQv+sM6H/dFFToaVFH1AeE0k6f55BPFhyvKwFgFBH2oMiECtTwaAaoaa0DsoUJYbsp/+SfLqG9QqWdNrJZi5BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f552e14ca8d04526726ee7cd3922e34065dd6aca68e980d4556aafaa9017ce30","last_reissued_at":"2026-07-05T02:28:06.082982Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:28:06.082982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Machine learning with persistent homology and chemical word embeddings improves prediction accuracy and interpretability in metal-organic frameworks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.AT","physics.comp-ph"],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Aditi S. Krishnapriyan, Dmitriy Morozov, Jens Hummelsh{\\o}j, Joseph Montoya, Maciej Haranczyk","submitted_at":"2020-10-01T16:31:46Z","abstract_excerpt":"Machine learning has emerged as a powerful approach in materials discovery. Its major challenge is selecting features that create interpretable representations of materials, useful across multiple prediction tasks. We introduce an end-to-end machine learning model that automatically generates descriptors that capture a complex representation of a material's structure and chemistry. This approach builds on computational topology techniques (namely, persistent homology) and word embeddings from natural language processing. It automatically encapsulates geometric and chemical information directly"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.00532","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/2010.00532/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":"2010.00532","created_at":"2026-07-05T02:28:06.083042+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.00532v2","created_at":"2026-07-05T02:28:06.083042+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.00532","created_at":"2026-07-05T02:28:06.083042+00:00"},{"alias_kind":"pith_short_12","alias_value":"6VJOCTFI2BCS","created_at":"2026-07-05T02:28:06.083042+00:00"},{"alias_kind":"pith_short_16","alias_value":"6VJOCTFI2BCSM4TO","created_at":"2026-07-05T02:28:06.083042+00:00"},{"alias_kind":"pith_short_8","alias_value":"6VJOCTFI","created_at":"2026-07-05T02:28:06.083042+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/6VJOCTFI2BCSM4TO47GTSIXDIB","json":"https://pith.science/pith/6VJOCTFI2BCSM4TO47GTSIXDIB.json","graph_json":"https://pith.science/api/pith-number/6VJOCTFI2BCSM4TO47GTSIXDIB/graph.json","events_json":"https://pith.science/api/pith-number/6VJOCTFI2BCSM4TO47GTSIXDIB/events.json","paper":"https://pith.science/paper/6VJOCTFI"},"agent_actions":{"view_html":"https://pith.science/pith/6VJOCTFI2BCSM4TO47GTSIXDIB","download_json":"https://pith.science/pith/6VJOCTFI2BCSM4TO47GTSIXDIB.json","view_paper":"https://pith.science/paper/6VJOCTFI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.00532&json=true","fetch_graph":"https://pith.science/api/pith-number/6VJOCTFI2BCSM4TO47GTSIXDIB/graph.json","fetch_events":"https://pith.science/api/pith-number/6VJOCTFI2BCSM4TO47GTSIXDIB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6VJOCTFI2BCSM4TO47GTSIXDIB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6VJOCTFI2BCSM4TO47GTSIXDIB/action/storage_attestation","attest_author":"https://pith.science/pith/6VJOCTFI2BCSM4TO47GTSIXDIB/action/author_attestation","sign_citation":"https://pith.science/pith/6VJOCTFI2BCSM4TO47GTSIXDIB/action/citation_signature","submit_replication":"https://pith.science/pith/6VJOCTFI2BCSM4TO47GTSIXDIB/action/replication_record"}},"created_at":"2026-07-05T02:28:06.083042+00:00","updated_at":"2026-07-05T02:28:06.083042+00:00"}