{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:AIEBXAHA7VQGZKNPXHJDRCYTPP","short_pith_number":"pith:AIEBXAHA","schema_version":"1.0","canonical_sha256":"02081b80e0fd606ca9afb9d2388b137bf5a60ebb6d0e568053067c03008cb359","source":{"kind":"arxiv","id":"2210.17340","version":1},"attestation_state":"computed","paper":{"title":"MatKG: The Largest Knowledge Graph in Materials Science -- Entities, Relations, and Link Prediction through Graph Representation Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Elsa Olivetti, Sumit Pai, Vineeth Venugopal","submitted_at":"2022-10-31T14:05:47Z","abstract_excerpt":"This paper introduces MatKG, a novel graph database of key concepts in material science spanning the traditional material-structure-property-processing paradigm. MatKG is autonomously generated through transformer-based, large language models and generates pseudo ontological schema through statistical co-occurrence mapping. At present, MatKG contains over 2 million unique relationship triples derived from 80,000 entities. This allows the curated analysis, querying, and visualization of materials knowledge at unique resolution and scale. Further, Knowledge Graph Embedding models are used to lea"},"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":"2210.17340","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2022-10-31T14:05:47Z","cross_cats_sorted":[],"title_canon_sha256":"4e48ed57b5aeaf9e52d681aa6ec38c1907db6b4f8fe5d1c2c6f48ed3d69c96f1","abstract_canon_sha256":"e3dbb04cd4013550faf4b1248fdff353a8582e96f9072118829b2639c3d4bb31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:12:04.350638Z","signature_b64":"CnN/DKONMHYxyBNkNVIV+dw9kMF7xQ0l3L/nWwKJ1jPF6smrtsvrrcMXuuGGZUx0MrNEre4Wb9tvP8m3PlrOBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02081b80e0fd606ca9afb9d2388b137bf5a60ebb6d0e568053067c03008cb359","last_reissued_at":"2026-07-05T05:12:04.350216Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:12:04.350216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MatKG: The Largest Knowledge Graph in Materials Science -- Entities, Relations, and Link Prediction through Graph Representation Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Elsa Olivetti, Sumit Pai, Vineeth Venugopal","submitted_at":"2022-10-31T14:05:47Z","abstract_excerpt":"This paper introduces MatKG, a novel graph database of key concepts in material science spanning the traditional material-structure-property-processing paradigm. MatKG is autonomously generated through transformer-based, large language models and generates pseudo ontological schema through statistical co-occurrence mapping. At present, MatKG contains over 2 million unique relationship triples derived from 80,000 entities. This allows the curated analysis, querying, and visualization of materials knowledge at unique resolution and scale. Further, Knowledge Graph Embedding models are used to lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.17340","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/2210.17340/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":"2210.17340","created_at":"2026-07-05T05:12:04.350267+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.17340v1","created_at":"2026-07-05T05:12:04.350267+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.17340","created_at":"2026-07-05T05:12:04.350267+00:00"},{"alias_kind":"pith_short_12","alias_value":"AIEBXAHA7VQG","created_at":"2026-07-05T05:12:04.350267+00:00"},{"alias_kind":"pith_short_16","alias_value":"AIEBXAHA7VQGZKNP","created_at":"2026-07-05T05:12:04.350267+00:00"},{"alias_kind":"pith_short_8","alias_value":"AIEBXAHA","created_at":"2026-07-05T05:12:04.350267+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.12000","citing_title":"ByteScience: Bridging Unstructured Scientific Literature and Structured Data with Auto Fine-tuned Large Language Model in Token Granularity","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AIEBXAHA7VQGZKNPXHJDRCYTPP","json":"https://pith.science/pith/AIEBXAHA7VQGZKNPXHJDRCYTPP.json","graph_json":"https://pith.science/api/pith-number/AIEBXAHA7VQGZKNPXHJDRCYTPP/graph.json","events_json":"https://pith.science/api/pith-number/AIEBXAHA7VQGZKNPXHJDRCYTPP/events.json","paper":"https://pith.science/paper/AIEBXAHA"},"agent_actions":{"view_html":"https://pith.science/pith/AIEBXAHA7VQGZKNPXHJDRCYTPP","download_json":"https://pith.science/pith/AIEBXAHA7VQGZKNPXHJDRCYTPP.json","view_paper":"https://pith.science/paper/AIEBXAHA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.17340&json=true","fetch_graph":"https://pith.science/api/pith-number/AIEBXAHA7VQGZKNPXHJDRCYTPP/graph.json","fetch_events":"https://pith.science/api/pith-number/AIEBXAHA7VQGZKNPXHJDRCYTPP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AIEBXAHA7VQGZKNPXHJDRCYTPP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AIEBXAHA7VQGZKNPXHJDRCYTPP/action/storage_attestation","attest_author":"https://pith.science/pith/AIEBXAHA7VQGZKNPXHJDRCYTPP/action/author_attestation","sign_citation":"https://pith.science/pith/AIEBXAHA7VQGZKNPXHJDRCYTPP/action/citation_signature","submit_replication":"https://pith.science/pith/AIEBXAHA7VQGZKNPXHJDRCYTPP/action/replication_record"}},"created_at":"2026-07-05T05:12:04.350267+00:00","updated_at":"2026-07-05T05:12:04.350267+00:00"}