{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EUU5LMEROCNH7MXP6QX3RSLFYP","short_pith_number":"pith:EUU5LMER","schema_version":"1.0","canonical_sha256":"2529d5b091709a7fb2eff42fb8c965c3e5351add2fa73ba761f0d04b4a283cc6","source":{"kind":"arxiv","id":"2204.13931","version":1},"attestation_state":"computed","paper":{"title":"KERMIT -- A Transformer-Based Approach for Knowledge Graph Matching","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Heiko Paulheim, Jan Portisch, Sven Hertling","submitted_at":"2022-04-29T08:07:17Z","abstract_excerpt":"One of the strongest signals for automated matching of knowledge graphs and ontologies are textual concept descriptions. With the rise of transformer-based language models, text comparison based on meaning (rather than lexical features) is available to researchers. However, performing pairwise comparisons of all textual descriptions of concepts in two knowledge graphs is expensive and scales quadratically (or even worse if concepts have more than one description). To overcome this problem, we follow a two-step approach: we first generate matching candidates using a pre-trained sentence transfo"},"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":"2204.13931","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-29T08:07:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"14e25907658a770505e674d760702d5b62573e007005aebb5ac004c6aebea4c0","abstract_canon_sha256":"1fc602807d4f81b2d581e2c4d159952fc38e0c8c8c6fbe5d9ae10525d8df4957"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:18:55.242924Z","signature_b64":"MiH264m2BSbHL/PQunbjQZgKxU/4kzJMJAETR1sIbBhLFCgEO5Dm/WdyiaeLZDfeo58uDT9KcZEy/1Q54uEeAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2529d5b091709a7fb2eff42fb8c965c3e5351add2fa73ba761f0d04b4a283cc6","last_reissued_at":"2026-07-05T04:18:55.242522Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:18:55.242522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KERMIT -- A Transformer-Based Approach for Knowledge Graph Matching","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Heiko Paulheim, Jan Portisch, Sven Hertling","submitted_at":"2022-04-29T08:07:17Z","abstract_excerpt":"One of the strongest signals for automated matching of knowledge graphs and ontologies are textual concept descriptions. With the rise of transformer-based language models, text comparison based on meaning (rather than lexical features) is available to researchers. However, performing pairwise comparisons of all textual descriptions of concepts in two knowledge graphs is expensive and scales quadratically (or even worse if concepts have more than one description). To overcome this problem, we follow a two-step approach: we first generate matching candidates using a pre-trained sentence transfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.13931","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/2204.13931/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":"2204.13931","created_at":"2026-07-05T04:18:55.242583+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.13931v1","created_at":"2026-07-05T04:18:55.242583+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.13931","created_at":"2026-07-05T04:18:55.242583+00:00"},{"alias_kind":"pith_short_12","alias_value":"EUU5LMEROCNH","created_at":"2026-07-05T04:18:55.242583+00:00"},{"alias_kind":"pith_short_16","alias_value":"EUU5LMEROCNH7MXP","created_at":"2026-07-05T04:18:55.242583+00:00"},{"alias_kind":"pith_short_8","alias_value":"EUU5LMER","created_at":"2026-07-05T04:18:55.242583+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/EUU5LMEROCNH7MXP6QX3RSLFYP","json":"https://pith.science/pith/EUU5LMEROCNH7MXP6QX3RSLFYP.json","graph_json":"https://pith.science/api/pith-number/EUU5LMEROCNH7MXP6QX3RSLFYP/graph.json","events_json":"https://pith.science/api/pith-number/EUU5LMEROCNH7MXP6QX3RSLFYP/events.json","paper":"https://pith.science/paper/EUU5LMER"},"agent_actions":{"view_html":"https://pith.science/pith/EUU5LMEROCNH7MXP6QX3RSLFYP","download_json":"https://pith.science/pith/EUU5LMEROCNH7MXP6QX3RSLFYP.json","view_paper":"https://pith.science/paper/EUU5LMER","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.13931&json=true","fetch_graph":"https://pith.science/api/pith-number/EUU5LMEROCNH7MXP6QX3RSLFYP/graph.json","fetch_events":"https://pith.science/api/pith-number/EUU5LMEROCNH7MXP6QX3RSLFYP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EUU5LMEROCNH7MXP6QX3RSLFYP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EUU5LMEROCNH7MXP6QX3RSLFYP/action/storage_attestation","attest_author":"https://pith.science/pith/EUU5LMEROCNH7MXP6QX3RSLFYP/action/author_attestation","sign_citation":"https://pith.science/pith/EUU5LMEROCNH7MXP6QX3RSLFYP/action/citation_signature","submit_replication":"https://pith.science/pith/EUU5LMEROCNH7MXP6QX3RSLFYP/action/replication_record"}},"created_at":"2026-07-05T04:18:55.242583+00:00","updated_at":"2026-07-05T04:18:55.242583+00:00"}