{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:26RZWJJKLTHOWRVJXFLEEKSBLF","short_pith_number":"pith:26RZWJJK","schema_version":"1.0","canonical_sha256":"d7a39b252a5cceeb46a9b956422a4159484d13a88a7cf5a3ea2d695349c6bc7b","source":{"kind":"arxiv","id":"2606.10287","version":1},"attestation_state":"computed","paper":{"title":"When Metrics Disagree: A Meta-Analysis of Knowledge-Graph-Completion Model Benchmarking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Ajaz Ahmad Bhat, Haji Gul","submitted_at":"2026-06-09T01:20:43Z","abstract_excerpt":"Evaluating Knowledge Graph Completion (KGC) models remains challenging because standard assessment relies on isolated rank-based metrics such as MRR, Hits$@$k, and Mean Rank, which often produce conflicting model orderings across datasets. A model that leads on MRR may trail on Hits@1, and strong performance on one dataset may not generalize to another. This fragmentation hinders comparison, enables selective reporting, and obscures real progress. We reframe KGC evaluation as a Multi-Criteria Decision-Making (MCDM) problem and present a meta-analysis of seven aggregators across five tests: con"},"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":"2606.10287","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T01:20:43Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d62b8f8a463b32bb65a77bbfaec8bef99597f2ef82500a93300ef7daeebddcbe","abstract_canon_sha256":"d4edfd70a4e0a5aaaa46917af67f9f28eecb55bcf25d760a3d048a9f11807193"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:09.055128Z","signature_b64":"Bi3I8QqswDs1p8hmi7cQ9GSFQrAqHO5KeSYRG8uwWTWNxN5ZgaoFuekbem98xKBpcHKJjfGCLTlKONht2HVuCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7a39b252a5cceeb46a9b956422a4159484d13a88a7cf5a3ea2d695349c6bc7b","last_reissued_at":"2026-06-10T01:10:09.054181Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:09.054181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Metrics Disagree: A Meta-Analysis of Knowledge-Graph-Completion Model Benchmarking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Ajaz Ahmad Bhat, Haji Gul","submitted_at":"2026-06-09T01:20:43Z","abstract_excerpt":"Evaluating Knowledge Graph Completion (KGC) models remains challenging because standard assessment relies on isolated rank-based metrics such as MRR, Hits$@$k, and Mean Rank, which often produce conflicting model orderings across datasets. A model that leads on MRR may trail on Hits@1, and strong performance on one dataset may not generalize to another. This fragmentation hinders comparison, enables selective reporting, and obscures real progress. We reframe KGC evaluation as a Multi-Criteria Decision-Making (MCDM) problem and present a meta-analysis of seven aggregators across five tests: con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10287","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/2606.10287/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":"2606.10287","created_at":"2026-06-10T01:10:09.054342+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10287v1","created_at":"2026-06-10T01:10:09.054342+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10287","created_at":"2026-06-10T01:10:09.054342+00:00"},{"alias_kind":"pith_short_12","alias_value":"26RZWJJKLTHO","created_at":"2026-06-10T01:10:09.054342+00:00"},{"alias_kind":"pith_short_16","alias_value":"26RZWJJKLTHOWRVJ","created_at":"2026-06-10T01:10:09.054342+00:00"},{"alias_kind":"pith_short_8","alias_value":"26RZWJJK","created_at":"2026-06-10T01:10:09.054342+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/26RZWJJKLTHOWRVJXFLEEKSBLF","json":"https://pith.science/pith/26RZWJJKLTHOWRVJXFLEEKSBLF.json","graph_json":"https://pith.science/api/pith-number/26RZWJJKLTHOWRVJXFLEEKSBLF/graph.json","events_json":"https://pith.science/api/pith-number/26RZWJJKLTHOWRVJXFLEEKSBLF/events.json","paper":"https://pith.science/paper/26RZWJJK"},"agent_actions":{"view_html":"https://pith.science/pith/26RZWJJKLTHOWRVJXFLEEKSBLF","download_json":"https://pith.science/pith/26RZWJJKLTHOWRVJXFLEEKSBLF.json","view_paper":"https://pith.science/paper/26RZWJJK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10287&json=true","fetch_graph":"https://pith.science/api/pith-number/26RZWJJKLTHOWRVJXFLEEKSBLF/graph.json","fetch_events":"https://pith.science/api/pith-number/26RZWJJKLTHOWRVJXFLEEKSBLF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/26RZWJJKLTHOWRVJXFLEEKSBLF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/26RZWJJKLTHOWRVJXFLEEKSBLF/action/storage_attestation","attest_author":"https://pith.science/pith/26RZWJJKLTHOWRVJXFLEEKSBLF/action/author_attestation","sign_citation":"https://pith.science/pith/26RZWJJKLTHOWRVJXFLEEKSBLF/action/citation_signature","submit_replication":"https://pith.science/pith/26RZWJJKLTHOWRVJXFLEEKSBLF/action/replication_record"}},"created_at":"2026-06-10T01:10:09.054342+00:00","updated_at":"2026-06-10T01:10:09.054342+00:00"}