{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:UK7CQ4OFYYWLLRI355UFNXVUFX","short_pith_number":"pith:UK7CQ4OF","schema_version":"1.0","canonical_sha256":"a2be2871c5c62cb5c51bef6856deb42dcffb45ed35bc74b098eb28b0ab804232","source":{"kind":"arxiv","id":"2203.01520","version":2},"attestation_state":"computed","paper":{"title":"An Open Challenge for Inductive Link Prediction on Knowledge Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Charles Tapley Hoyt, Max Berrendorf, Mikhail Galkin","submitted_at":"2022-03-03T05:24:09Z","abstract_excerpt":"An emerging trend in representation learning over knowledge graphs (KGs) moves beyond transductive link prediction tasks over a fixed set of known entities in favor of inductive tasks that imply training on one graph and performing inference over a new graph with unseen entities. In inductive setups, node features are often not available and training shallow entity embedding matrices is meaningless as they cannot be used at inference time with unseen entities. Despite the growing interest, there are not enough benchmarks for evaluating inductive representation learning methods. In this work, w"},"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":"2203.01520","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-03T05:24:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"99e2d38ff6ea0840b3476c62c8709b48aa1460ded0a032d6e4d38973197d5cf4","abstract_canon_sha256":"4983297cd1799e0e7a29889e3676e5c895ec1c0e08890f30a25807c3f4a81fd0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:15:29.273757Z","signature_b64":"B9ehEuIzD7yoVcKtYThAzYUCrtpp3aQFfIKkijYtuQw+F6QepM0sfWy0rU0NN4t2UhypBrA8Et3Q5q9LfXsFDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2be2871c5c62cb5c51bef6856deb42dcffb45ed35bc74b098eb28b0ab804232","last_reissued_at":"2026-07-05T04:15:29.273337Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:15:29.273337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Open Challenge for Inductive Link Prediction on Knowledge Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Charles Tapley Hoyt, Max Berrendorf, Mikhail Galkin","submitted_at":"2022-03-03T05:24:09Z","abstract_excerpt":"An emerging trend in representation learning over knowledge graphs (KGs) moves beyond transductive link prediction tasks over a fixed set of known entities in favor of inductive tasks that imply training on one graph and performing inference over a new graph with unseen entities. In inductive setups, node features are often not available and training shallow entity embedding matrices is meaningless as they cannot be used at inference time with unseen entities. Despite the growing interest, there are not enough benchmarks for evaluating inductive representation learning methods. In this work, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.01520","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/2203.01520/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":"2203.01520","created_at":"2026-07-05T04:15:29.273400+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.01520v2","created_at":"2026-07-05T04:15:29.273400+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.01520","created_at":"2026-07-05T04:15:29.273400+00:00"},{"alias_kind":"pith_short_12","alias_value":"UK7CQ4OFYYWL","created_at":"2026-07-05T04:15:29.273400+00:00"},{"alias_kind":"pith_short_16","alias_value":"UK7CQ4OFYYWLLRI3","created_at":"2026-07-05T04:15:29.273400+00:00"},{"alias_kind":"pith_short_8","alias_value":"UK7CQ4OF","created_at":"2026-07-05T04:15:29.273400+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14907","citing_title":"KGPFN: Unlocking the Potential of Knowledge Graph Foundation Model via In-Context Learning","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18001","citing_title":"Half a Link can Be Enough to Predict a Whole Link: Understanding Generalization in Knowledge Graph Foundation Models","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UK7CQ4OFYYWLLRI355UFNXVUFX","json":"https://pith.science/pith/UK7CQ4OFYYWLLRI355UFNXVUFX.json","graph_json":"https://pith.science/api/pith-number/UK7CQ4OFYYWLLRI355UFNXVUFX/graph.json","events_json":"https://pith.science/api/pith-number/UK7CQ4OFYYWLLRI355UFNXVUFX/events.json","paper":"https://pith.science/paper/UK7CQ4OF"},"agent_actions":{"view_html":"https://pith.science/pith/UK7CQ4OFYYWLLRI355UFNXVUFX","download_json":"https://pith.science/pith/UK7CQ4OFYYWLLRI355UFNXVUFX.json","view_paper":"https://pith.science/paper/UK7CQ4OF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.01520&json=true","fetch_graph":"https://pith.science/api/pith-number/UK7CQ4OFYYWLLRI355UFNXVUFX/graph.json","fetch_events":"https://pith.science/api/pith-number/UK7CQ4OFYYWLLRI355UFNXVUFX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UK7CQ4OFYYWLLRI355UFNXVUFX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UK7CQ4OFYYWLLRI355UFNXVUFX/action/storage_attestation","attest_author":"https://pith.science/pith/UK7CQ4OFYYWLLRI355UFNXVUFX/action/author_attestation","sign_citation":"https://pith.science/pith/UK7CQ4OFYYWLLRI355UFNXVUFX/action/citation_signature","submit_replication":"https://pith.science/pith/UK7CQ4OFYYWLLRI355UFNXVUFX/action/replication_record"}},"created_at":"2026-07-05T04:15:29.273400+00:00","updated_at":"2026-07-05T04:15:29.273400+00:00"}