{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JGEKVMYTXDC2WNA22EDDJ2AJG4","short_pith_number":"pith:JGEKVMYT","schema_version":"1.0","canonical_sha256":"4988aab313b8c5ab341ad10634e8093706523e5ac8fb1dd409abbcf52194739b","source":{"kind":"arxiv","id":"1912.09867","version":2},"attestation_state":"computed","paper":{"title":"Meta-Graph: Few Shot Link Prediction via Meta Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ankit Jain, Avishek Joey Bose, Piero Molino, William L. Hamilton","submitted_at":"2019-12-20T15:09:50Z","abstract_excerpt":"We consider the task of few shot link prediction on graphs. The goal is to learn from a distribution over graphs so that a model is able to quickly infer missing edges in a new graph after a small amount of training. We show that current link prediction methods are generally ill-equipped to handle this task. They cannot effectively transfer learned knowledge from one graph to another and are unable to effectively learn from sparse samples of edges. To address this challenge, we introduce a new gradient-based meta learning framework, Meta-Graph. Our framework leverages higher-order gradients al"},"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":"1912.09867","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-20T15:09:50Z","cross_cats_sorted":["cs.SI","stat.ML"],"title_canon_sha256":"b96bccb0e91786fae752cf712ae53f84a7a1a2b8878a537479444cdc78b06255","abstract_canon_sha256":"f32d83f70474a16e40cece6194da3b9182e0b6a92ad3077b4d64701ce2ec40f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:44:42.001812Z","signature_b64":"S/PYp+CjbM97dsS2Uoq51XAfRlZsRgP6NJVbwxwrs5jM96TE1efejLatEpCWyf0sftLoN+mi1kH1kUksCyMLCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4988aab313b8c5ab341ad10634e8093706523e5ac8fb1dd409abbcf52194739b","last_reissued_at":"2026-07-05T00:44:42.001380Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:44:42.001380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-Graph: Few Shot Link Prediction via Meta Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ankit Jain, Avishek Joey Bose, Piero Molino, William L. Hamilton","submitted_at":"2019-12-20T15:09:50Z","abstract_excerpt":"We consider the task of few shot link prediction on graphs. The goal is to learn from a distribution over graphs so that a model is able to quickly infer missing edges in a new graph after a small amount of training. We show that current link prediction methods are generally ill-equipped to handle this task. They cannot effectively transfer learned knowledge from one graph to another and are unable to effectively learn from sparse samples of edges. To address this challenge, we introduce a new gradient-based meta learning framework, Meta-Graph. Our framework leverages higher-order gradients al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.09867","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/1912.09867/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":"1912.09867","created_at":"2026-07-05T00:44:42.001437+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.09867v2","created_at":"2026-07-05T00:44:42.001437+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.09867","created_at":"2026-07-05T00:44:42.001437+00:00"},{"alias_kind":"pith_short_12","alias_value":"JGEKVMYTXDC2","created_at":"2026-07-05T00:44:42.001437+00:00"},{"alias_kind":"pith_short_16","alias_value":"JGEKVMYTXDC2WNA2","created_at":"2026-07-05T00:44:42.001437+00:00"},{"alias_kind":"pith_short_8","alias_value":"JGEKVMYT","created_at":"2026-07-05T00:44:42.001437+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.00453","citing_title":"TMetaNet: Topological Meta-Learning Framework for Dynamic Link Prediction","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JGEKVMYTXDC2WNA22EDDJ2AJG4","json":"https://pith.science/pith/JGEKVMYTXDC2WNA22EDDJ2AJG4.json","graph_json":"https://pith.science/api/pith-number/JGEKVMYTXDC2WNA22EDDJ2AJG4/graph.json","events_json":"https://pith.science/api/pith-number/JGEKVMYTXDC2WNA22EDDJ2AJG4/events.json","paper":"https://pith.science/paper/JGEKVMYT"},"agent_actions":{"view_html":"https://pith.science/pith/JGEKVMYTXDC2WNA22EDDJ2AJG4","download_json":"https://pith.science/pith/JGEKVMYTXDC2WNA22EDDJ2AJG4.json","view_paper":"https://pith.science/paper/JGEKVMYT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.09867&json=true","fetch_graph":"https://pith.science/api/pith-number/JGEKVMYTXDC2WNA22EDDJ2AJG4/graph.json","fetch_events":"https://pith.science/api/pith-number/JGEKVMYTXDC2WNA22EDDJ2AJG4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JGEKVMYTXDC2WNA22EDDJ2AJG4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JGEKVMYTXDC2WNA22EDDJ2AJG4/action/storage_attestation","attest_author":"https://pith.science/pith/JGEKVMYTXDC2WNA22EDDJ2AJG4/action/author_attestation","sign_citation":"https://pith.science/pith/JGEKVMYTXDC2WNA22EDDJ2AJG4/action/citation_signature","submit_replication":"https://pith.science/pith/JGEKVMYTXDC2WNA22EDDJ2AJG4/action/replication_record"}},"created_at":"2026-07-05T00:44:42.001437+00:00","updated_at":"2026-07-05T00:44:42.001437+00:00"}