{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MGGUIKLMWPQ76YLMDON4URXL5W","short_pith_number":"pith:MGGUIKLM","schema_version":"1.0","canonical_sha256":"618d44296cb3e1ff616c1b9bca46ebeda35e6d2894eade34cafcb37f87a72e44","source":{"kind":"arxiv","id":"2505.19408","version":1},"attestation_state":"computed","paper":{"title":"Future Link Prediction Without Memory or Aggregation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fengran Mo, Lu Yi, Runlin Lei, Yanping Zheng, Yuhang Ye, Zhewei Wei","submitted_at":"2025-05-26T01:53:27Z","abstract_excerpt":"Future link prediction on temporal graphs is a fundamental task with wide applicability in real-world dynamic systems. These scenarios often involve both recurring (seen) and novel (unseen) interactions, requiring models to generalize effectively across both types of edges. However, existing methods typically rely on complex memory and aggregation modules, yet struggle to handle unseen edges. In this paper, we revisit the architecture of existing temporal graph models and identify two essential but overlooked modeling requirements for future link prediction: representing nodes with unique iden"},"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":"2505.19408","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T01:53:27Z","cross_cats_sorted":[],"title_canon_sha256":"d88fc878867deecad33720428deeeb87228dd0d40b01a2d9dbe8d35d6e2b568c","abstract_canon_sha256":"4f6039b91fc5673d09682d8967433b75ab486b8aa9c5acdb4eda3ce56743266e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:29.809575Z","signature_b64":"VTKua0Zp80qCtuh4eSSTjAkZlXyhPdzImj07Lmpaj0mU1su5F0N+6304Lg2/4pfrWVxSb81Gb4UYb2fnX9IwCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"618d44296cb3e1ff616c1b9bca46ebeda35e6d2894eade34cafcb37f87a72e44","last_reissued_at":"2026-07-05T11:09:29.809071Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:29.809071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Future Link Prediction Without Memory or Aggregation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fengran Mo, Lu Yi, Runlin Lei, Yanping Zheng, Yuhang Ye, Zhewei Wei","submitted_at":"2025-05-26T01:53:27Z","abstract_excerpt":"Future link prediction on temporal graphs is a fundamental task with wide applicability in real-world dynamic systems. These scenarios often involve both recurring (seen) and novel (unseen) interactions, requiring models to generalize effectively across both types of edges. However, existing methods typically rely on complex memory and aggregation modules, yet struggle to handle unseen edges. In this paper, we revisit the architecture of existing temporal graph models and identify two essential but overlooked modeling requirements for future link prediction: representing nodes with unique iden"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19408","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/2505.19408/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":"2505.19408","created_at":"2026-07-05T11:09:29.809132+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19408v1","created_at":"2026-07-05T11:09:29.809132+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19408","created_at":"2026-07-05T11:09:29.809132+00:00"},{"alias_kind":"pith_short_12","alias_value":"MGGUIKLMWPQ7","created_at":"2026-07-05T11:09:29.809132+00:00"},{"alias_kind":"pith_short_16","alias_value":"MGGUIKLMWPQ76YLM","created_at":"2026-07-05T11:09:29.809132+00:00"},{"alias_kind":"pith_short_8","alias_value":"MGGUIKLM","created_at":"2026-07-05T11:09:29.809132+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/MGGUIKLMWPQ76YLMDON4URXL5W","json":"https://pith.science/pith/MGGUIKLMWPQ76YLMDON4URXL5W.json","graph_json":"https://pith.science/api/pith-number/MGGUIKLMWPQ76YLMDON4URXL5W/graph.json","events_json":"https://pith.science/api/pith-number/MGGUIKLMWPQ76YLMDON4URXL5W/events.json","paper":"https://pith.science/paper/MGGUIKLM"},"agent_actions":{"view_html":"https://pith.science/pith/MGGUIKLMWPQ76YLMDON4URXL5W","download_json":"https://pith.science/pith/MGGUIKLMWPQ76YLMDON4URXL5W.json","view_paper":"https://pith.science/paper/MGGUIKLM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19408&json=true","fetch_graph":"https://pith.science/api/pith-number/MGGUIKLMWPQ76YLMDON4URXL5W/graph.json","fetch_events":"https://pith.science/api/pith-number/MGGUIKLMWPQ76YLMDON4URXL5W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MGGUIKLMWPQ76YLMDON4URXL5W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MGGUIKLMWPQ76YLMDON4URXL5W/action/storage_attestation","attest_author":"https://pith.science/pith/MGGUIKLMWPQ76YLMDON4URXL5W/action/author_attestation","sign_citation":"https://pith.science/pith/MGGUIKLMWPQ76YLMDON4URXL5W/action/citation_signature","submit_replication":"https://pith.science/pith/MGGUIKLMWPQ76YLMDON4URXL5W/action/replication_record"}},"created_at":"2026-07-05T11:09:29.809132+00:00","updated_at":"2026-07-05T11:09:29.809132+00:00"}