{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NL7B4V4HFYETTA7EWSCAXY2RPD","short_pith_number":"pith:NL7B4V4H","schema_version":"1.0","canonical_sha256":"6afe1e57872e093983e4b4840be35178d0142dd0372193ec02745c36e53f81ad","source":{"kind":"arxiv","id":"2503.11737","version":4},"attestation_state":"computed","paper":{"title":"Multi-View Node Pruning for Accurate Graph Representation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Doheon Lee, Hanjin Kim, Jiseong Park, Jueun Choi, Seojin Kim, Sung Ju Hwang","submitted_at":"2025-03-14T14:44:54Z","abstract_excerpt":"Graph pooling, which compresses a whole graph into a smaller coarsened graph, is an essential component of graph representation learning. To efficiently compress a given graph, graph pooling methods often drop their nodes with attention-based scoring with the task loss. However, this often results in simply removing nodes with lower degrees without consideration of their feature-level relevance to the given task. To fix this problem, we propose a Multi-View Pruning(MVP), a graph pruning method based on a multi-view framework and reconstruction loss. Given a graph, MVP first constructs multiple"},"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":"2503.11737","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-14T14:44:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"568916bbeb7c28cf13ff874a6f294086d91994d8bfb49d1aa69d7fecfceb4d48","abstract_canon_sha256":"6c11e9cc92d59ddc05b2b17c006055373edab72e02309d48fe0bc8f96b094d30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:27.973633Z","signature_b64":"A+x5tHCFRWK5qs6l5P9q4SJF0LLpfzvJsA1EwcFhVOLsH5XVl76Bpik/EGihwgUqSexqBqowj/XzFuxnGy3kDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6afe1e57872e093983e4b4840be35178d0142dd0372193ec02745c36e53f81ad","last_reissued_at":"2026-07-05T11:38:27.973094Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:27.973094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-View Node Pruning for Accurate Graph Representation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Doheon Lee, Hanjin Kim, Jiseong Park, Jueun Choi, Seojin Kim, Sung Ju Hwang","submitted_at":"2025-03-14T14:44:54Z","abstract_excerpt":"Graph pooling, which compresses a whole graph into a smaller coarsened graph, is an essential component of graph representation learning. To efficiently compress a given graph, graph pooling methods often drop their nodes with attention-based scoring with the task loss. However, this often results in simply removing nodes with lower degrees without consideration of their feature-level relevance to the given task. To fix this problem, we propose a Multi-View Pruning(MVP), a graph pruning method based on a multi-view framework and reconstruction loss. Given a graph, MVP first constructs multiple"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.11737","kind":"arxiv","version":4},"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/2503.11737/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":"2503.11737","created_at":"2026-07-05T11:38:27.973157+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.11737v4","created_at":"2026-07-05T11:38:27.973157+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.11737","created_at":"2026-07-05T11:38:27.973157+00:00"},{"alias_kind":"pith_short_12","alias_value":"NL7B4V4HFYET","created_at":"2026-07-05T11:38:27.973157+00:00"},{"alias_kind":"pith_short_16","alias_value":"NL7B4V4HFYETTA7E","created_at":"2026-07-05T11:38:27.973157+00:00"},{"alias_kind":"pith_short_8","alias_value":"NL7B4V4H","created_at":"2026-07-05T11:38:27.973157+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/NL7B4V4HFYETTA7EWSCAXY2RPD","json":"https://pith.science/pith/NL7B4V4HFYETTA7EWSCAXY2RPD.json","graph_json":"https://pith.science/api/pith-number/NL7B4V4HFYETTA7EWSCAXY2RPD/graph.json","events_json":"https://pith.science/api/pith-number/NL7B4V4HFYETTA7EWSCAXY2RPD/events.json","paper":"https://pith.science/paper/NL7B4V4H"},"agent_actions":{"view_html":"https://pith.science/pith/NL7B4V4HFYETTA7EWSCAXY2RPD","download_json":"https://pith.science/pith/NL7B4V4HFYETTA7EWSCAXY2RPD.json","view_paper":"https://pith.science/paper/NL7B4V4H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.11737&json=true","fetch_graph":"https://pith.science/api/pith-number/NL7B4V4HFYETTA7EWSCAXY2RPD/graph.json","fetch_events":"https://pith.science/api/pith-number/NL7B4V4HFYETTA7EWSCAXY2RPD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NL7B4V4HFYETTA7EWSCAXY2RPD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NL7B4V4HFYETTA7EWSCAXY2RPD/action/storage_attestation","attest_author":"https://pith.science/pith/NL7B4V4HFYETTA7EWSCAXY2RPD/action/author_attestation","sign_citation":"https://pith.science/pith/NL7B4V4HFYETTA7EWSCAXY2RPD/action/citation_signature","submit_replication":"https://pith.science/pith/NL7B4V4HFYETTA7EWSCAXY2RPD/action/replication_record"}},"created_at":"2026-07-05T11:38:27.973157+00:00","updated_at":"2026-07-05T11:38:27.973157+00:00"}