{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4MXK7S4PQMXDLX25UBDFILUBI2","short_pith_number":"pith:4MXK7S4P","schema_version":"1.0","canonical_sha256":"e32eafcb8f832e35df5da046542e8146a1ae2b144ee889f9c82b913760f91cea","source":{"kind":"arxiv","id":"2412.11739","version":1},"attestation_state":"computed","paper":{"title":"Asymmetric Learning for Spectral Graph Neural Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fangbing Liu, Qing Wang","submitted_at":"2024-12-16T13:00:49Z","abstract_excerpt":"Optimizing spectral graph neural networks (GNNs) remains a critical challenge in the field, yet the underlying processes are not well understood. In this paper, we investigate the inherent differences between graph convolution parameters and feature transformation parameters in spectral GNNs and their impact on the optimization landscape. Our analysis reveals that these differences contribute to a poorly conditioned problem, resulting in suboptimal performance. To address this issue, we introduce the concept of the block condition number of the Hessian matrix, which characterizes the difficult"},"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":"2412.11739","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-16T13:00:49Z","cross_cats_sorted":[],"title_canon_sha256":"eaff196d76590f2e351d2ba4db86803f333221612b0dc56092c95350f12c97fa","abstract_canon_sha256":"7ac12e93b740507383d2a8d5653f6315eabe2348b7765a07a109736cd0a516ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:50.974071Z","signature_b64":"mXWJ18V3Sy3UM+CjG7+eavXviRZptlPTlJDIJ23YwQn6A4hASV+GA5zFo5s2ThdE/XqfzQayNAxyHRa/y2XGAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e32eafcb8f832e35df5da046542e8146a1ae2b144ee889f9c82b913760f91cea","last_reissued_at":"2026-07-05T09:49:50.973599Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:50.973599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Asymmetric Learning for Spectral Graph Neural Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fangbing Liu, Qing Wang","submitted_at":"2024-12-16T13:00:49Z","abstract_excerpt":"Optimizing spectral graph neural networks (GNNs) remains a critical challenge in the field, yet the underlying processes are not well understood. In this paper, we investigate the inherent differences between graph convolution parameters and feature transformation parameters in spectral GNNs and their impact on the optimization landscape. Our analysis reveals that these differences contribute to a poorly conditioned problem, resulting in suboptimal performance. To address this issue, we introduce the concept of the block condition number of the Hessian matrix, which characterizes the difficult"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11739","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/2412.11739/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":"2412.11739","created_at":"2026-07-05T09:49:50.973659+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.11739v1","created_at":"2026-07-05T09:49:50.973659+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11739","created_at":"2026-07-05T09:49:50.973659+00:00"},{"alias_kind":"pith_short_12","alias_value":"4MXK7S4PQMXD","created_at":"2026-07-05T09:49:50.973659+00:00"},{"alias_kind":"pith_short_16","alias_value":"4MXK7S4PQMXDLX25","created_at":"2026-07-05T09:49:50.973659+00:00"},{"alias_kind":"pith_short_8","alias_value":"4MXK7S4P","created_at":"2026-07-05T09:49:50.973659+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/4MXK7S4PQMXDLX25UBDFILUBI2","json":"https://pith.science/pith/4MXK7S4PQMXDLX25UBDFILUBI2.json","graph_json":"https://pith.science/api/pith-number/4MXK7S4PQMXDLX25UBDFILUBI2/graph.json","events_json":"https://pith.science/api/pith-number/4MXK7S4PQMXDLX25UBDFILUBI2/events.json","paper":"https://pith.science/paper/4MXK7S4P"},"agent_actions":{"view_html":"https://pith.science/pith/4MXK7S4PQMXDLX25UBDFILUBI2","download_json":"https://pith.science/pith/4MXK7S4PQMXDLX25UBDFILUBI2.json","view_paper":"https://pith.science/paper/4MXK7S4P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.11739&json=true","fetch_graph":"https://pith.science/api/pith-number/4MXK7S4PQMXDLX25UBDFILUBI2/graph.json","fetch_events":"https://pith.science/api/pith-number/4MXK7S4PQMXDLX25UBDFILUBI2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4MXK7S4PQMXDLX25UBDFILUBI2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4MXK7S4PQMXDLX25UBDFILUBI2/action/storage_attestation","attest_author":"https://pith.science/pith/4MXK7S4PQMXDLX25UBDFILUBI2/action/author_attestation","sign_citation":"https://pith.science/pith/4MXK7S4PQMXDLX25UBDFILUBI2/action/citation_signature","submit_replication":"https://pith.science/pith/4MXK7S4PQMXDLX25UBDFILUBI2/action/replication_record"}},"created_at":"2026-07-05T09:49:50.973659+00:00","updated_at":"2026-07-05T09:49:50.973659+00:00"}