{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XVFD2TNJJX2XMRCPPSF2PAPDMB","short_pith_number":"pith:XVFD2TNJ","canonical_record":{"source":{"id":"2605.05759","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-07T06:53:49Z","cross_cats_sorted":[],"title_canon_sha256":"a5da1a32f16db056e2dc56860ddde4bd8f17ec8abfd3d5d87573cfd8777cc097","abstract_canon_sha256":"fc85b9df44f1ab81b55b85a085ca4e31ea90e15b78b343524dc15af6a9b5b031"},"schema_version":"1.0"},"canonical_sha256":"bd4a3d4da94df576444f7c8ba781e3604cc8f13a039af604728b6c9024b9f159","source":{"kind":"arxiv","id":"2605.05759","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.05759","created_at":"2026-05-26T01:03:32Z"},{"alias_kind":"arxiv_version","alias_value":"2605.05759v2","created_at":"2026-05-26T01:03:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.05759","created_at":"2026-05-26T01:03:32Z"},{"alias_kind":"pith_short_12","alias_value":"XVFD2TNJJX2X","created_at":"2026-05-26T01:03:32Z"},{"alias_kind":"pith_short_16","alias_value":"XVFD2TNJJX2XMRCP","created_at":"2026-05-26T01:03:32Z"},{"alias_kind":"pith_short_8","alias_value":"XVFD2TNJ","created_at":"2026-05-26T01:03:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XVFD2TNJJX2XMRCPPSF2PAPDMB","target":"record","payload":{"canonical_record":{"source":{"id":"2605.05759","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-07T06:53:49Z","cross_cats_sorted":[],"title_canon_sha256":"a5da1a32f16db056e2dc56860ddde4bd8f17ec8abfd3d5d87573cfd8777cc097","abstract_canon_sha256":"fc85b9df44f1ab81b55b85a085ca4e31ea90e15b78b343524dc15af6a9b5b031"},"schema_version":"1.0"},"canonical_sha256":"bd4a3d4da94df576444f7c8ba781e3604cc8f13a039af604728b6c9024b9f159","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:32.483930Z","signature_b64":"Y8X17VUV0lS10Qryv0ePj40RWIKp3+8MUEtd9tshNY8HKkQz1ZvOFSefyZoeVKsS0YQXG1wcyX6B27aspd65Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd4a3d4da94df576444f7c8ba781e3604cc8f13a039af604728b6c9024b9f159","last_reissued_at":"2026-05-26T01:03:32.483238Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:32.483238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.05759","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T01:03:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DR9666HET9I62CRIsiiS12nivBbtnSGUs0DBabQMs5jglOx2pNX9s2k9Tqrjpo/vdP9SMgkjreNu2YYsTnBOBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T21:40:34.514441Z"},"content_sha256":"52880adb939c84a62ef151de17920e6918a68bd3f27b63adedca89b0a08ab7e2","schema_version":"1.0","event_id":"sha256:52880adb939c84a62ef151de17920e6918a68bd3f27b63adedca89b0a08ab7e2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XVFD2TNJJX2XMRCPPSF2PAPDMB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Full-Spectrum Graph Neural Networks: Expressive and Scalable","license":"http://creativecommons.org/licenses/by/4.0/","headline":"FSpecGNN lifts classical spectral GNNs to the node-pair domain using bivariate filters over eigenvalue pairs, recovering the old models as a diagonal case while reaching universal approximation of node-pair signals.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Deyu Bo, Kelin Xia, Longlong Li, Xiaohan Wang","submitted_at":"2026-05-07T06:53:49Z","abstract_excerpt":"It is well established that spectral graph neural networks (GNNs) can universally approximate node signals; however, their expressive power remains bounded by the 1-dimensional Weisfeiler-Lehman test, which is mirrored in their lack of universality for higher-order signals. To go beyond this bound, we propose the Full-Spectrum GNNs (FSpecGNNs), a second-order generalization of classical spectral GNNs. FSpecGNN advances spectral filtering from two perspectives: (1) it lifts signals from the node domain to the node-pair domain; and (2) it extends the univariate spectral filter over eigenvalues t"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We show that classical spectral GNNs arise as a diagonal special case of FSpecGNN, and prove that FSpecGNN can be at most as expressive as Local 2-GNN while universally approximating node-pair signals, the latter being particularly beneficial for heterophilic graph learning.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the low-rank approximation of the full-spectrum convolution preserves both the universal approximation property for node-pair signals and the claimed expressivity bound without introducing errors that invalidate the theoretical results on realistic graphs.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"FSpecGNN generalizes spectral GNNs to node-pair domain with bivariate filters, achieving universal approximation of node-pair signals while remaining at most as expressive as Local 2-GNN and admitting scalable low-rank implementations.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"FSpecGNN lifts classical spectral GNNs to the node-pair domain using bivariate filters over eigenvalue pairs, recovering the old models as a diagonal case while reaching universal approximation of node-pair signals.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"cc8774462bd94fcd0dcb89c4e1b9cbf9c6a15aa3f09a984132327088f8764a07"},"source":{"id":"2605.05759","kind":"arxiv","version":2},"verdict":{"id":"5707001d-d420-43c5-b9df-cfa82b3fc18d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T14:51:22.625269Z","strongest_claim":"We show that classical spectral GNNs arise as a diagonal special case of FSpecGNN, and prove that FSpecGNN can be at most as expressive as Local 2-GNN while universally approximating node-pair signals, the latter being particularly beneficial for heterophilic graph learning.","one_line_summary":"FSpecGNN generalizes spectral GNNs to node-pair domain with bivariate filters, achieving universal approximation of node-pair signals while remaining at most as expressive as Local 2-GNN and admitting scalable low-rank implementations.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the low-rank approximation of the full-spectrum convolution preserves both the universal approximation property for node-pair signals and the claimed expressivity bound without introducing errors that invalidate the theoretical results on realistic graphs.","pith_extraction_headline":"FSpecGNN lifts classical spectral GNNs to the node-pair domain using bivariate filters over eigenvalue pairs, recovering the old models as a diagonal case while reaching universal approximation of node-pair signals."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.05759/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T13:42:04.674408Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-20T09:35:50.470497Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T20:01:19.501599Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T13:17:58.367695Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"6f7688238a30e38ac5420e8d728b6f4c77f1d935abbb05b1882d10561c16fee0"},"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"},"verdict_id":"5707001d-d420-43c5-b9df-cfa82b3fc18d"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T01:03:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FZGxxGWXks4yQfhlbm6V3wEkjn1FilCwt8YfQ3zp2Hq9r6wpC97hPmMyQ9d3cG7bvYRcLCNzf1YfGLR9QsuoAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T21:40:34.515491Z"},"content_sha256":"bce274599d7a95f4c85f5662121b3d29d498f298f0abf7fc3f0eaf76bb6adb90","schema_version":"1.0","event_id":"sha256:bce274599d7a95f4c85f5662121b3d29d498f298f0abf7fc3f0eaf76bb6adb90"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XVFD2TNJJX2XMRCPPSF2PAPDMB/bundle.json","state_url":"https://pith.science/pith/XVFD2TNJJX2XMRCPPSF2PAPDMB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XVFD2TNJJX2XMRCPPSF2PAPDMB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-28T21:40:34Z","links":{"resolver":"https://pith.science/pith/XVFD2TNJJX2XMRCPPSF2PAPDMB","bundle":"https://pith.science/pith/XVFD2TNJJX2XMRCPPSF2PAPDMB/bundle.json","state":"https://pith.science/pith/XVFD2TNJJX2XMRCPPSF2PAPDMB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XVFD2TNJJX2XMRCPPSF2PAPDMB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XVFD2TNJJX2XMRCPPSF2PAPDMB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fc85b9df44f1ab81b55b85a085ca4e31ea90e15b78b343524dc15af6a9b5b031","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-07T06:53:49Z","title_canon_sha256":"a5da1a32f16db056e2dc56860ddde4bd8f17ec8abfd3d5d87573cfd8777cc097"},"schema_version":"1.0","source":{"id":"2605.05759","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.05759","created_at":"2026-05-26T01:03:32Z"},{"alias_kind":"arxiv_version","alias_value":"2605.05759v2","created_at":"2026-05-26T01:03:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.05759","created_at":"2026-05-26T01:03:32Z"},{"alias_kind":"pith_short_12","alias_value":"XVFD2TNJJX2X","created_at":"2026-05-26T01:03:32Z"},{"alias_kind":"pith_short_16","alias_value":"XVFD2TNJJX2XMRCP","created_at":"2026-05-26T01:03:32Z"},{"alias_kind":"pith_short_8","alias_value":"XVFD2TNJ","created_at":"2026-05-26T01:03:32Z"}],"graph_snapshots":[{"event_id":"sha256:bce274599d7a95f4c85f5662121b3d29d498f298f0abf7fc3f0eaf76bb6adb90","target":"graph","created_at":"2026-05-26T01:03:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We show that classical spectral GNNs arise as a diagonal special case of FSpecGNN, and prove that FSpecGNN can be at most as expressive as Local 2-GNN while universally approximating node-pair signals, the latter being particularly beneficial for heterophilic graph learning."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the low-rank approximation of the full-spectrum convolution preserves both the universal approximation property for node-pair signals and the claimed expressivity bound without introducing errors that invalidate the theoretical results on realistic graphs."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"FSpecGNN generalizes spectral GNNs to node-pair domain with bivariate filters, achieving universal approximation of node-pair signals while remaining at most as expressive as Local 2-GNN and admitting scalable low-rank implementations."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"FSpecGNN lifts classical spectral GNNs to the node-pair domain using bivariate filters over eigenvalue pairs, recovering the old models as a diagonal case while reaching universal approximation of node-pair signals."}],"snapshot_sha256":"cc8774462bd94fcd0dcb89c4e1b9cbf9c6a15aa3f09a984132327088f8764a07"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T13:42:04.674408Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T09:35:50.470497Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T20:01:19.501599Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T13:17:58.367695Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.05759/integrity.json","findings":[],"snapshot_sha256":"6f7688238a30e38ac5420e8d728b6f4c77f1d935abbb05b1882d10561c16fee0","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"It is well established that spectral graph neural networks (GNNs) can universally approximate node signals; however, their expressive power remains bounded by the 1-dimensional Weisfeiler-Lehman test, which is mirrored in their lack of universality for higher-order signals. To go beyond this bound, we propose the Full-Spectrum GNNs (FSpecGNNs), a second-order generalization of classical spectral GNNs. FSpecGNN advances spectral filtering from two perspectives: (1) it lifts signals from the node domain to the node-pair domain; and (2) it extends the univariate spectral filter over eigenvalues t","authors_text":"Deyu Bo, Kelin Xia, Longlong Li, Xiaohan Wang","cross_cats":[],"headline":"FSpecGNN lifts classical spectral GNNs to the node-pair domain using bivariate filters over eigenvalue pairs, recovering the old models as a diagonal case while reaching universal approximation of node-pair signals.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-07T06:53:49Z","title":"Full-Spectrum Graph Neural Networks: Expressive and Scalable"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.05759","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-08T14:51:22.625269Z","id":"5707001d-d420-43c5-b9df-cfa82b3fc18d","model_set":{"reader":"grok-4.3"},"one_line_summary":"FSpecGNN generalizes spectral GNNs to node-pair domain with bivariate filters, achieving universal approximation of node-pair signals while remaining at most as expressive as Local 2-GNN and admitting scalable low-rank implementations.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"FSpecGNN lifts classical spectral GNNs to the node-pair domain using bivariate filters over eigenvalue pairs, recovering the old models as a diagonal case while reaching universal approximation of node-pair signals.","strongest_claim":"We show that classical spectral GNNs arise as a diagonal special case of FSpecGNN, and prove that FSpecGNN can be at most as expressive as Local 2-GNN while universally approximating node-pair signals, the latter being particularly beneficial for heterophilic graph learning.","weakest_assumption":"That the low-rank approximation of the full-spectrum convolution preserves both the universal approximation property for node-pair signals and the claimed expressivity bound without introducing errors that invalidate the theoretical results on realistic graphs."}},"verdict_id":"5707001d-d420-43c5-b9df-cfa82b3fc18d"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:52880adb939c84a62ef151de17920e6918a68bd3f27b63adedca89b0a08ab7e2","target":"record","created_at":"2026-05-26T01:03:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"fc85b9df44f1ab81b55b85a085ca4e31ea90e15b78b343524dc15af6a9b5b031","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-07T06:53:49Z","title_canon_sha256":"a5da1a32f16db056e2dc56860ddde4bd8f17ec8abfd3d5d87573cfd8777cc097"},"schema_version":"1.0","source":{"id":"2605.05759","kind":"arxiv","version":2}},"canonical_sha256":"bd4a3d4da94df576444f7c8ba781e3604cc8f13a039af604728b6c9024b9f159","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd4a3d4da94df576444f7c8ba781e3604cc8f13a039af604728b6c9024b9f159","first_computed_at":"2026-05-26T01:03:32.483238Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:32.483238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y8X17VUV0lS10Qryv0ePj40RWIKp3+8MUEtd9tshNY8HKkQz1ZvOFSefyZoeVKsS0YQXG1wcyX6B27aspd65Cw==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:32.483930Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.05759","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52880adb939c84a62ef151de17920e6918a68bd3f27b63adedca89b0a08ab7e2","sha256:bce274599d7a95f4c85f5662121b3d29d498f298f0abf7fc3f0eaf76bb6adb90"],"state_sha256":"f25c3c6759edef174a0b28a112e2baca4a4014d56a0b50d6832674dbee80e803"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KcOw1ZTktaIwU0BhdddoeB6OM2hmkqzWwXDEJlUohRAfpIFSfXdTNhcVozaIDcXSlqLkad0ZsTD5arGg+0tRDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T21:40:34.520034Z","bundle_sha256":"3a0367f5b68d372be35dd72ec8998a89c6b50f2020df3b3a763680491b72eac8"}}