{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:UA25CK3KVPHZL5O7XEVU6DU33W","short_pith_number":"pith:UA25CK3K","schema_version":"1.0","canonical_sha256":"a035d12b6aabcf95f5dfb92b4f0e9bdd8c5f10d2eba014dc6796f8f8c190328c","source":{"kind":"arxiv","id":"2012.15024","version":2},"attestation_state":"computed","paper":{"title":"Adaptive Graph Diffusion Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chuxiong Sun, Hongming Gu, Jie Hu, Jinpeng Chen, Mingchuan Yang","submitted_at":"2020-12-30T03:43:04Z","abstract_excerpt":"Graph Neural Networks (GNNs) have received much attention in the graph deep learning domain. However, recent research empirically and theoretically shows that deep GNNs suffer from over-fitting and over-smoothing problems. The usual solutions either cannot solve extensive runtime of deep GNNs or restrict graph convolution in the same feature space. We propose the Adaptive Graph Diffusion Networks (AGDNs) which perform multi-layer generalized graph diffusion in different feature spaces with moderate complexity and runtime. Standard graph diffusion methods combine large and dense powers of the t"},"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":"2012.15024","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-30T03:43:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2e1487b403d1d7cd105a88982655620170b680a885071d163f5ea7a768312386","abstract_canon_sha256":"63974f92e8cfc3262459442a1b78ad30d141e504d915760565169f21d82be00a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:54:00.362950Z","signature_b64":"i6hnKnzZAoisJ0EQWck27v/i5FsmyIjyJ9bvqbWmD1ggSQyxzleEakmWwiDYPKFk/CQWTlZVQtn7NA1MY5wOCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a035d12b6aabcf95f5dfb92b4f0e9bdd8c5f10d2eba014dc6796f8f8c190328c","last_reissued_at":"2026-07-05T04:54:00.362520Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:54:00.362520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Graph Diffusion Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chuxiong Sun, Hongming Gu, Jie Hu, Jinpeng Chen, Mingchuan Yang","submitted_at":"2020-12-30T03:43:04Z","abstract_excerpt":"Graph Neural Networks (GNNs) have received much attention in the graph deep learning domain. However, recent research empirically and theoretically shows that deep GNNs suffer from over-fitting and over-smoothing problems. The usual solutions either cannot solve extensive runtime of deep GNNs or restrict graph convolution in the same feature space. We propose the Adaptive Graph Diffusion Networks (AGDNs) which perform multi-layer generalized graph diffusion in different feature spaces with moderate complexity and runtime. Standard graph diffusion methods combine large and dense powers of the t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.15024","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/2012.15024/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":"2012.15024","created_at":"2026-07-05T04:54:00.362578+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.15024v2","created_at":"2026-07-05T04:54:00.362578+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.15024","created_at":"2026-07-05T04:54:00.362578+00:00"},{"alias_kind":"pith_short_12","alias_value":"UA25CK3KVPHZ","created_at":"2026-07-05T04:54:00.362578+00:00"},{"alias_kind":"pith_short_16","alias_value":"UA25CK3KVPHZL5O7","created_at":"2026-07-05T04:54:00.362578+00:00"},{"alias_kind":"pith_short_8","alias_value":"UA25CK3K","created_at":"2026-07-05T04:54:00.362578+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01660","citing_title":"Gate the Filter, Not the Message: Node-Channel Mixtures for Pre-Propagation GNNs","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UA25CK3KVPHZL5O7XEVU6DU33W","json":"https://pith.science/pith/UA25CK3KVPHZL5O7XEVU6DU33W.json","graph_json":"https://pith.science/api/pith-number/UA25CK3KVPHZL5O7XEVU6DU33W/graph.json","events_json":"https://pith.science/api/pith-number/UA25CK3KVPHZL5O7XEVU6DU33W/events.json","paper":"https://pith.science/paper/UA25CK3K"},"agent_actions":{"view_html":"https://pith.science/pith/UA25CK3KVPHZL5O7XEVU6DU33W","download_json":"https://pith.science/pith/UA25CK3KVPHZL5O7XEVU6DU33W.json","view_paper":"https://pith.science/paper/UA25CK3K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.15024&json=true","fetch_graph":"https://pith.science/api/pith-number/UA25CK3KVPHZL5O7XEVU6DU33W/graph.json","fetch_events":"https://pith.science/api/pith-number/UA25CK3KVPHZL5O7XEVU6DU33W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UA25CK3KVPHZL5O7XEVU6DU33W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UA25CK3KVPHZL5O7XEVU6DU33W/action/storage_attestation","attest_author":"https://pith.science/pith/UA25CK3KVPHZL5O7XEVU6DU33W/action/author_attestation","sign_citation":"https://pith.science/pith/UA25CK3KVPHZL5O7XEVU6DU33W/action/citation_signature","submit_replication":"https://pith.science/pith/UA25CK3KVPHZL5O7XEVU6DU33W/action/replication_record"}},"created_at":"2026-07-05T04:54:00.362578+00:00","updated_at":"2026-07-05T04:54:00.362578+00:00"}