{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:PX2HADUYQSMKKAS7K7B45DSXC2","short_pith_number":"pith:PX2HADUY","schema_version":"1.0","canonical_sha256":"7df4700e988498a5025f57c3ce8e5716b2be21965d6b3d6334f88f8c12ae11d5","source":{"kind":"arxiv","id":"1912.00967","version":3},"attestation_state":"computed","paper":{"title":"Continuous Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jian Tang, Louis-Pascal A. C. Xhonneux, Meng Qu","submitted_at":"2019-12-02T17:59:12Z","abstract_excerpt":"This paper builds on the connection between graph neural networks and traditional dynamical systems. We propose continuous graph neural networks (CGNN), which generalise existing graph neural networks with discrete dynamics in that they can be viewed as a specific discretisation scheme. The key idea is how to characterise the continuous dynamics of node representations, i.e. the derivatives of node representations, w.r.t. time. Inspired by existing diffusion-based methods on graphs (e.g. PageRank and epidemic models on social networks), we define the derivatives as a combination of the current"},"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":"1912.00967","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-02T17:59:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"063ffb5685883de13235befa896ed32884f8b32eaefa6fd5e4bb773df6005d9e","abstract_canon_sha256":"b0eb422cac0f7eeecfe37e4599bee81da943cd89791a62ed3f4b5c3df862849a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:19:37.372546Z","signature_b64":"nLGbkLd3sVpRtEIjL727xxqcxUb2/6NvR/Iw1UR6+5bi6aMwf9QLD6vyDcfTIEDEeKTYVq4eeEv4d6NWeAUPCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7df4700e988498a5025f57c3ce8e5716b2be21965d6b3d6334f88f8c12ae11d5","last_reissued_at":"2026-07-05T01:19:37.372109Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:19:37.372109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continuous Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jian Tang, Louis-Pascal A. C. Xhonneux, Meng Qu","submitted_at":"2019-12-02T17:59:12Z","abstract_excerpt":"This paper builds on the connection between graph neural networks and traditional dynamical systems. We propose continuous graph neural networks (CGNN), which generalise existing graph neural networks with discrete dynamics in that they can be viewed as a specific discretisation scheme. The key idea is how to characterise the continuous dynamics of node representations, i.e. the derivatives of node representations, w.r.t. time. Inspired by existing diffusion-based methods on graphs (e.g. PageRank and epidemic models on social networks), we define the derivatives as a combination of the current"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.00967","kind":"arxiv","version":3},"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/1912.00967/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":"1912.00967","created_at":"2026-07-05T01:19:37.372173+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.00967v3","created_at":"2026-07-05T01:19:37.372173+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.00967","created_at":"2026-07-05T01:19:37.372173+00:00"},{"alias_kind":"pith_short_12","alias_value":"PX2HADUYQSMK","created_at":"2026-07-05T01:19:37.372173+00:00"},{"alias_kind":"pith_short_16","alias_value":"PX2HADUYQSMKKAS7","created_at":"2026-07-05T01:19:37.372173+00:00"},{"alias_kind":"pith_short_8","alias_value":"PX2HADUY","created_at":"2026-07-05T01:19:37.372173+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/PX2HADUYQSMKKAS7K7B45DSXC2","json":"https://pith.science/pith/PX2HADUYQSMKKAS7K7B45DSXC2.json","graph_json":"https://pith.science/api/pith-number/PX2HADUYQSMKKAS7K7B45DSXC2/graph.json","events_json":"https://pith.science/api/pith-number/PX2HADUYQSMKKAS7K7B45DSXC2/events.json","paper":"https://pith.science/paper/PX2HADUY"},"agent_actions":{"view_html":"https://pith.science/pith/PX2HADUYQSMKKAS7K7B45DSXC2","download_json":"https://pith.science/pith/PX2HADUYQSMKKAS7K7B45DSXC2.json","view_paper":"https://pith.science/paper/PX2HADUY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.00967&json=true","fetch_graph":"https://pith.science/api/pith-number/PX2HADUYQSMKKAS7K7B45DSXC2/graph.json","fetch_events":"https://pith.science/api/pith-number/PX2HADUYQSMKKAS7K7B45DSXC2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PX2HADUYQSMKKAS7K7B45DSXC2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PX2HADUYQSMKKAS7K7B45DSXC2/action/storage_attestation","attest_author":"https://pith.science/pith/PX2HADUYQSMKKAS7K7B45DSXC2/action/author_attestation","sign_citation":"https://pith.science/pith/PX2HADUYQSMKKAS7K7B45DSXC2/action/citation_signature","submit_replication":"https://pith.science/pith/PX2HADUYQSMKKAS7K7B45DSXC2/action/replication_record"}},"created_at":"2026-07-05T01:19:37.372173+00:00","updated_at":"2026-07-05T01:19:37.372173+00:00"}