{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4VD2A5NTK5OBQEDNZME5FGE6XS","short_pith_number":"pith:4VD2A5NT","schema_version":"1.0","canonical_sha256":"e547a075b3575c18106dcb09d2989ebc95ff72ec020c771c176cd776a84d95b9","source":{"kind":"arxiv","id":"2201.12032","version":4},"attestation_state":"computed","paper":{"title":"Neural Approximation of Graph Topological Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chao Chen, Liangcai Gao, Tengfei Ma, Yusu Wang, Zhi Tang, Zuoyu Yan","submitted_at":"2022-01-28T10:54:45Z","abstract_excerpt":"Topological features based on persistent homology capture high-order structural information so as to augment graph neural network methods. However, computing extended persistent homology summaries remains slow for large and dense graphs and can be a serious bottleneck for the learning pipeline. Inspired by recent success in neural algorithmic reasoning, we propose a novel graph neural network to estimate extended persistence diagrams (EPDs) on graphs efficiently. Our model is built on algorithmic insights, and benefits from better supervision and closer alignment with the EPD computation algor"},"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":"2201.12032","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-28T10:54:45Z","cross_cats_sorted":[],"title_canon_sha256":"bd1807c22afa9bb3269eddd1920e04b0b875e8944bf7725b44a0e86a0c943d0f","abstract_canon_sha256":"f7a613ca3982dc120165c5c7a6dac5b634e757c28d601256d20f73390971fce4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:15:58.610106Z","signature_b64":"gfyi5r/T5GuAPoTjDLySw0Z4XpBIPhJwuW/UVKZVgnxsXgbf8ocUEssy3CQPEMls9ZzT7NHODNPA+uwZK2ThDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e547a075b3575c18106dcb09d2989ebc95ff72ec020c771c176cd776a84d95b9","last_reissued_at":"2026-07-05T05:15:58.609570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:15:58.609570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Approximation of Graph Topological Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chao Chen, Liangcai Gao, Tengfei Ma, Yusu Wang, Zhi Tang, Zuoyu Yan","submitted_at":"2022-01-28T10:54:45Z","abstract_excerpt":"Topological features based on persistent homology capture high-order structural information so as to augment graph neural network methods. However, computing extended persistent homology summaries remains slow for large and dense graphs and can be a serious bottleneck for the learning pipeline. Inspired by recent success in neural algorithmic reasoning, we propose a novel graph neural network to estimate extended persistence diagrams (EPDs) on graphs efficiently. Our model is built on algorithmic insights, and benefits from better supervision and closer alignment with the EPD computation algor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.12032","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/2201.12032/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":"2201.12032","created_at":"2026-07-05T05:15:58.609628+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.12032v4","created_at":"2026-07-05T05:15:58.609628+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.12032","created_at":"2026-07-05T05:15:58.609628+00:00"},{"alias_kind":"pith_short_12","alias_value":"4VD2A5NTK5OB","created_at":"2026-07-05T05:15:58.609628+00:00"},{"alias_kind":"pith_short_16","alias_value":"4VD2A5NTK5OBQEDN","created_at":"2026-07-05T05:15:58.609628+00:00"},{"alias_kind":"pith_short_8","alias_value":"4VD2A5NT","created_at":"2026-07-05T05:15:58.609628+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.05063","citing_title":"Computing and Learning on Combinatorial Data","ref_index":231,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4VD2A5NTK5OBQEDNZME5FGE6XS","json":"https://pith.science/pith/4VD2A5NTK5OBQEDNZME5FGE6XS.json","graph_json":"https://pith.science/api/pith-number/4VD2A5NTK5OBQEDNZME5FGE6XS/graph.json","events_json":"https://pith.science/api/pith-number/4VD2A5NTK5OBQEDNZME5FGE6XS/events.json","paper":"https://pith.science/paper/4VD2A5NT"},"agent_actions":{"view_html":"https://pith.science/pith/4VD2A5NTK5OBQEDNZME5FGE6XS","download_json":"https://pith.science/pith/4VD2A5NTK5OBQEDNZME5FGE6XS.json","view_paper":"https://pith.science/paper/4VD2A5NT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.12032&json=true","fetch_graph":"https://pith.science/api/pith-number/4VD2A5NTK5OBQEDNZME5FGE6XS/graph.json","fetch_events":"https://pith.science/api/pith-number/4VD2A5NTK5OBQEDNZME5FGE6XS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4VD2A5NTK5OBQEDNZME5FGE6XS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4VD2A5NTK5OBQEDNZME5FGE6XS/action/storage_attestation","attest_author":"https://pith.science/pith/4VD2A5NTK5OBQEDNZME5FGE6XS/action/author_attestation","sign_citation":"https://pith.science/pith/4VD2A5NTK5OBQEDNZME5FGE6XS/action/citation_signature","submit_replication":"https://pith.science/pith/4VD2A5NTK5OBQEDNZME5FGE6XS/action/replication_record"}},"created_at":"2026-07-05T05:15:58.609628+00:00","updated_at":"2026-07-05T05:15:58.609628+00:00"}