{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2JKTL3VXUHO2ZMPPQ3DF633XUR","short_pith_number":"pith:2JKTL3VX","schema_version":"1.0","canonical_sha256":"d25535eeb7a1ddacb1ef86c65f6f77a44e18bec95fd7b1cf8c9a39dd469e2968","source":{"kind":"arxiv","id":"2205.09575","version":1},"attestation_state":"computed","paper":{"title":"Learning Graph Structure from Convolutional Mixtures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI","eess.SP"],"primary_cat":"cs.LG","authors_text":"Alejandro Ribeiro, Gonzalo Mateos, Max Wasserman, Saurabh Sihag","submitted_at":"2022-05-19T14:08:15Z","abstract_excerpt":"Machine learning frameworks such as graph neural networks typically rely on a given, fixed graph to exploit relational inductive biases and thus effectively learn from network data. However, when said graphs are (partially) unobserved, noisy, or dynamic, the problem of inferring graph structure from data becomes relevant. In this paper, we postulate a graph convolutional relationship between the observed and latent graphs, and formulate the graph learning task as a network inverse (deconvolution) problem. In lieu of eigendecomposition-based spectral methods or iterative optimization solutions,"},"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":"2205.09575","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-19T14:08:15Z","cross_cats_sorted":["cs.SI","eess.SP"],"title_canon_sha256":"ae540762b4182c7713fa3078ea248b1b6c4807293d10c1a721cf755fa51f18f4","abstract_canon_sha256":"5889477c830f4eede00121b56c4837f65db4c322e31518063d39156c7b771676"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:24:46.303223Z","signature_b64":"Bq3oeFHorPF+Eel1S3Vwg680FLz7Ejzsp3vpYYrlIkqhem/B8L4Kq0hyr4gFVjOyB+XBuNnCto1kFzDFWBs4Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d25535eeb7a1ddacb1ef86c65f6f77a44e18bec95fd7b1cf8c9a39dd469e2968","last_reissued_at":"2026-07-05T04:24:46.302818Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:24:46.302818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Graph Structure from Convolutional Mixtures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI","eess.SP"],"primary_cat":"cs.LG","authors_text":"Alejandro Ribeiro, Gonzalo Mateos, Max Wasserman, Saurabh Sihag","submitted_at":"2022-05-19T14:08:15Z","abstract_excerpt":"Machine learning frameworks such as graph neural networks typically rely on a given, fixed graph to exploit relational inductive biases and thus effectively learn from network data. However, when said graphs are (partially) unobserved, noisy, or dynamic, the problem of inferring graph structure from data becomes relevant. In this paper, we postulate a graph convolutional relationship between the observed and latent graphs, and formulate the graph learning task as a network inverse (deconvolution) problem. In lieu of eigendecomposition-based spectral methods or iterative optimization solutions,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.09575","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/2205.09575/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":"2205.09575","created_at":"2026-07-05T04:24:46.302885+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.09575v1","created_at":"2026-07-05T04:24:46.302885+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.09575","created_at":"2026-07-05T04:24:46.302885+00:00"},{"alias_kind":"pith_short_12","alias_value":"2JKTL3VXUHO2","created_at":"2026-07-05T04:24:46.302885+00:00"},{"alias_kind":"pith_short_16","alias_value":"2JKTL3VXUHO2ZMPP","created_at":"2026-07-05T04:24:46.302885+00:00"},{"alias_kind":"pith_short_8","alias_value":"2JKTL3VX","created_at":"2026-07-05T04:24:46.302885+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/2JKTL3VXUHO2ZMPPQ3DF633XUR","json":"https://pith.science/pith/2JKTL3VXUHO2ZMPPQ3DF633XUR.json","graph_json":"https://pith.science/api/pith-number/2JKTL3VXUHO2ZMPPQ3DF633XUR/graph.json","events_json":"https://pith.science/api/pith-number/2JKTL3VXUHO2ZMPPQ3DF633XUR/events.json","paper":"https://pith.science/paper/2JKTL3VX"},"agent_actions":{"view_html":"https://pith.science/pith/2JKTL3VXUHO2ZMPPQ3DF633XUR","download_json":"https://pith.science/pith/2JKTL3VXUHO2ZMPPQ3DF633XUR.json","view_paper":"https://pith.science/paper/2JKTL3VX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.09575&json=true","fetch_graph":"https://pith.science/api/pith-number/2JKTL3VXUHO2ZMPPQ3DF633XUR/graph.json","fetch_events":"https://pith.science/api/pith-number/2JKTL3VXUHO2ZMPPQ3DF633XUR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2JKTL3VXUHO2ZMPPQ3DF633XUR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2JKTL3VXUHO2ZMPPQ3DF633XUR/action/storage_attestation","attest_author":"https://pith.science/pith/2JKTL3VXUHO2ZMPPQ3DF633XUR/action/author_attestation","sign_citation":"https://pith.science/pith/2JKTL3VXUHO2ZMPPQ3DF633XUR/action/citation_signature","submit_replication":"https://pith.science/pith/2JKTL3VXUHO2ZMPPQ3DF633XUR/action/replication_record"}},"created_at":"2026-07-05T04:24:46.302885+00:00","updated_at":"2026-07-05T04:24:46.302885+00:00"}