{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DQD4YCZ3L7XBAXIYO6XG55OXPY","short_pith_number":"pith:DQD4YCZ3","schema_version":"1.0","canonical_sha256":"1c07cc0b3b5fee105d1877ae6ef5d77e26256769748a8a71ec903ed6df2e551d","source":{"kind":"arxiv","id":"2303.11754","version":3},"attestation_state":"computed","paper":{"title":"Projections of Model Spaces for Latent Graph Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"\\'Alvaro Arroyo, Haitz S\\'aez de Oc\\'ariz Borde, Ingmar Posner","submitted_at":"2023-03-21T11:20:22Z","abstract_excerpt":"Graph Neural Networks leverage the connectivity structure of graphs as an inductive bias. Latent graph inference focuses on learning an adequate graph structure to diffuse information on and improve the downstream performance of the model. In this work we employ stereographic projections of the hyperbolic and spherical model spaces, as well as products of Riemannian manifolds, for the purpose of latent graph inference. Stereographically projected model spaces achieve comparable performance to their non-projected counterparts, while providing theoretical guarantees that avoid divergence of the "},"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":"2303.11754","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-21T11:20:22Z","cross_cats_sorted":[],"title_canon_sha256":"563b283e0605adf93f3eac9ad774f9d0c50d57dd06cfe42b51af340371496706","abstract_canon_sha256":"e4d6ad8bacd7e4ebfdcb6725660d542c13a271106b7d55a23477badb7b9b44aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:00:17.003691Z","signature_b64":"jfXkAHWQPsWudzrbI7aZcPRtAG361/k1nNnCvarr4qJ4j4bnNtGME/VjJVzLwhSgeLuAGAoKGLwiTl6qudUVDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c07cc0b3b5fee105d1877ae6ef5d77e26256769748a8a71ec903ed6df2e551d","last_reissued_at":"2026-07-05T06:00:17.003208Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:00:17.003208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Projections of Model Spaces for Latent Graph Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"\\'Alvaro Arroyo, Haitz S\\'aez de Oc\\'ariz Borde, Ingmar Posner","submitted_at":"2023-03-21T11:20:22Z","abstract_excerpt":"Graph Neural Networks leverage the connectivity structure of graphs as an inductive bias. Latent graph inference focuses on learning an adequate graph structure to diffuse information on and improve the downstream performance of the model. In this work we employ stereographic projections of the hyperbolic and spherical model spaces, as well as products of Riemannian manifolds, for the purpose of latent graph inference. Stereographically projected model spaces achieve comparable performance to their non-projected counterparts, while providing theoretical guarantees that avoid divergence of the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.11754","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/2303.11754/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":"2303.11754","created_at":"2026-07-05T06:00:17.003269+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.11754v3","created_at":"2026-07-05T06:00:17.003269+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.11754","created_at":"2026-07-05T06:00:17.003269+00:00"},{"alias_kind":"pith_short_12","alias_value":"DQD4YCZ3L7XB","created_at":"2026-07-05T06:00:17.003269+00:00"},{"alias_kind":"pith_short_16","alias_value":"DQD4YCZ3L7XBAXIY","created_at":"2026-07-05T06:00:17.003269+00:00"},{"alias_kind":"pith_short_8","alias_value":"DQD4YCZ3","created_at":"2026-07-05T06:00:17.003269+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/DQD4YCZ3L7XBAXIYO6XG55OXPY","json":"https://pith.science/pith/DQD4YCZ3L7XBAXIYO6XG55OXPY.json","graph_json":"https://pith.science/api/pith-number/DQD4YCZ3L7XBAXIYO6XG55OXPY/graph.json","events_json":"https://pith.science/api/pith-number/DQD4YCZ3L7XBAXIYO6XG55OXPY/events.json","paper":"https://pith.science/paper/DQD4YCZ3"},"agent_actions":{"view_html":"https://pith.science/pith/DQD4YCZ3L7XBAXIYO6XG55OXPY","download_json":"https://pith.science/pith/DQD4YCZ3L7XBAXIYO6XG55OXPY.json","view_paper":"https://pith.science/paper/DQD4YCZ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.11754&json=true","fetch_graph":"https://pith.science/api/pith-number/DQD4YCZ3L7XBAXIYO6XG55OXPY/graph.json","fetch_events":"https://pith.science/api/pith-number/DQD4YCZ3L7XBAXIYO6XG55OXPY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DQD4YCZ3L7XBAXIYO6XG55OXPY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DQD4YCZ3L7XBAXIYO6XG55OXPY/action/storage_attestation","attest_author":"https://pith.science/pith/DQD4YCZ3L7XBAXIYO6XG55OXPY/action/author_attestation","sign_citation":"https://pith.science/pith/DQD4YCZ3L7XBAXIYO6XG55OXPY/action/citation_signature","submit_replication":"https://pith.science/pith/DQD4YCZ3L7XBAXIYO6XG55OXPY/action/replication_record"}},"created_at":"2026-07-05T06:00:17.003269+00:00","updated_at":"2026-07-05T06:00:17.003269+00:00"}