{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NMCUJRF2YZSOLVFZBJ5BVMT22A","short_pith_number":"pith:NMCUJRF2","schema_version":"1.0","canonical_sha256":"6b0544c4bac664e5d4b90a7a1ab27ad0215e584ff638eb1a8ea0ebb9a6d849cf","source":{"kind":"arxiv","id":"2608.01160","version":1},"attestation_state":"computed","paper":{"title":"Differentiable Lifting for Topological Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Alexander Nikitin, Amauri H. Souza, Diego Mesquita, Gabriel Duarte, Jorge Luiz Franco, Moacir Ponti","submitted_at":"2026-08-02T11:30:09Z","abstract_excerpt":"Topological neural networks (TNNs) enable leveraging high-order structures on graphs (e.g., cycles and cliques) to boost the expressive power of message-passing neural networks. In turn, however, these structures are typically identified a priori through an unsupervised graph lifting operation. Notwithstanding, this choice is crucial and may have a drastic impact on a TNN's performance on downstream tasks. To circumvent this issue, we propose $\\partial$lift (DiffLift), a general framework for learning graph liftings to hypergraphs and cellular- and simplicial complexes in an end-to-end fashion"},"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":"2608.01160","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-02T11:30:09Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"09ee551af9320c73a7d2593dbd4f2d72c2a924945590414491a738b511652c00","abstract_canon_sha256":"47e8ff210d6065e247f517b3a6775f270b2925fe90857eb7208a5787ac145b45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T01:57:09.795497Z","signature_b64":"ADb4s5zyejaApDbiIsmNVJY5WEDjXmiFTPPx2E2nKHeV1zfD6jnORR0SsrrmkpUbevx+745n2uadWS/DBQlsDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b0544c4bac664e5d4b90a7a1ab27ad0215e584ff638eb1a8ea0ebb9a6d849cf","last_reissued_at":"2026-08-04T01:57:09.793929Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T01:57:09.793929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentiable Lifting for Topological Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Alexander Nikitin, Amauri H. Souza, Diego Mesquita, Gabriel Duarte, Jorge Luiz Franco, Moacir Ponti","submitted_at":"2026-08-02T11:30:09Z","abstract_excerpt":"Topological neural networks (TNNs) enable leveraging high-order structures on graphs (e.g., cycles and cliques) to boost the expressive power of message-passing neural networks. In turn, however, these structures are typically identified a priori through an unsupervised graph lifting operation. Notwithstanding, this choice is crucial and may have a drastic impact on a TNN's performance on downstream tasks. To circumvent this issue, we propose $\\partial$lift (DiffLift), a general framework for learning graph liftings to hypergraphs and cellular- and simplicial complexes in an end-to-end fashion"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01160","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/2608.01160/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":"2608.01160","created_at":"2026-08-04T01:57:09.795251+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01160v1","created_at":"2026-08-04T01:57:09.795251+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01160","created_at":"2026-08-04T01:57:09.795251+00:00"},{"alias_kind":"pith_short_12","alias_value":"NMCUJRF2YZSO","created_at":"2026-08-04T01:57:09.795251+00:00"},{"alias_kind":"pith_short_16","alias_value":"NMCUJRF2YZSOLVFZ","created_at":"2026-08-04T01:57:09.795251+00:00"},{"alias_kind":"pith_short_8","alias_value":"NMCUJRF2","created_at":"2026-08-04T01:57:09.795251+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/NMCUJRF2YZSOLVFZBJ5BVMT22A","json":"https://pith.science/pith/NMCUJRF2YZSOLVFZBJ5BVMT22A.json","graph_json":"https://pith.science/api/pith-number/NMCUJRF2YZSOLVFZBJ5BVMT22A/graph.json","events_json":"https://pith.science/api/pith-number/NMCUJRF2YZSOLVFZBJ5BVMT22A/events.json","paper":"https://pith.science/paper/NMCUJRF2"},"agent_actions":{"view_html":"https://pith.science/pith/NMCUJRF2YZSOLVFZBJ5BVMT22A","download_json":"https://pith.science/pith/NMCUJRF2YZSOLVFZBJ5BVMT22A.json","view_paper":"https://pith.science/paper/NMCUJRF2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01160&json=true","fetch_graph":"https://pith.science/api/pith-number/NMCUJRF2YZSOLVFZBJ5BVMT22A/graph.json","fetch_events":"https://pith.science/api/pith-number/NMCUJRF2YZSOLVFZBJ5BVMT22A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NMCUJRF2YZSOLVFZBJ5BVMT22A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NMCUJRF2YZSOLVFZBJ5BVMT22A/action/storage_attestation","attest_author":"https://pith.science/pith/NMCUJRF2YZSOLVFZBJ5BVMT22A/action/author_attestation","sign_citation":"https://pith.science/pith/NMCUJRF2YZSOLVFZBJ5BVMT22A/action/citation_signature","submit_replication":"https://pith.science/pith/NMCUJRF2YZSOLVFZBJ5BVMT22A/action/replication_record"}},"created_at":"2026-08-04T01:57:09.795251+00:00","updated_at":"2026-08-04T01:57:09.795251+00:00"}