{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RVX7DQ4KAK7AMRUD5ZFXW5SMBZ","short_pith_number":"pith:RVX7DQ4K","schema_version":"1.0","canonical_sha256":"8d6ff1c38a02be064683ee4b7b764c0e7bec6452912c9d62ce8c2f125f8c3523","source":{"kind":"arxiv","id":"2405.14094","version":2},"attestation_state":"computed","paper":{"title":"Attending to Topological Spaces: The Cellular Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","math.AT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Carles Casacuberta, Claudio Battiloro, Mathilde Papillon, Mustafa Hajij, Nina Miolane, Pablo Hern\\'andez-Garc\\'ia, Rub\\'en Ballester, Sergio Escalera, Tolga Birdal","submitted_at":"2024-05-23T01:48:32Z","abstract_excerpt":"Topological Deep Learning seeks to enhance the predictive performance of neural network models by harnessing topological structures in input data. Topological neural networks operate on spaces such as cell complexes and hypergraphs, that can be seen as generalizations of graphs. In this work, we introduce the Cellular Transformer (CT), a novel architecture that generalizes graph-based transformers to cell complexes. First, we propose a new formulation of the usual self- and cross-attention mechanisms, tailored to leverage incidence relations in cell complexes, e.g., edge-face and node-edge rel"},"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":"2405.14094","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T01:48:32Z","cross_cats_sorted":["cs.AI","cs.CV","math.AT","stat.ML"],"title_canon_sha256":"d0df97c79450795f2bce3812499643bcfebea80e2120d4e0dd6b812817c0b639","abstract_canon_sha256":"6b64dc63b4a4ffba6cb255f65f12163414470fc1520c3eaa264e30a59ed09a32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:23.867067Z","signature_b64":"aY17K+a3BksR4BAsYwzG+OXTT3m9VmtnMttTpOkmIjAJ/DKo+ZyiTbFlHi7RE2F2oNwzMM7PcJ4rLTmlAjAQDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d6ff1c38a02be064683ee4b7b764c0e7bec6452912c9d62ce8c2f125f8c3523","last_reissued_at":"2026-07-05T08:23:23.866533Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:23.866533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attending to Topological Spaces: The Cellular Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","math.AT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Carles Casacuberta, Claudio Battiloro, Mathilde Papillon, Mustafa Hajij, Nina Miolane, Pablo Hern\\'andez-Garc\\'ia, Rub\\'en Ballester, Sergio Escalera, Tolga Birdal","submitted_at":"2024-05-23T01:48:32Z","abstract_excerpt":"Topological Deep Learning seeks to enhance the predictive performance of neural network models by harnessing topological structures in input data. Topological neural networks operate on spaces such as cell complexes and hypergraphs, that can be seen as generalizations of graphs. In this work, we introduce the Cellular Transformer (CT), a novel architecture that generalizes graph-based transformers to cell complexes. First, we propose a new formulation of the usual self- and cross-attention mechanisms, tailored to leverage incidence relations in cell complexes, e.g., edge-face and node-edge rel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14094","kind":"arxiv","version":2},"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/2405.14094/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":"2405.14094","created_at":"2026-07-05T08:23:23.866593+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.14094v2","created_at":"2026-07-05T08:23:23.866593+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14094","created_at":"2026-07-05T08:23:23.866593+00:00"},{"alias_kind":"pith_short_12","alias_value":"RVX7DQ4KAK7A","created_at":"2026-07-05T08:23:23.866593+00:00"},{"alias_kind":"pith_short_16","alias_value":"RVX7DQ4KAK7AMRUD","created_at":"2026-07-05T08:23:23.866593+00:00"},{"alias_kind":"pith_short_8","alias_value":"RVX7DQ4K","created_at":"2026-07-05T08:23:23.866593+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23517","citing_title":"Collapsed Effective Operators for Higher-order Structures","ref_index":96,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03163","citing_title":"Global and Local Topology-Aware Attention with Persistent Homology and Euler Biases for Time-Series Forecasting","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06467","citing_title":"No Triangulation Without Representation: Generalization in Topological Deep Learning","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07397","citing_title":"Have Graph -- Will Lift? The Case for Higher-Order Benchmarks","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RVX7DQ4KAK7AMRUD5ZFXW5SMBZ","json":"https://pith.science/pith/RVX7DQ4KAK7AMRUD5ZFXW5SMBZ.json","graph_json":"https://pith.science/api/pith-number/RVX7DQ4KAK7AMRUD5ZFXW5SMBZ/graph.json","events_json":"https://pith.science/api/pith-number/RVX7DQ4KAK7AMRUD5ZFXW5SMBZ/events.json","paper":"https://pith.science/paper/RVX7DQ4K"},"agent_actions":{"view_html":"https://pith.science/pith/RVX7DQ4KAK7AMRUD5ZFXW5SMBZ","download_json":"https://pith.science/pith/RVX7DQ4KAK7AMRUD5ZFXW5SMBZ.json","view_paper":"https://pith.science/paper/RVX7DQ4K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.14094&json=true","fetch_graph":"https://pith.science/api/pith-number/RVX7DQ4KAK7AMRUD5ZFXW5SMBZ/graph.json","fetch_events":"https://pith.science/api/pith-number/RVX7DQ4KAK7AMRUD5ZFXW5SMBZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RVX7DQ4KAK7AMRUD5ZFXW5SMBZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RVX7DQ4KAK7AMRUD5ZFXW5SMBZ/action/storage_attestation","attest_author":"https://pith.science/pith/RVX7DQ4KAK7AMRUD5ZFXW5SMBZ/action/author_attestation","sign_citation":"https://pith.science/pith/RVX7DQ4KAK7AMRUD5ZFXW5SMBZ/action/citation_signature","submit_replication":"https://pith.science/pith/RVX7DQ4KAK7AMRUD5ZFXW5SMBZ/action/replication_record"}},"created_at":"2026-07-05T08:23:23.866593+00:00","updated_at":"2026-07-05T08:23:23.866593+00:00"}