{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VJFHC4LSGFSNMV2GBELZN6PSI6","short_pith_number":"pith:VJFHC4LS","schema_version":"1.0","canonical_sha256":"aa4a7171723164d65746091796f9f247ac81a3b50cf3d866897b9f187b7c11eb","source":{"kind":"arxiv","id":"2312.08515","version":2},"attestation_state":"computed","paper":{"title":"Simplicial Representation Learning with Neural $k$-Forms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.AT"],"primary_cat":"cs.LG","authors_text":"Bastian Rieck, Celia Hacker, Kelly Maggs","submitted_at":"2023-12-13T21:03:39Z","abstract_excerpt":"Geometric deep learning extends deep learning to incorporate information about the geometry and topology data, especially in complex domains like graphs. Despite the popularity of message passing in this field, it has limitations such as the need for graph rewiring, ambiguity in interpreting data, and over-smoothing. In this paper, we take a different approach, focusing on leveraging geometric information from simplicial complexes embedded in $\\mathbb{R}^n$ using node coordinates. We use differential k-forms in \\mathbb{R}^n to create representations of simplices, offering interpretability and "},"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":"2312.08515","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-13T21:03:39Z","cross_cats_sorted":["math.AT"],"title_canon_sha256":"c2e61bb4f61e7136113714aa4a304d54107fb90422ce6b797ce3482d42218994","abstract_canon_sha256":"16ead81a2ce9f35778f368e43c93948ece96f4ed7bc8093146bf245255643971"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:19.699840Z","signature_b64":"N5qSuzJgy7d4ar1Yle6uPl7ZqV0oomZm1nStaa/wjqwfVQIddTPRPYEXrhjVcxUK0FCwNTa3UDWXblhDP5c9AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa4a7171723164d65746091796f9f247ac81a3b50cf3d866897b9f187b7c11eb","last_reissued_at":"2026-07-05T07:56:19.699179Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:19.699179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simplicial Representation Learning with Neural $k$-Forms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.AT"],"primary_cat":"cs.LG","authors_text":"Bastian Rieck, Celia Hacker, Kelly Maggs","submitted_at":"2023-12-13T21:03:39Z","abstract_excerpt":"Geometric deep learning extends deep learning to incorporate information about the geometry and topology data, especially in complex domains like graphs. Despite the popularity of message passing in this field, it has limitations such as the need for graph rewiring, ambiguity in interpreting data, and over-smoothing. In this paper, we take a different approach, focusing on leveraging geometric information from simplicial complexes embedded in $\\mathbb{R}^n$ using node coordinates. We use differential k-forms in \\mathbb{R}^n to create representations of simplices, offering interpretability and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08515","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/2312.08515/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":"2312.08515","created_at":"2026-07-05T07:56:19.699260+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.08515v2","created_at":"2026-07-05T07:56:19.699260+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08515","created_at":"2026-07-05T07:56:19.699260+00:00"},{"alias_kind":"pith_short_12","alias_value":"VJFHC4LSGFSN","created_at":"2026-07-05T07:56:19.699260+00:00"},{"alias_kind":"pith_short_16","alias_value":"VJFHC4LSGFSNMV2G","created_at":"2026-07-05T07:56:19.699260+00:00"},{"alias_kind":"pith_short_8","alias_value":"VJFHC4LS","created_at":"2026-07-05T07:56:19.699260+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23517","citing_title":"Collapsed Effective Operators for Higher-order Structures","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22853","citing_title":"Topological Signal Processing: An Application-Oriented Tutorial","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15524","citing_title":"Neural Point-Forms","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VJFHC4LSGFSNMV2GBELZN6PSI6","json":"https://pith.science/pith/VJFHC4LSGFSNMV2GBELZN6PSI6.json","graph_json":"https://pith.science/api/pith-number/VJFHC4LSGFSNMV2GBELZN6PSI6/graph.json","events_json":"https://pith.science/api/pith-number/VJFHC4LSGFSNMV2GBELZN6PSI6/events.json","paper":"https://pith.science/paper/VJFHC4LS"},"agent_actions":{"view_html":"https://pith.science/pith/VJFHC4LSGFSNMV2GBELZN6PSI6","download_json":"https://pith.science/pith/VJFHC4LSGFSNMV2GBELZN6PSI6.json","view_paper":"https://pith.science/paper/VJFHC4LS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.08515&json=true","fetch_graph":"https://pith.science/api/pith-number/VJFHC4LSGFSNMV2GBELZN6PSI6/graph.json","fetch_events":"https://pith.science/api/pith-number/VJFHC4LSGFSNMV2GBELZN6PSI6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VJFHC4LSGFSNMV2GBELZN6PSI6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VJFHC4LSGFSNMV2GBELZN6PSI6/action/storage_attestation","attest_author":"https://pith.science/pith/VJFHC4LSGFSNMV2GBELZN6PSI6/action/author_attestation","sign_citation":"https://pith.science/pith/VJFHC4LSGFSNMV2GBELZN6PSI6/action/citation_signature","submit_replication":"https://pith.science/pith/VJFHC4LSGFSNMV2GBELZN6PSI6/action/replication_record"}},"created_at":"2026-07-05T07:56:19.699260+00:00","updated_at":"2026-07-05T07:56:19.699260+00:00"}