{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5X6BE5MBOBI25EQFDSGXNHAMZN","short_pith_number":"pith:5X6BE5MB","schema_version":"1.0","canonical_sha256":"edfc1275817051ae92051c8d769c0ccb431296ce1cd02e233a1d4a7d7b55b7ad","source":{"kind":"arxiv","id":"2406.05753","version":5},"attestation_state":"computed","paper":{"title":"Grounding Continuous Representations in Geometry: Equivariant Neural Fields","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"David M Knigge, David R Wessels, Efstratios Gavves, Erik J Bekkers, Riccardo Valperga, Samuele Papa, Sharvaree Vadgama","submitted_at":"2024-06-09T12:16:30Z","abstract_excerpt":"Conditional Neural Fields (CNFs) are increasingly being leveraged as continuous signal representations, by associating each data-sample with a latent variable that conditions a shared backbone Neural Field (NeF) to reconstruct the sample. However, existing CNF architectures face limitations when using this latent downstream in tasks requiring fine-grained geometric reasoning, such as classification and segmentation. We posit that this results from lack of explicit modelling of geometric information (e.g., locality in the signal or the orientation of a feature) in the latent space of CNFs. As s"},"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":"2406.05753","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-09T12:16:30Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"f3593e20c1128e10797e765fdd856931d59492e09fce8fcc635ba0f026d665f5","abstract_canon_sha256":"d996ecb7685001f9bd1cd80d51a3f801a1f709c9ddd52a8b9905488282e13f16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:08.448750Z","signature_b64":"dQEc1b8/6h64BDW2sT5Hvo1wj7T6l5OA506XtN6ErVDiXHUqJ+qo8Y1zHXzNWi0TBW2Zqm124uvwQ2Tbs+qmCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edfc1275817051ae92051c8d769c0ccb431296ce1cd02e233a1d4a7d7b55b7ad","last_reissued_at":"2026-07-05T10:11:08.448240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:08.448240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Grounding Continuous Representations in Geometry: Equivariant Neural Fields","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"David M Knigge, David R Wessels, Efstratios Gavves, Erik J Bekkers, Riccardo Valperga, Samuele Papa, Sharvaree Vadgama","submitted_at":"2024-06-09T12:16:30Z","abstract_excerpt":"Conditional Neural Fields (CNFs) are increasingly being leveraged as continuous signal representations, by associating each data-sample with a latent variable that conditions a shared backbone Neural Field (NeF) to reconstruct the sample. However, existing CNF architectures face limitations when using this latent downstream in tasks requiring fine-grained geometric reasoning, such as classification and segmentation. We posit that this results from lack of explicit modelling of geometric information (e.g., locality in the signal or the orientation of a feature) in the latent space of CNFs. As s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05753","kind":"arxiv","version":5},"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/2406.05753/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":"2406.05753","created_at":"2026-07-05T10:11:08.448310+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.05753v5","created_at":"2026-07-05T10:11:08.448310+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05753","created_at":"2026-07-05T10:11:08.448310+00:00"},{"alias_kind":"pith_short_12","alias_value":"5X6BE5MBOBI2","created_at":"2026-07-05T10:11:08.448310+00:00"},{"alias_kind":"pith_short_16","alias_value":"5X6BE5MBOBI25EQF","created_at":"2026-07-05T10:11:08.448310+00:00"},{"alias_kind":"pith_short_8","alias_value":"5X6BE5MB","created_at":"2026-07-05T10:11:08.448310+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16035","citing_title":"Equivariant Eikonal Neural Networks: Grid-Free, Scalable Travel-Time Prediction on Homogeneous Spaces","ref_index":57,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5X6BE5MBOBI25EQFDSGXNHAMZN","json":"https://pith.science/pith/5X6BE5MBOBI25EQFDSGXNHAMZN.json","graph_json":"https://pith.science/api/pith-number/5X6BE5MBOBI25EQFDSGXNHAMZN/graph.json","events_json":"https://pith.science/api/pith-number/5X6BE5MBOBI25EQFDSGXNHAMZN/events.json","paper":"https://pith.science/paper/5X6BE5MB"},"agent_actions":{"view_html":"https://pith.science/pith/5X6BE5MBOBI25EQFDSGXNHAMZN","download_json":"https://pith.science/pith/5X6BE5MBOBI25EQFDSGXNHAMZN.json","view_paper":"https://pith.science/paper/5X6BE5MB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.05753&json=true","fetch_graph":"https://pith.science/api/pith-number/5X6BE5MBOBI25EQFDSGXNHAMZN/graph.json","fetch_events":"https://pith.science/api/pith-number/5X6BE5MBOBI25EQFDSGXNHAMZN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5X6BE5MBOBI25EQFDSGXNHAMZN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5X6BE5MBOBI25EQFDSGXNHAMZN/action/storage_attestation","attest_author":"https://pith.science/pith/5X6BE5MBOBI25EQFDSGXNHAMZN/action/author_attestation","sign_citation":"https://pith.science/pith/5X6BE5MBOBI25EQFDSGXNHAMZN/action/citation_signature","submit_replication":"https://pith.science/pith/5X6BE5MBOBI25EQFDSGXNHAMZN/action/replication_record"}},"created_at":"2026-07-05T10:11:08.448310+00:00","updated_at":"2026-07-05T10:11:08.448310+00:00"}