{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:O37O32M3IXS5G2YCSNNQOKBDS2","short_pith_number":"pith:O37O32M3","schema_version":"1.0","canonical_sha256":"76feede99b45e5d36b02935b07282396a0347a8a55a6a15dd971f675423cac35","source":{"kind":"arxiv","id":"2410.13821","version":3},"attestation_state":"computed","paper":{"title":"Artificial Kuramoto Oscillatory Neurons","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andreas Geiger, Max Welling, Sindy L\\\"owe, Takeru Miyato","submitted_at":"2024-10-17T17:47:54Z","abstract_excerpt":"It has long been known in both neuroscience and AI that ``binding'' between neurons leads to a form of competitive learning where representations are compressed in order to represent more abstract concepts in deeper layers of the network. More recently, it was also hypothesized that dynamic (spatiotemporal) representations play an important role in both neuroscience and AI. Building on these ideas, we introduce Artificial Kuramoto Oscillatory Neurons (AKOrN) as a dynamical alternative to threshold units, which can be combined with arbitrary connectivity designs such as fully connected, convolu"},"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":"2410.13821","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-17T17:47:54Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"ca4fbdbcf853c7e97f3fe577936d7b330872e2c0a17def4b66ea9af1bc4fef65","abstract_canon_sha256":"6760281313c0b023c6dc08d13fb32909678bf1364164955b5a806900384cf477"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:18.602656Z","signature_b64":"mmNCXqaLOecwT4fOzB5+bYKsBP23rgYEumdkOVn43c7IlpWJY8NEYCQJRqRy3Z7yFamDDjUpSboYORWFDRGtBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76feede99b45e5d36b02935b07282396a0347a8a55a6a15dd971f675423cac35","last_reissued_at":"2026-07-05T11:04:18.602113Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:18.602113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Artificial Kuramoto Oscillatory Neurons","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andreas Geiger, Max Welling, Sindy L\\\"owe, Takeru Miyato","submitted_at":"2024-10-17T17:47:54Z","abstract_excerpt":"It has long been known in both neuroscience and AI that ``binding'' between neurons leads to a form of competitive learning where representations are compressed in order to represent more abstract concepts in deeper layers of the network. More recently, it was also hypothesized that dynamic (spatiotemporal) representations play an important role in both neuroscience and AI. Building on these ideas, we introduce Artificial Kuramoto Oscillatory Neurons (AKOrN) as a dynamical alternative to threshold units, which can be combined with arbitrary connectivity designs such as fully connected, convolu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13821","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/2410.13821/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":"2410.13821","created_at":"2026-07-05T11:04:18.602172+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.13821v3","created_at":"2026-07-05T11:04:18.602172+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13821","created_at":"2026-07-05T11:04:18.602172+00:00"},{"alias_kind":"pith_short_12","alias_value":"O37O32M3IXS5","created_at":"2026-07-05T11:04:18.602172+00:00"},{"alias_kind":"pith_short_16","alias_value":"O37O32M3IXS5G2YC","created_at":"2026-07-05T11:04:18.602172+00:00"},{"alias_kind":"pith_short_8","alias_value":"O37O32M3","created_at":"2026-07-05T11:04:18.602172+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25971","citing_title":"Improving Neural Network Training by Decoupling the Magnitude and Direction of Weight Vectors","ref_index":135,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27294","citing_title":"Generative Models on Analog Hardware with Dynamics","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03976","citing_title":"Formalizing the Binding Problem","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14685","citing_title":"Spontaneous symmetry breaking and Goldstone modes for deep information propagation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21174","citing_title":"Exact expression for maximum Lyapunov exponent during transients in computationally powerful dynamical networks","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2603.01097","citing_title":"Understanding LoRA as Knowledge Memory: An Empirical Analysis","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04418","citing_title":"Demystifying Manifold Constraints in LLM Pre-training","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20595","citing_title":"An explicit operator explains end-to-end computation in the modern neural networks used for sequence and language modeling","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O37O32M3IXS5G2YCSNNQOKBDS2","json":"https://pith.science/pith/O37O32M3IXS5G2YCSNNQOKBDS2.json","graph_json":"https://pith.science/api/pith-number/O37O32M3IXS5G2YCSNNQOKBDS2/graph.json","events_json":"https://pith.science/api/pith-number/O37O32M3IXS5G2YCSNNQOKBDS2/events.json","paper":"https://pith.science/paper/O37O32M3"},"agent_actions":{"view_html":"https://pith.science/pith/O37O32M3IXS5G2YCSNNQOKBDS2","download_json":"https://pith.science/pith/O37O32M3IXS5G2YCSNNQOKBDS2.json","view_paper":"https://pith.science/paper/O37O32M3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.13821&json=true","fetch_graph":"https://pith.science/api/pith-number/O37O32M3IXS5G2YCSNNQOKBDS2/graph.json","fetch_events":"https://pith.science/api/pith-number/O37O32M3IXS5G2YCSNNQOKBDS2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O37O32M3IXS5G2YCSNNQOKBDS2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O37O32M3IXS5G2YCSNNQOKBDS2/action/storage_attestation","attest_author":"https://pith.science/pith/O37O32M3IXS5G2YCSNNQOKBDS2/action/author_attestation","sign_citation":"https://pith.science/pith/O37O32M3IXS5G2YCSNNQOKBDS2/action/citation_signature","submit_replication":"https://pith.science/pith/O37O32M3IXS5G2YCSNNQOKBDS2/action/replication_record"}},"created_at":"2026-07-05T11:04:18.602172+00:00","updated_at":"2026-07-05T11:04:18.602172+00:00"}