{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QRNLQKV374YPO4OO6SYWWKAV7N","short_pith_number":"pith:QRNLQKV3","schema_version":"1.0","canonical_sha256":"845ab82abbff30f771cef4b16b2815fb41bad7d72ca50da1b91fa2874bd6ae62","source":{"kind":"arxiv","id":"2605.23188","version":1},"attestation_state":"computed","paper":{"title":"SpikingMoE: SDPrompt-Guided Dynamic Expert Fusion in Spiking Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Chenxi Qin, Jungang Li, Liqun Chen, Wenwei Shao, Xin Zhang, Yukai Yang","submitted_at":"2026-05-22T03:14:15Z","abstract_excerpt":"Spiking Neural Networks (SNNs) provide an energy-efficient paradigm for visual recognition. We present SpikingMoE, which integrates a spike-driven Transformer with a Mixture-of-Experts (MoE) framework for dynamic computation. Inspired by the lateral geniculate nucleus (LGN), a spike-driven prompt (SDprompt) enables input-dependent expert routing in a biologically plausible manner. By replacing standard MLPs with spike-compatible expert modules and enforcing binary spike communication, SpikingMoE is designed for neuromorphic hardware. Experiments on CIFAR-10 and CIFAR-100 achieve 94.09% and 74."},"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":"2605.23188","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2026-05-22T03:14:15Z","cross_cats_sorted":[],"title_canon_sha256":"2552d00a74e34041c733b8e51402cef6a217c7312a4b07917d146f3b0805acd3","abstract_canon_sha256":"eb794c46d44184ab6ae5529744f55173791533eaeb5d700bb1c363cc65c8c4e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:42.230233Z","signature_b64":"RDAxwDdsQiMYK/Ev42cS/5HxO1VTAkBnEwFwGAVGkh00AGRk9SrcYPBgKEMWeoB8vNL5hdFhNPEWpWVgTS7rCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"845ab82abbff30f771cef4b16b2815fb41bad7d72ca50da1b91fa2874bd6ae62","last_reissued_at":"2026-05-25T02:01:42.229528Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:42.229528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpikingMoE: SDPrompt-Guided Dynamic Expert Fusion in Spiking Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Chenxi Qin, Jungang Li, Liqun Chen, Wenwei Shao, Xin Zhang, Yukai Yang","submitted_at":"2026-05-22T03:14:15Z","abstract_excerpt":"Spiking Neural Networks (SNNs) provide an energy-efficient paradigm for visual recognition. We present SpikingMoE, which integrates a spike-driven Transformer with a Mixture-of-Experts (MoE) framework for dynamic computation. Inspired by the lateral geniculate nucleus (LGN), a spike-driven prompt (SDprompt) enables input-dependent expert routing in a biologically plausible manner. By replacing standard MLPs with spike-compatible expert modules and enforcing binary spike communication, SpikingMoE is designed for neuromorphic hardware. Experiments on CIFAR-10 and CIFAR-100 achieve 94.09% and 74."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23188","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/2605.23188/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":"2605.23188","created_at":"2026-05-25T02:01:42.229650+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.23188v1","created_at":"2026-05-25T02:01:42.229650+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23188","created_at":"2026-05-25T02:01:42.229650+00:00"},{"alias_kind":"pith_short_12","alias_value":"QRNLQKV374YP","created_at":"2026-05-25T02:01:42.229650+00:00"},{"alias_kind":"pith_short_16","alias_value":"QRNLQKV374YPO4OO","created_at":"2026-05-25T02:01:42.229650+00:00"},{"alias_kind":"pith_short_8","alias_value":"QRNLQKV3","created_at":"2026-05-25T02:01:42.229650+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.23188","citing_title":"SpikingMoE: SDPrompt-Guided Dynamic Expert Fusion in Spiking Neural Networks","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QRNLQKV374YPO4OO6SYWWKAV7N","json":"https://pith.science/pith/QRNLQKV374YPO4OO6SYWWKAV7N.json","graph_json":"https://pith.science/api/pith-number/QRNLQKV374YPO4OO6SYWWKAV7N/graph.json","events_json":"https://pith.science/api/pith-number/QRNLQKV374YPO4OO6SYWWKAV7N/events.json","paper":"https://pith.science/paper/QRNLQKV3"},"agent_actions":{"view_html":"https://pith.science/pith/QRNLQKV374YPO4OO6SYWWKAV7N","download_json":"https://pith.science/pith/QRNLQKV374YPO4OO6SYWWKAV7N.json","view_paper":"https://pith.science/paper/QRNLQKV3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.23188&json=true","fetch_graph":"https://pith.science/api/pith-number/QRNLQKV374YPO4OO6SYWWKAV7N/graph.json","fetch_events":"https://pith.science/api/pith-number/QRNLQKV374YPO4OO6SYWWKAV7N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QRNLQKV374YPO4OO6SYWWKAV7N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QRNLQKV374YPO4OO6SYWWKAV7N/action/storage_attestation","attest_author":"https://pith.science/pith/QRNLQKV374YPO4OO6SYWWKAV7N/action/author_attestation","sign_citation":"https://pith.science/pith/QRNLQKV374YPO4OO6SYWWKAV7N/action/citation_signature","submit_replication":"https://pith.science/pith/QRNLQKV374YPO4OO6SYWWKAV7N/action/replication_record"}},"created_at":"2026-05-25T02:01:42.229650+00:00","updated_at":"2026-05-25T02:01:42.229650+00:00"}