{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BNJTDNWUIFV255BHDOHBEXXVHF","short_pith_number":"pith:BNJTDNWU","schema_version":"1.0","canonical_sha256":"0b5331b6d4416baef4271b8e125ef539614c4b4ee8672cec9363fb490986a98a","source":{"kind":"arxiv","id":"2608.01622","version":1},"attestation_state":"computed","paper":{"title":"SMM Transformer: Leveraging Spiking Neural Networks for Multimodal Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.NE","authors_text":"Haoqi Zhu, Hongzhi Wang, Jinxing Han, Xiubo Liang, Yuke Li, Yu Zhao","submitted_at":"2026-08-03T02:54:28Z","abstract_excerpt":"Spiking Neural Networks (SNNs) enable event-driven computation with sparse activations, but building multimodal Transformers on SNNs is hindered by unstable training in deep spiking stacks and the mismatch between dense softmax attention and spike-based communication. We propose SMM Transformer, an SNN-based multimodal Transformer framework that combines (i)PLMP, a Parallel LIF with Multistage Learnable Parameters neuron and a tailored P-STBP algorithm for stable deep SNN training, (ii) SMSA, an attention-inspired spike-driven token-mixing module that replaces dense pairwise softmax attention "},"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":"2608.01622","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2026-08-03T02:54:28Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"304424a3f6d338b0cfffb4a6b5959a4a90a1807febed5a5368e786510157183d","abstract_canon_sha256":"4c17661952db7703ea9ec4ea5b7c4475db8ceb25b94920a780496dbbc55933ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:06:08.925434Z","signature_b64":"7KYWV1khXOXhaUz2ovGIPMNEleT3lzqLvZezVzxt1A/8Sokm4GYFLLnUPg65XXB52khOWOZTvnT3/BR4v8DyAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b5331b6d4416baef4271b8e125ef539614c4b4ee8672cec9363fb490986a98a","last_reissued_at":"2026-08-04T02:06:08.923894Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:06:08.923894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SMM Transformer: Leveraging Spiking Neural Networks for Multimodal Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.NE","authors_text":"Haoqi Zhu, Hongzhi Wang, Jinxing Han, Xiubo Liang, Yuke Li, Yu Zhao","submitted_at":"2026-08-03T02:54:28Z","abstract_excerpt":"Spiking Neural Networks (SNNs) enable event-driven computation with sparse activations, but building multimodal Transformers on SNNs is hindered by unstable training in deep spiking stacks and the mismatch between dense softmax attention and spike-based communication. We propose SMM Transformer, an SNN-based multimodal Transformer framework that combines (i)PLMP, a Parallel LIF with Multistage Learnable Parameters neuron and a tailored P-STBP algorithm for stable deep SNN training, (ii) SMSA, an attention-inspired spike-driven token-mixing module that replaces dense pairwise softmax attention "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01622","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/2608.01622/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":"2608.01622","created_at":"2026-08-04T02:06:08.925379+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01622v1","created_at":"2026-08-04T02:06:08.925379+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01622","created_at":"2026-08-04T02:06:08.925379+00:00"},{"alias_kind":"pith_short_12","alias_value":"BNJTDNWUIFV2","created_at":"2026-08-04T02:06:08.925379+00:00"},{"alias_kind":"pith_short_16","alias_value":"BNJTDNWUIFV255BH","created_at":"2026-08-04T02:06:08.925379+00:00"},{"alias_kind":"pith_short_8","alias_value":"BNJTDNWU","created_at":"2026-08-04T02:06:08.925379+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BNJTDNWUIFV255BHDOHBEXXVHF","json":"https://pith.science/pith/BNJTDNWUIFV255BHDOHBEXXVHF.json","graph_json":"https://pith.science/api/pith-number/BNJTDNWUIFV255BHDOHBEXXVHF/graph.json","events_json":"https://pith.science/api/pith-number/BNJTDNWUIFV255BHDOHBEXXVHF/events.json","paper":"https://pith.science/paper/BNJTDNWU"},"agent_actions":{"view_html":"https://pith.science/pith/BNJTDNWUIFV255BHDOHBEXXVHF","download_json":"https://pith.science/pith/BNJTDNWUIFV255BHDOHBEXXVHF.json","view_paper":"https://pith.science/paper/BNJTDNWU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01622&json=true","fetch_graph":"https://pith.science/api/pith-number/BNJTDNWUIFV255BHDOHBEXXVHF/graph.json","fetch_events":"https://pith.science/api/pith-number/BNJTDNWUIFV255BHDOHBEXXVHF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BNJTDNWUIFV255BHDOHBEXXVHF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BNJTDNWUIFV255BHDOHBEXXVHF/action/storage_attestation","attest_author":"https://pith.science/pith/BNJTDNWUIFV255BHDOHBEXXVHF/action/author_attestation","sign_citation":"https://pith.science/pith/BNJTDNWUIFV255BHDOHBEXXVHF/action/citation_signature","submit_replication":"https://pith.science/pith/BNJTDNWUIFV255BHDOHBEXXVHF/action/replication_record"}},"created_at":"2026-08-04T02:06:08.925379+00:00","updated_at":"2026-08-04T02:06:08.925379+00:00"}