{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZFDBQJYK6LGDD3A4BC7BPNNCDH","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f8f239ef015a9abfa7b2137cef2df5da217b3ce37f97193c3790fe4ff2d00063","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-07-11T02:01:26Z","title_canon_sha256":"9fcf02fdf58e267c8a3b020d17de71ad34703921e1bf25d0e6be365b5d3cf12b"},"schema_version":"1.0","source":{"id":"2407.08130","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.08130","created_at":"2026-07-05T08:42:43Z"},{"alias_kind":"arxiv_version","alias_value":"2407.08130v1","created_at":"2026-07-05T08:42:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08130","created_at":"2026-07-05T08:42:43Z"},{"alias_kind":"pith_short_12","alias_value":"ZFDBQJYK6LGD","created_at":"2026-07-05T08:42:43Z"},{"alias_kind":"pith_short_16","alias_value":"ZFDBQJYK6LGDD3A4","created_at":"2026-07-05T08:42:43Z"},{"alias_kind":"pith_short_8","alias_value":"ZFDBQJYK","created_at":"2026-07-05T08:42:43Z"}],"graph_snapshots":[{"event_id":"sha256:29bc8c0132716836f072b3562f2a1742fef7fee5ede58e97e4189f62169ffbf0","target":"graph","created_at":"2026-07-05T08:42:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2407.08130/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The spiking neural networks (SNNs) that efficiently encode temporal sequences have shown great potential in extracting audio-visual joint feature representations. However, coupling SNNs (binary spike sequences) with transformers (float-point sequences) to jointly explore the temporal-semantic information still facing challenges. In this paper, we introduce a novel Spiking Tucker Fusion Transformer (STFT) for audio-visual zero-shot learning (ZSL). The STFT leverage the temporal and semantic information from different time steps to generate robust representations. The time-step factor (TSF) is i","authors_text":"Penghong Wang, Ruiqin Xiong, Wenrui Li, Xiaopeng Fan","cross_cats":["cs.CV","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-07-11T02:01:26Z","title":"Spiking Tucker Fusion Transformer for Audio-Visual Zero-Shot Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08130","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9adc8bfb40f009b4994e89fc65eaedca92f8bb802797af0e91b7e4474ab413a5","target":"record","created_at":"2026-07-05T08:42:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f8f239ef015a9abfa7b2137cef2df5da217b3ce37f97193c3790fe4ff2d00063","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-07-11T02:01:26Z","title_canon_sha256":"9fcf02fdf58e267c8a3b020d17de71ad34703921e1bf25d0e6be365b5d3cf12b"},"schema_version":"1.0","source":{"id":"2407.08130","kind":"arxiv","version":1}},"canonical_sha256":"c94618270af2cc31ec1c08be17b5a219dcce918f4b1d4b7588762b3734e9abf5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c94618270af2cc31ec1c08be17b5a219dcce918f4b1d4b7588762b3734e9abf5","first_computed_at":"2026-07-05T08:42:43.616297Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:42:43.616297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qMhYQc1w4txNfSMKX8nB4dJ25Z1BfLnLdXypMcyDkhWZZAL0/CyDtrKdMt3HGe7vFloLslx+avmMpFbscUfeBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:42:43.616835Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.08130","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9adc8bfb40f009b4994e89fc65eaedca92f8bb802797af0e91b7e4474ab413a5","sha256:29bc8c0132716836f072b3562f2a1742fef7fee5ede58e97e4189f62169ffbf0"],"state_sha256":"70331b0801bf6d3c2094aa2904cf8b525600933dffa1ffd44868b412f95cbb5b"}