{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QGNIFNWSPSHHOM35RCYSPCUR5J","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":"ac6513de2fb55dee5c1a58c07b99219ab46d5c76a4d091e63a0d79fa24a71706","cross_cats_sorted":["cs.AI","cs.CV","eess.SP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-05-27T03:32:45Z","title_canon_sha256":"8de112846a2eb95abd58080d9dd417ed2f9cc1e51da03553660f5e76dcba59bc"},"schema_version":"1.0","source":{"id":"2506.10011","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.10011","created_at":"2026-07-05T11:20:38Z"},{"alias_kind":"arxiv_version","alias_value":"2506.10011v1","created_at":"2026-07-05T11:20:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10011","created_at":"2026-07-05T11:20:38Z"},{"alias_kind":"pith_short_12","alias_value":"QGNIFNWSPSHH","created_at":"2026-07-05T11:20:38Z"},{"alias_kind":"pith_short_16","alias_value":"QGNIFNWSPSHHOM35","created_at":"2026-07-05T11:20:38Z"},{"alias_kind":"pith_short_8","alias_value":"QGNIFNWS","created_at":"2026-07-05T11:20:38Z"}],"graph_snapshots":[{"event_id":"sha256:cd8083b163adeb7b2dc1b71f3dd1d0101a1c720f19919ae94fb7ba78c3f46a1a","target":"graph","created_at":"2026-07-05T11:20:38Z","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/2506.10011/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal intent recognition (MIR) seeks to accurately interpret user intentions by integrating verbal and non-verbal information across video, audio and text modalities. While existing approaches prioritize text analysis, they often overlook the rich semantic content embedded in non-verbal cues. This paper presents a novel Wavelet-Driven Multimodal Intent Recognition(WDMIR) framework that enhances intent understanding through frequency-domain analysis of non-verbal information. To be more specific, we propose: (1) a wavelet-driven fusion module that performs synchronized decomposition and in","authors_text":"Junyu Lu, Kai Zhang, Linbo Zhu, Qi Liu, Weiyin Gong, Xinjie Sun, Yanghai Zhang","cross_cats":["cs.AI","cs.CV","eess.SP"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-05-27T03:32:45Z","title":"WDMIR: Wavelet-Driven Multimodal Intent Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10011","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:f5370191b15899e849b7784d196be5e21a5298a3b66f7cda6cc3992aa6517ba9","target":"record","created_at":"2026-07-05T11:20:38Z","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":"ac6513de2fb55dee5c1a58c07b99219ab46d5c76a4d091e63a0d79fa24a71706","cross_cats_sorted":["cs.AI","cs.CV","eess.SP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-05-27T03:32:45Z","title_canon_sha256":"8de112846a2eb95abd58080d9dd417ed2f9cc1e51da03553660f5e76dcba59bc"},"schema_version":"1.0","source":{"id":"2506.10011","kind":"arxiv","version":1}},"canonical_sha256":"819a82b6d27c8e77337d88b1278a91ea79aff6bf8cb35a1fa97bb58fae84c190","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"819a82b6d27c8e77337d88b1278a91ea79aff6bf8cb35a1fa97bb58fae84c190","first_computed_at":"2026-07-05T11:20:38.570331Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:38.570331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wxxHSezIHOupW26H9vM4AC/bbDpkJn0ag5Qj+ckkshn3cU3Q00ZDAfn2YXU1vnIk8zZUBVpK4/bbr34LYi4BBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:38.570788Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.10011","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5370191b15899e849b7784d196be5e21a5298a3b66f7cda6cc3992aa6517ba9","sha256:cd8083b163adeb7b2dc1b71f3dd1d0101a1c720f19919ae94fb7ba78c3f46a1a"],"state_sha256":"a9302a9e94fd64e8f3fd1ce9d7a65e3c5a35f35692860f0f19de327d5cbc7207"}