{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PFOBSF4B6H5DZPBOUZLRUE6OLK","short_pith_number":"pith:PFOBSF4B","schema_version":"1.0","canonical_sha256":"795c191781f1fa3cbc2ea6571a13ce5a9fc6a7c007202d54dc89662c99b7d320","source":{"kind":"arxiv","id":"2401.00424","version":1},"attestation_state":"computed","paper":{"title":"SDIF-DA: A Shallow-to-Deep Interaction Framework with Data Augmentation for Multi-modal Intent Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bingbing Wang, Geng Tu, Libo Qin, Ruifeng Xu, Shijue Huang","submitted_at":"2023-12-31T08:33:37Z","abstract_excerpt":"Multi-modal intent detection aims to utilize various modalities to understand the user's intentions, which is essential for the deployment of dialogue systems in real-world scenarios. The two core challenges for multi-modal intent detection are (1) how to effectively align and fuse different features of modalities and (2) the limited labeled multi-modal intent training data. In this work, we introduce a shallow-to-deep interaction framework with data augmentation (SDIF-DA) to address the above challenges. Firstly, SDIF-DA leverages a shallow-to-deep interaction module to progressively and effe"},"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":"2401.00424","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-31T08:33:37Z","cross_cats_sorted":[],"title_canon_sha256":"ba566835fd705f9b1299abb4cb62414cb5d65ce0708f828333f68b431b76da6e","abstract_canon_sha256":"12d8e431cec38254b227536c230b92a1360aba18ede8e9cb6e06f46a16f6953f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:29:18.344689Z","signature_b64":"QUucQHRa0hy62e1j5eT/+n+pMKzA3HZu/FPAbPs0S8YGIWboQ2AbLc5p0LUH1kJziuFE7Clg/9sBXDHe0vMVDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"795c191781f1fa3cbc2ea6571a13ce5a9fc6a7c007202d54dc89662c99b7d320","last_reissued_at":"2026-07-05T07:29:18.344148Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:29:18.344148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SDIF-DA: A Shallow-to-Deep Interaction Framework with Data Augmentation for Multi-modal Intent Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bingbing Wang, Geng Tu, Libo Qin, Ruifeng Xu, Shijue Huang","submitted_at":"2023-12-31T08:33:37Z","abstract_excerpt":"Multi-modal intent detection aims to utilize various modalities to understand the user's intentions, which is essential for the deployment of dialogue systems in real-world scenarios. The two core challenges for multi-modal intent detection are (1) how to effectively align and fuse different features of modalities and (2) the limited labeled multi-modal intent training data. In this work, we introduce a shallow-to-deep interaction framework with data augmentation (SDIF-DA) to address the above challenges. Firstly, SDIF-DA leverages a shallow-to-deep interaction module to progressively and effe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00424","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/2401.00424/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":"2401.00424","created_at":"2026-07-05T07:29:18.344207+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.00424v1","created_at":"2026-07-05T07:29:18.344207+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00424","created_at":"2026-07-05T07:29:18.344207+00:00"},{"alias_kind":"pith_short_12","alias_value":"PFOBSF4B6H5D","created_at":"2026-07-05T07:29:18.344207+00:00"},{"alias_kind":"pith_short_16","alias_value":"PFOBSF4B6H5DZPBO","created_at":"2026-07-05T07:29:18.344207+00:00"},{"alias_kind":"pith_short_8","alias_value":"PFOBSF4B","created_at":"2026-07-05T07:29:18.344207+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/PFOBSF4B6H5DZPBOUZLRUE6OLK","json":"https://pith.science/pith/PFOBSF4B6H5DZPBOUZLRUE6OLK.json","graph_json":"https://pith.science/api/pith-number/PFOBSF4B6H5DZPBOUZLRUE6OLK/graph.json","events_json":"https://pith.science/api/pith-number/PFOBSF4B6H5DZPBOUZLRUE6OLK/events.json","paper":"https://pith.science/paper/PFOBSF4B"},"agent_actions":{"view_html":"https://pith.science/pith/PFOBSF4B6H5DZPBOUZLRUE6OLK","download_json":"https://pith.science/pith/PFOBSF4B6H5DZPBOUZLRUE6OLK.json","view_paper":"https://pith.science/paper/PFOBSF4B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.00424&json=true","fetch_graph":"https://pith.science/api/pith-number/PFOBSF4B6H5DZPBOUZLRUE6OLK/graph.json","fetch_events":"https://pith.science/api/pith-number/PFOBSF4B6H5DZPBOUZLRUE6OLK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PFOBSF4B6H5DZPBOUZLRUE6OLK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PFOBSF4B6H5DZPBOUZLRUE6OLK/action/storage_attestation","attest_author":"https://pith.science/pith/PFOBSF4B6H5DZPBOUZLRUE6OLK/action/author_attestation","sign_citation":"https://pith.science/pith/PFOBSF4B6H5DZPBOUZLRUE6OLK/action/citation_signature","submit_replication":"https://pith.science/pith/PFOBSF4B6H5DZPBOUZLRUE6OLK/action/replication_record"}},"created_at":"2026-07-05T07:29:18.344207+00:00","updated_at":"2026-07-05T07:29:18.344207+00:00"}