{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PFOBSF4B6H5DZPBOUZLRUE6OLK","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":"12d8e431cec38254b227536c230b92a1360aba18ede8e9cb6e06f46a16f6953f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-31T08:33:37Z","title_canon_sha256":"ba566835fd705f9b1299abb4cb62414cb5d65ce0708f828333f68b431b76da6e"},"schema_version":"1.0","source":{"id":"2401.00424","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.00424","created_at":"2026-07-05T07:29:18Z"},{"alias_kind":"arxiv_version","alias_value":"2401.00424v1","created_at":"2026-07-05T07:29:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00424","created_at":"2026-07-05T07:29:18Z"},{"alias_kind":"pith_short_12","alias_value":"PFOBSF4B6H5D","created_at":"2026-07-05T07:29:18Z"},{"alias_kind":"pith_short_16","alias_value":"PFOBSF4B6H5DZPBO","created_at":"2026-07-05T07:29:18Z"},{"alias_kind":"pith_short_8","alias_value":"PFOBSF4B","created_at":"2026-07-05T07:29:18Z"}],"graph_snapshots":[{"event_id":"sha256:cf8ea9187eee07b5a672e2d03cbe0e8b71b77aeea9150ea43ff490fc932e21da","target":"graph","created_at":"2026-07-05T07:29:18Z","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/2401.00424/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bingbing Wang, Geng Tu, Libo Qin, Ruifeng Xu, Shijue Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-31T08:33:37Z","title":"SDIF-DA: A Shallow-to-Deep Interaction Framework with Data Augmentation for Multi-modal Intent Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00424","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":"sha256:345aa30855078c9d520e27c320d800aed5c4aa58e78cf23ea8ba54cd5ab15410","target":"record","created_at":"2026-07-05T07:29:18Z","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":"12d8e431cec38254b227536c230b92a1360aba18ede8e9cb6e06f46a16f6953f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-31T08:33:37Z","title_canon_sha256":"ba566835fd705f9b1299abb4cb62414cb5d65ce0708f828333f68b431b76da6e"},"schema_version":"1.0","source":{"id":"2401.00424","kind":"arxiv","version":1}},"canonical_sha256":"795c191781f1fa3cbc2ea6571a13ce5a9fc6a7c007202d54dc89662c99b7d320","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"795c191781f1fa3cbc2ea6571a13ce5a9fc6a7c007202d54dc89662c99b7d320","first_computed_at":"2026-07-05T07:29:18.344148Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:29:18.344148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QUucQHRa0hy62e1j5eT/+n+pMKzA3HZu/FPAbPs0S8YGIWboQ2AbLc5p0LUH1kJziuFE7Clg/9sBXDHe0vMVDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:29:18.344689Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.00424","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:345aa30855078c9d520e27c320d800aed5c4aa58e78cf23ea8ba54cd5ab15410","sha256:cf8ea9187eee07b5a672e2d03cbe0e8b71b77aeea9150ea43ff490fc932e21da"],"state_sha256":"d11d96b5f4484f2bff27ccd4c4d2d4a4ea84399be5efcc2e138c613e9f6b6a72"}