{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MMBIHYB3D43QZJBOZFFJV3DPFD","short_pith_number":"pith:MMBIHYB3","schema_version":"1.0","canonical_sha256":"630283e03b1f370ca42ec94a9aec6f28f5cb671341f63f6e5875f24f81792847","source":{"kind":"arxiv","id":"2209.04355","version":1},"attestation_state":"computed","paper":{"title":"MIntRec: A New Dataset for Multimodal Intent Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hanlei Zhang, Hua Xu, Jiayan Teng, Qianrui Zhou, Shaojie Zhao, Xin Wang","submitted_at":"2022-09-09T15:37:39Z","abstract_excerpt":"Multimodal intent recognition is a significant task for understanding human language in real-world multimodal scenes. Most existing intent recognition methods have limitations in leveraging the multimodal information due to the restrictions of the benchmark datasets with only text information. This paper introduces a novel dataset for multimodal intent recognition (MIntRec) to address this issue. It formulates coarse-grained and fine-grained intent taxonomies based on the data collected from the TV series Superstore. The dataset consists of 2,224 high-quality samples with text, video, and audi"},"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":"2209.04355","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-09-09T15:37:39Z","cross_cats_sorted":[],"title_canon_sha256":"cd6bca8f328f07aaf5cb41be23874c52268ba35c5dae3a668340827ff7276e88","abstract_canon_sha256":"a6929edaa64ae10f63efb5d8e28a65c3c85239a1641e7031bcc37c33f2fe59ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:39:53.056682Z","signature_b64":"Gj6qJnkQ0iNUt38YiTCzabbQ+pK9o7eLPZkccpzhVRGHMFejwZXtbCLKHqvLHYzRGeadh26wHBvBlY/fu0ltAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"630283e03b1f370ca42ec94a9aec6f28f5cb671341f63f6e5875f24f81792847","last_reissued_at":"2026-07-05T05:39:53.056267Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:39:53.056267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MIntRec: A New Dataset for Multimodal Intent Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hanlei Zhang, Hua Xu, Jiayan Teng, Qianrui Zhou, Shaojie Zhao, Xin Wang","submitted_at":"2022-09-09T15:37:39Z","abstract_excerpt":"Multimodal intent recognition is a significant task for understanding human language in real-world multimodal scenes. Most existing intent recognition methods have limitations in leveraging the multimodal information due to the restrictions of the benchmark datasets with only text information. This paper introduces a novel dataset for multimodal intent recognition (MIntRec) to address this issue. It formulates coarse-grained and fine-grained intent taxonomies based on the data collected from the TV series Superstore. The dataset consists of 2,224 high-quality samples with text, video, and audi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.04355","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/2209.04355/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":"2209.04355","created_at":"2026-07-05T05:39:53.056321+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.04355v1","created_at":"2026-07-05T05:39:53.056321+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.04355","created_at":"2026-07-05T05:39:53.056321+00:00"},{"alias_kind":"pith_short_12","alias_value":"MMBIHYB3D43Q","created_at":"2026-07-05T05:39:53.056321+00:00"},{"alias_kind":"pith_short_16","alias_value":"MMBIHYB3D43QZJBO","created_at":"2026-07-05T05:39:53.056321+00:00"},{"alias_kind":"pith_short_8","alias_value":"MMBIHYB3","created_at":"2026-07-05T05:39:53.056321+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/MMBIHYB3D43QZJBOZFFJV3DPFD","json":"https://pith.science/pith/MMBIHYB3D43QZJBOZFFJV3DPFD.json","graph_json":"https://pith.science/api/pith-number/MMBIHYB3D43QZJBOZFFJV3DPFD/graph.json","events_json":"https://pith.science/api/pith-number/MMBIHYB3D43QZJBOZFFJV3DPFD/events.json","paper":"https://pith.science/paper/MMBIHYB3"},"agent_actions":{"view_html":"https://pith.science/pith/MMBIHYB3D43QZJBOZFFJV3DPFD","download_json":"https://pith.science/pith/MMBIHYB3D43QZJBOZFFJV3DPFD.json","view_paper":"https://pith.science/paper/MMBIHYB3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.04355&json=true","fetch_graph":"https://pith.science/api/pith-number/MMBIHYB3D43QZJBOZFFJV3DPFD/graph.json","fetch_events":"https://pith.science/api/pith-number/MMBIHYB3D43QZJBOZFFJV3DPFD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MMBIHYB3D43QZJBOZFFJV3DPFD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MMBIHYB3D43QZJBOZFFJV3DPFD/action/storage_attestation","attest_author":"https://pith.science/pith/MMBIHYB3D43QZJBOZFFJV3DPFD/action/author_attestation","sign_citation":"https://pith.science/pith/MMBIHYB3D43QZJBOZFFJV3DPFD/action/citation_signature","submit_replication":"https://pith.science/pith/MMBIHYB3D43QZJBOZFFJV3DPFD/action/replication_record"}},"created_at":"2026-07-05T05:39:53.056321+00:00","updated_at":"2026-07-05T05:39:53.056321+00:00"}