{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:MMBIHYB3D43QZJBOZFFJV3DPFD","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":"a6929edaa64ae10f63efb5d8e28a65c3c85239a1641e7031bcc37c33f2fe59ef","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-09-09T15:37:39Z","title_canon_sha256":"cd6bca8f328f07aaf5cb41be23874c52268ba35c5dae3a668340827ff7276e88"},"schema_version":"1.0","source":{"id":"2209.04355","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.04355","created_at":"2026-07-05T05:39:53Z"},{"alias_kind":"arxiv_version","alias_value":"2209.04355v1","created_at":"2026-07-05T05:39:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.04355","created_at":"2026-07-05T05:39:53Z"},{"alias_kind":"pith_short_12","alias_value":"MMBIHYB3D43Q","created_at":"2026-07-05T05:39:53Z"},{"alias_kind":"pith_short_16","alias_value":"MMBIHYB3D43QZJBO","created_at":"2026-07-05T05:39:53Z"},{"alias_kind":"pith_short_8","alias_value":"MMBIHYB3","created_at":"2026-07-05T05:39:53Z"}],"graph_snapshots":[{"event_id":"sha256:43b3cc922cc8c92d7f5043479a9ccb113fc6aa9edf2b85b540b1e5988c0d627f","target":"graph","created_at":"2026-07-05T05:39:53Z","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/2209.04355/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hanlei Zhang, Hua Xu, Jiayan Teng, Qianrui Zhou, Shaojie Zhao, Xin Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-09-09T15:37:39Z","title":"MIntRec: A New Dataset for Multimodal Intent Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.04355","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":"sha256:7237d8b6e28d3790bd67a53768e86b684ef4066815f0ce32318887b5ffabb92c","target":"record","created_at":"2026-07-05T05:39:53Z","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":"a6929edaa64ae10f63efb5d8e28a65c3c85239a1641e7031bcc37c33f2fe59ef","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-09-09T15:37:39Z","title_canon_sha256":"cd6bca8f328f07aaf5cb41be23874c52268ba35c5dae3a668340827ff7276e88"},"schema_version":"1.0","source":{"id":"2209.04355","kind":"arxiv","version":1}},"canonical_sha256":"630283e03b1f370ca42ec94a9aec6f28f5cb671341f63f6e5875f24f81792847","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"630283e03b1f370ca42ec94a9aec6f28f5cb671341f63f6e5875f24f81792847","first_computed_at":"2026-07-05T05:39:53.056267Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:39:53.056267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gj6qJnkQ0iNUt38YiTCzabbQ+pK9o7eLPZkccpzhVRGHMFejwZXtbCLKHqvLHYzRGeadh26wHBvBlY/fu0ltAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:39:53.056682Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.04355","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7237d8b6e28d3790bd67a53768e86b684ef4066815f0ce32318887b5ffabb92c","sha256:43b3cc922cc8c92d7f5043479a9ccb113fc6aa9edf2b85b540b1e5988c0d627f"],"state_sha256":"4da2057435040d89af60aaf0f5f24eefb104664d3921fc5624976f687a6ad4b7"}