{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:H35HDJY54APZFZRR5CXCB7H6OR","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":"b4f80b8d66fa0492bc66dd71586e43369a4be9ca55b757dcfc77ba06a55bf091","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-05-21T13:24:07Z","title_canon_sha256":"0e03377e5641e054bc3f73644e93b6d3ebf0699af821e732efdfeb996d3ed759"},"schema_version":"1.0","source":{"id":"2405.12775","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.12775","created_at":"2026-07-05T08:21:25Z"},{"alias_kind":"arxiv_version","alias_value":"2405.12775v1","created_at":"2026-07-05T08:21:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.12775","created_at":"2026-07-05T08:21:25Z"},{"alias_kind":"pith_short_12","alias_value":"H35HDJY54APZ","created_at":"2026-07-05T08:21:25Z"},{"alias_kind":"pith_short_16","alias_value":"H35HDJY54APZFZRR","created_at":"2026-07-05T08:21:25Z"},{"alias_kind":"pith_short_8","alias_value":"H35HDJY5","created_at":"2026-07-05T08:21:25Z"}],"graph_snapshots":[{"event_id":"sha256:99d2ce41a13c51e26627b68c739765cf53955045fc27469bd606a56b4314fca8","target":"graph","created_at":"2026-07-05T08:21:25Z","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/2405.12775/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Discovering the semantics of multimodal utterances is essential for understanding human language and enhancing human-machine interactions. Existing methods manifest limitations in leveraging nonverbal information for discerning complex semantics in unsupervised scenarios. This paper introduces a novel unsupervised multimodal clustering method (UMC), making a pioneering contribution to this field. UMC introduces a unique approach to constructing augmentation views for multimodal data, which are then used to perform pre-training to establish well-initialized representations for subsequent cluste","authors_text":"Fei Long, Hanlei Zhang, Hua Xu, Kai Gao, Xin Wang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-05-21T13:24:07Z","title":"Unsupervised Multimodal Clustering for Semantics Discovery in Multimodal Utterances"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.12775","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":"sha256:9e21029cf6f18c1c4bbd9c24ad77c6e3709fedf380c4b517e99716f39c3fa2eb","target":"record","created_at":"2026-07-05T08:21:25Z","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":"b4f80b8d66fa0492bc66dd71586e43369a4be9ca55b757dcfc77ba06a55bf091","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-05-21T13:24:07Z","title_canon_sha256":"0e03377e5641e054bc3f73644e93b6d3ebf0699af821e732efdfeb996d3ed759"},"schema_version":"1.0","source":{"id":"2405.12775","kind":"arxiv","version":1}},"canonical_sha256":"3efa71a71de01f92e631e8ae20fcfe745af4792b2cd4731cdb489341422fcd86","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3efa71a71de01f92e631e8ae20fcfe745af4792b2cd4731cdb489341422fcd86","first_computed_at":"2026-07-05T08:21:25.709079Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:21:25.709079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hg19kjlFm0OaSJuN1GhyN9dAxtoM5zrv23bv+iNbeyMdMI9zGdGoaJSvF1/inaZnRi90NpwRWZdCZkwjfzV5AA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:21:25.709685Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.12775","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e21029cf6f18c1c4bbd9c24ad77c6e3709fedf380c4b517e99716f39c3fa2eb","sha256:99d2ce41a13c51e26627b68c739765cf53955045fc27469bd606a56b4314fca8"],"state_sha256":"20b15fcfa9762497a9a0c1195c05c53e27974627d41f2ae80d7bb248a8c21194"}