{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ERG6DNFMREMOPYDCH2GL22DKBR","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":"8c12614592b4bfb481df90dea5e7b332688993d03a38c83e11d25476d10c5ed9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-02T16:09:33Z","title_canon_sha256":"7448092d84c8ce7d57172ce8f365aee9bba9f98dbb69cfb1d67dd44853833285"},"schema_version":"1.0","source":{"id":"2112.01368","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.01368","created_at":"2026-07-05T03:37:08Z"},{"alias_kind":"arxiv_version","alias_value":"2112.01368v1","created_at":"2026-07-05T03:37:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.01368","created_at":"2026-07-05T03:37:08Z"},{"alias_kind":"pith_short_12","alias_value":"ERG6DNFMREMO","created_at":"2026-07-05T03:37:08Z"},{"alias_kind":"pith_short_16","alias_value":"ERG6DNFMREMOPYDC","created_at":"2026-07-05T03:37:08Z"},{"alias_kind":"pith_short_8","alias_value":"ERG6DNFM","created_at":"2026-07-05T03:37:08Z"}],"graph_snapshots":[{"event_id":"sha256:ce84de437c56fa1cab21a12a04e25ce78c4c99640d820529157868ddb69f6749","target":"graph","created_at":"2026-07-05T03:37:08Z","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/2112.01368/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fusion technique is a key research topic in multimodal sentiment analysis. The recent attention-based fusion demonstrates advances over simple operation-based fusion. However, these fusion works adopt single-scale, i.e., token-level or utterance-level, unimodal representation. Such single-scale fusion is suboptimal because that different modality should be aligned with different granularities. This paper proposes a fusion model named ScaleVLAD to gather multi-Scale representation from text, video, and audio with shared Vectors of Locally Aggregated Descriptors to improve unaligned multimodal s","authors_text":"Bin Wang, Huaishao Luo, Lei Ji, Shenggong Ji, Tianrui Li, Yanyong Huang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-02T16:09:33Z","title":"ScaleVLAD: Improving Multimodal Sentiment Analysis via Multi-Scale Fusion of Locally Descriptors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.01368","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":"sha256:07c4b05f0a17f1c4d24d570cd7fdcb30683bd03332f7161b58fac7d0a520285b","target":"record","created_at":"2026-07-05T03:37:08Z","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":"8c12614592b4bfb481df90dea5e7b332688993d03a38c83e11d25476d10c5ed9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-02T16:09:33Z","title_canon_sha256":"7448092d84c8ce7d57172ce8f365aee9bba9f98dbb69cfb1d67dd44853833285"},"schema_version":"1.0","source":{"id":"2112.01368","kind":"arxiv","version":1}},"canonical_sha256":"244de1b4ac8918e7e0623e8cbd686a0c6803e585f14e1689b7bbb410fded95ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"244de1b4ac8918e7e0623e8cbd686a0c6803e585f14e1689b7bbb410fded95ac","first_computed_at":"2026-07-05T03:37:08.703884Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:37:08.703884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yl3ZTHG8Om51zmS0e9bHzOsdE6+zuJ76wTLvZ/3sr4wnbB65hsHZg4LENWVbPxfeAjvuRlqWYhB/UtgM9Ex4CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:37:08.704447Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.01368","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:07c4b05f0a17f1c4d24d570cd7fdcb30683bd03332f7161b58fac7d0a520285b","sha256:ce84de437c56fa1cab21a12a04e25ce78c4c99640d820529157868ddb69f6749"],"state_sha256":"87803b410775c14945243a7bfbf90fda5d409c5400bc6543d8eadacf7c00b67c"}