{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:XW4EYCK4AIFPT7PEQKXFUDD5M5","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":"9305b9b3d0fa7dc799641e1dab60002a8d5830e6ee670fcec068f5c6d032fe50","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-10-24T01:17:58Z","title_canon_sha256":"2a96451f2cdc6bc27b641b2a45366691223f5a99f9ceaa99bdf4dc8f8a5cc39e"},"schema_version":"1.0","source":{"id":"2010.12733","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.12733","created_at":"2026-07-05T02:58:04Z"},{"alias_kind":"arxiv_version","alias_value":"2010.12733v2","created_at":"2026-07-05T02:58:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12733","created_at":"2026-07-05T02:58:04Z"},{"alias_kind":"pith_short_12","alias_value":"XW4EYCK4AIFP","created_at":"2026-07-05T02:58:04Z"},{"alias_kind":"pith_short_16","alias_value":"XW4EYCK4AIFPT7PE","created_at":"2026-07-05T02:58:04Z"},{"alias_kind":"pith_short_8","alias_value":"XW4EYCK4","created_at":"2026-07-05T02:58:04Z"}],"graph_snapshots":[{"event_id":"sha256:7aab7163b59e74337b3f2a1aa917358b44b95d905d716978852b3161f0760358","target":"graph","created_at":"2026-07-05T02:58:04Z","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/2010.12733/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech emotion recognition is a challenging task because the emotion expression is complex, multimodal and fine-grained. In this paper, we propose a novel multimodal deep learning approach to perform fine-grained emotion recognition from real-life speeches. We design a temporal alignment mean-max pooling mechanism to capture the subtle and fine-grained emotions implied in every utterance. In addition, we propose a cross modality excitement module to conduct sample-specific adjustment on cross modality embeddings and adaptively recalibrate the corresponding values by its aligned latent features","authors_text":"Hang Li, Wenbiao Ding, Zhongqin Wu, Zitao Liu","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-10-24T01:17:58Z","title":"Learning Fine-Grained Cross Modality Excitement for Speech Emotion Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12733","kind":"arxiv","version":2},"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":"sha256:1bd05fb1733cd1b1358a6d7bd55009af6c69a7e82ebd3b5cc1aa8f7a2d67e803","target":"record","created_at":"2026-07-05T02:58:04Z","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":"9305b9b3d0fa7dc799641e1dab60002a8d5830e6ee670fcec068f5c6d032fe50","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-10-24T01:17:58Z","title_canon_sha256":"2a96451f2cdc6bc27b641b2a45366691223f5a99f9ceaa99bdf4dc8f8a5cc39e"},"schema_version":"1.0","source":{"id":"2010.12733","kind":"arxiv","version":2}},"canonical_sha256":"bdb84c095c020af9fde482ae5a0c7d6764d15738c104ba322265b01f2d97d03a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bdb84c095c020af9fde482ae5a0c7d6764d15738c104ba322265b01f2d97d03a","first_computed_at":"2026-07-05T02:58:04.956591Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:58:04.956591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2s7vPF54D7ZkdtBoQ1O7WZp0Kqifo4YBOUR6ZuQrLSb/hRGahaz4MrghDuMUDfczsh0BQgaBqiqg1SVUPuzeAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:58:04.957066Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.12733","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1bd05fb1733cd1b1358a6d7bd55009af6c69a7e82ebd3b5cc1aa8f7a2d67e803","sha256:7aab7163b59e74337b3f2a1aa917358b44b95d905d716978852b3161f0760358"],"state_sha256":"9618388497f10efb7606ab5e5fb546f762c574e5cfbf351602ede0d5e526b387"}