{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SQ542GBJQ63NOCIPTNUPUWHHVO","short_pith_number":"pith:SQ542GBJ","canonical_record":{"source":{"id":"2410.00390","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-01T04:22:10Z","cross_cats_sorted":[],"title_canon_sha256":"e3ea1b8e324aa915d060547b9eaa0580cfcc95d7f6c52c1e361a68286a90572b","abstract_canon_sha256":"410d5afe6d3ea56a5e8a2c12a1a0a1600d29a3841129b5edad18cfd50910d446"},"schema_version":"1.0"},"canonical_sha256":"943bcd182987b6d7090f9b68fa58e7abb7b66a52c45c2cf1885cd8fc22197c63","source":{"kind":"arxiv","id":"2410.00390","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.00390","created_at":"2026-07-05T09:14:04Z"},{"alias_kind":"arxiv_version","alias_value":"2410.00390v1","created_at":"2026-07-05T09:14:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.00390","created_at":"2026-07-05T09:14:04Z"},{"alias_kind":"pith_short_12","alias_value":"SQ542GBJQ63N","created_at":"2026-07-05T09:14:04Z"},{"alias_kind":"pith_short_16","alias_value":"SQ542GBJQ63NOCIP","created_at":"2026-07-05T09:14:04Z"},{"alias_kind":"pith_short_8","alias_value":"SQ542GBJ","created_at":"2026-07-05T09:14:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SQ542GBJQ63NOCIPTNUPUWHHVO","target":"record","payload":{"canonical_record":{"source":{"id":"2410.00390","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-01T04:22:10Z","cross_cats_sorted":[],"title_canon_sha256":"e3ea1b8e324aa915d060547b9eaa0580cfcc95d7f6c52c1e361a68286a90572b","abstract_canon_sha256":"410d5afe6d3ea56a5e8a2c12a1a0a1600d29a3841129b5edad18cfd50910d446"},"schema_version":"1.0"},"canonical_sha256":"943bcd182987b6d7090f9b68fa58e7abb7b66a52c45c2cf1885cd8fc22197c63","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:04.386336Z","signature_b64":"ccNsWlAwfNC/LFkUahcyCT0GQECgCwNMLI1P1DlQ+Ugggk4SrkH6I5yZMhl/swPTmO37w+QEVyyB5ZWrGR6xCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"943bcd182987b6d7090f9b68fa58e7abb7b66a52c45c2cf1885cd8fc22197c63","last_reissued_at":"2026-07-05T09:14:04.385877Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:04.385877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.00390","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:14:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4b7HnMATRI7s1ajxIIFIPwa+lua2MV99hQcdhKVvkqvnYk+8VgdYd+oK5c537kjwdblEU3t/ECmtvK6EUA3vAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:58:48.430253Z"},"content_sha256":"9bd9733c30f9949c7c162ee353117884fa88bf2c85528b8d1f3584516e9bc5b7","schema_version":"1.0","event_id":"sha256:9bd9733c30f9949c7c162ee353117884fa88bf2c85528b8d1f3584516e9bc5b7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SQ542GBJQ63NOCIPTNUPUWHHVO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Scale Temporal Transformer For Speech Emotion Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Hengsheng Fan, Weibin Zhang, Xiangmin Xu, Xiaofen Xing, Yuanbo Fang, Zhipeng Li","submitted_at":"2024-10-01T04:22:10Z","abstract_excerpt":"Speech emotion recognition plays a crucial role in human-machine interaction systems. Recently various optimized Transformers have been successfully applied to speech emotion recognition. However, the existing Transformer architectures focus more on global information and require large computation. On the other hand, abundant speech emotional representations exist locally on different parts of the input speech. To tackle these problems, we propose a Multi-Scale TRansfomer (MSTR) for speech emotion recognition. It comprises of three main components: (1) a multi-scale temporal feature operator, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.00390","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/2410.00390/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:14:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6OTGf1yuf4RUWL++mDvTkN4boar1zy8n2AfIHF6AUSKyM4gE8wx6SPyvObY7Qd6Hcgdppn4sn8oOtbF5Czi1Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:58:48.430886Z"},"content_sha256":"bbd9b7579d1615d51d86ed7cd5752da527c7f26b877fbd114e2e457c45117871","schema_version":"1.0","event_id":"sha256:bbd9b7579d1615d51d86ed7cd5752da527c7f26b877fbd114e2e457c45117871"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SQ542GBJQ63NOCIPTNUPUWHHVO/bundle.json","state_url":"https://pith.science/pith/SQ542GBJQ63NOCIPTNUPUWHHVO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SQ542GBJQ63NOCIPTNUPUWHHVO/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-11T08:58:48Z","links":{"resolver":"https://pith.science/pith/SQ542GBJQ63NOCIPTNUPUWHHVO","bundle":"https://pith.science/pith/SQ542GBJQ63NOCIPTNUPUWHHVO/bundle.json","state":"https://pith.science/pith/SQ542GBJQ63NOCIPTNUPUWHHVO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SQ542GBJQ63NOCIPTNUPUWHHVO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SQ542GBJQ63NOCIPTNUPUWHHVO","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":"410d5afe6d3ea56a5e8a2c12a1a0a1600d29a3841129b5edad18cfd50910d446","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-01T04:22:10Z","title_canon_sha256":"e3ea1b8e324aa915d060547b9eaa0580cfcc95d7f6c52c1e361a68286a90572b"},"schema_version":"1.0","source":{"id":"2410.00390","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.00390","created_at":"2026-07-05T09:14:04Z"},{"alias_kind":"arxiv_version","alias_value":"2410.00390v1","created_at":"2026-07-05T09:14:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.00390","created_at":"2026-07-05T09:14:04Z"},{"alias_kind":"pith_short_12","alias_value":"SQ542GBJQ63N","created_at":"2026-07-05T09:14:04Z"},{"alias_kind":"pith_short_16","alias_value":"SQ542GBJQ63NOCIP","created_at":"2026-07-05T09:14:04Z"},{"alias_kind":"pith_short_8","alias_value":"SQ542GBJ","created_at":"2026-07-05T09:14:04Z"}],"graph_snapshots":[{"event_id":"sha256:bbd9b7579d1615d51d86ed7cd5752da527c7f26b877fbd114e2e457c45117871","target":"graph","created_at":"2026-07-05T09:14:04Z","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/2410.00390/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech emotion recognition plays a crucial role in human-machine interaction systems. Recently various optimized Transformers have been successfully applied to speech emotion recognition. However, the existing Transformer architectures focus more on global information and require large computation. On the other hand, abundant speech emotional representations exist locally on different parts of the input speech. To tackle these problems, we propose a Multi-Scale TRansfomer (MSTR) for speech emotion recognition. It comprises of three main components: (1) a multi-scale temporal feature operator, ","authors_text":"Hengsheng Fan, Weibin Zhang, Xiangmin Xu, Xiaofen Xing, Yuanbo Fang, Zhipeng Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-01T04:22:10Z","title":"Multi-Scale Temporal Transformer For Speech Emotion Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.00390","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":"sha256:9bd9733c30f9949c7c162ee353117884fa88bf2c85528b8d1f3584516e9bc5b7","target":"record","created_at":"2026-07-05T09:14:04Z","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":"410d5afe6d3ea56a5e8a2c12a1a0a1600d29a3841129b5edad18cfd50910d446","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-01T04:22:10Z","title_canon_sha256":"e3ea1b8e324aa915d060547b9eaa0580cfcc95d7f6c52c1e361a68286a90572b"},"schema_version":"1.0","source":{"id":"2410.00390","kind":"arxiv","version":1}},"canonical_sha256":"943bcd182987b6d7090f9b68fa58e7abb7b66a52c45c2cf1885cd8fc22197c63","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"943bcd182987b6d7090f9b68fa58e7abb7b66a52c45c2cf1885cd8fc22197c63","first_computed_at":"2026-07-05T09:14:04.385877Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:14:04.385877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ccNsWlAwfNC/LFkUahcyCT0GQECgCwNMLI1P1DlQ+Ugggk4SrkH6I5yZMhl/swPTmO37w+QEVyyB5ZWrGR6xCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:14:04.386336Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.00390","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9bd9733c30f9949c7c162ee353117884fa88bf2c85528b8d1f3584516e9bc5b7","sha256:bbd9b7579d1615d51d86ed7cd5752da527c7f26b877fbd114e2e457c45117871"],"state_sha256":"028eefdeb4ffdfc8e4197f8b014880c5aa9c01b6c387cdab75fb75b64cabf742"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aS+zQRnWGQp/25n1EnOMa2DjLxHdXwJoqxFVBqH9hwHelKSdVRCRXubc6QIroRsVL/Hsbw/P5EfxtqjV4ef0Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T08:58:48.436745Z","bundle_sha256":"06b048ae406774c8e341d8f8b9af3d2578ef355334d21d1ed65688ee8f714821"}}