{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:W7FNRYAXWSWHUBEMVPSH2T6IBF","short_pith_number":"pith:W7FNRYAX","schema_version":"1.0","canonical_sha256":"b7cad8e017b4ac7a048cabe47d4fc8097a996792f1409f3465a2ae8078f226e9","source":{"kind":"arxiv","id":"2606.27536","version":1},"attestation_state":"computed","paper":{"title":"Learning from Annotation Uncertainty: Entropy-Aware Curriculum for Speech Emotion Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SD","authors_text":"John H.L. Hansen, Zahra Omidi","submitted_at":"2026-06-25T20:35:17Z","abstract_excerpt":"Speech emotion recognition (SER) often relies on hard consensus labels that collapse annotator disagreement. We study distribution-based supervision for 9-class SER on MSP-Podcast 2.0 using a WavLM-Base multitask model for categorical emotion and dimensional VAD. Hard-label training is compared with targets from primary and merged primary--secondary annotator vote distributions. Distributional objectives improve alignment with human vote distributions, reducing JSD/KLD relative to hard-label training. Analysis shows that hard supervision partly benefits from assigning ambiguous utterances to t"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.27536","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-25T20:35:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"09311f2b3169a753ac72789ecdf2edd792c6af1aa6d5d60f64c159eee6d67848","abstract_canon_sha256":"9d720ceeb6b6b176fa5a8cc5bc0a7758cad7dddc94fc75f1b15c86b764860543"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T00:14:09.314098Z","signature_b64":"EdrWtsYumqd3oXEydiS3EytYkZe63FSP9bw1jvsfHmw3D3P897V918ooWDr/sfid16tZPhIqo0XXxeocfUE2BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7cad8e017b4ac7a048cabe47d4fc8097a996792f1409f3465a2ae8078f226e9","last_reissued_at":"2026-06-29T00:14:09.313708Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T00:14:09.313708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning from Annotation Uncertainty: Entropy-Aware Curriculum for Speech Emotion Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SD","authors_text":"John H.L. Hansen, Zahra Omidi","submitted_at":"2026-06-25T20:35:17Z","abstract_excerpt":"Speech emotion recognition (SER) often relies on hard consensus labels that collapse annotator disagreement. We study distribution-based supervision for 9-class SER on MSP-Podcast 2.0 using a WavLM-Base multitask model for categorical emotion and dimensional VAD. Hard-label training is compared with targets from primary and merged primary--secondary annotator vote distributions. Distributional objectives improve alignment with human vote distributions, reducing JSD/KLD relative to hard-label training. Analysis shows that hard supervision partly benefits from assigning ambiguous utterances to t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27536","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/2606.27536/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.27536","created_at":"2026-06-29T00:14:09.313763+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.27536v1","created_at":"2026-06-29T00:14:09.313763+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27536","created_at":"2026-06-29T00:14:09.313763+00:00"},{"alias_kind":"pith_short_12","alias_value":"W7FNRYAXWSWH","created_at":"2026-06-29T00:14:09.313763+00:00"},{"alias_kind":"pith_short_16","alias_value":"W7FNRYAXWSWHUBEM","created_at":"2026-06-29T00:14:09.313763+00:00"},{"alias_kind":"pith_short_8","alias_value":"W7FNRYAX","created_at":"2026-06-29T00:14:09.313763+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.27536","citing_title":"Learning from Annotation Uncertainty: Entropy-Aware Curriculum for Speech Emotion Recognition","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W7FNRYAXWSWHUBEMVPSH2T6IBF","json":"https://pith.science/pith/W7FNRYAXWSWHUBEMVPSH2T6IBF.json","graph_json":"https://pith.science/api/pith-number/W7FNRYAXWSWHUBEMVPSH2T6IBF/graph.json","events_json":"https://pith.science/api/pith-number/W7FNRYAXWSWHUBEMVPSH2T6IBF/events.json","paper":"https://pith.science/paper/W7FNRYAX"},"agent_actions":{"view_html":"https://pith.science/pith/W7FNRYAXWSWHUBEMVPSH2T6IBF","download_json":"https://pith.science/pith/W7FNRYAXWSWHUBEMVPSH2T6IBF.json","view_paper":"https://pith.science/paper/W7FNRYAX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.27536&json=true","fetch_graph":"https://pith.science/api/pith-number/W7FNRYAXWSWHUBEMVPSH2T6IBF/graph.json","fetch_events":"https://pith.science/api/pith-number/W7FNRYAXWSWHUBEMVPSH2T6IBF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W7FNRYAXWSWHUBEMVPSH2T6IBF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W7FNRYAXWSWHUBEMVPSH2T6IBF/action/storage_attestation","attest_author":"https://pith.science/pith/W7FNRYAXWSWHUBEMVPSH2T6IBF/action/author_attestation","sign_citation":"https://pith.science/pith/W7FNRYAXWSWHUBEMVPSH2T6IBF/action/citation_signature","submit_replication":"https://pith.science/pith/W7FNRYAXWSWHUBEMVPSH2T6IBF/action/replication_record"}},"created_at":"2026-06-29T00:14:09.313763+00:00","updated_at":"2026-06-29T00:14:09.313763+00:00"}