{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CSCX2RTGCVAOKVT3F2E2YRS7I6","short_pith_number":"pith:CSCX2RTG","schema_version":"1.0","canonical_sha256":"14857d46661540e5567b2e89ac465f47b9bfebbe934f8965c9e71819ca9f404e","source":{"kind":"arxiv","id":"2307.12343","version":1},"attestation_state":"computed","paper":{"title":"Self-Supervised Learning for Audio-Based Emotion Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Peranut Nimitsurachat, Peter Washington","submitted_at":"2023-07-23T14:40:50Z","abstract_excerpt":"Emotion recognition models using audio input data can enable the development of interactive systems with applications in mental healthcare, marketing, gaming, and social media analysis. While the field of affective computing using audio data is rich, a major barrier to achieve consistently high-performance models is the paucity of available training labels. Self-supervised learning (SSL) is a family of methods which can learn despite a scarcity of supervised labels by predicting properties of the data itself. To understand the utility of self-supervised learning for audio-based emotion recogni"},"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":"2307.12343","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-07-23T14:40:50Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"834a19300cf5ece66edcee028d18391cc079914992a0f34eac5a7ccc9cc024cd","abstract_canon_sha256":"1a9c7de085d4a3555b352a0af440bf33352bea6b8eede27590345fb4f280ba54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:33:52.911460Z","signature_b64":"R+RbcRuQLcRF2eyAbixMgO5xJzGghnKLkGXkGM/kehGqkZC4uN6WGkRKJqk+x5LMM6PCwGIBlfjbPlUI8l5OBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14857d46661540e5567b2e89ac465f47b9bfebbe934f8965c9e71819ca9f404e","last_reissued_at":"2026-07-05T06:33:52.911008Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:33:52.911008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Supervised Learning for Audio-Based Emotion Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Peranut Nimitsurachat, Peter Washington","submitted_at":"2023-07-23T14:40:50Z","abstract_excerpt":"Emotion recognition models using audio input data can enable the development of interactive systems with applications in mental healthcare, marketing, gaming, and social media analysis. While the field of affective computing using audio data is rich, a major barrier to achieve consistently high-performance models is the paucity of available training labels. Self-supervised learning (SSL) is a family of methods which can learn despite a scarcity of supervised labels by predicting properties of the data itself. To understand the utility of self-supervised learning for audio-based emotion recogni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.12343","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/2307.12343/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":"2307.12343","created_at":"2026-07-05T06:33:52.911065+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.12343v1","created_at":"2026-07-05T06:33:52.911065+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.12343","created_at":"2026-07-05T06:33:52.911065+00:00"},{"alias_kind":"pith_short_12","alias_value":"CSCX2RTGCVAO","created_at":"2026-07-05T06:33:52.911065+00:00"},{"alias_kind":"pith_short_16","alias_value":"CSCX2RTGCVAOKVT3","created_at":"2026-07-05T06:33:52.911065+00:00"},{"alias_kind":"pith_short_8","alias_value":"CSCX2RTG","created_at":"2026-07-05T06:33:52.911065+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CSCX2RTGCVAOKVT3F2E2YRS7I6","json":"https://pith.science/pith/CSCX2RTGCVAOKVT3F2E2YRS7I6.json","graph_json":"https://pith.science/api/pith-number/CSCX2RTGCVAOKVT3F2E2YRS7I6/graph.json","events_json":"https://pith.science/api/pith-number/CSCX2RTGCVAOKVT3F2E2YRS7I6/events.json","paper":"https://pith.science/paper/CSCX2RTG"},"agent_actions":{"view_html":"https://pith.science/pith/CSCX2RTGCVAOKVT3F2E2YRS7I6","download_json":"https://pith.science/pith/CSCX2RTGCVAOKVT3F2E2YRS7I6.json","view_paper":"https://pith.science/paper/CSCX2RTG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.12343&json=true","fetch_graph":"https://pith.science/api/pith-number/CSCX2RTGCVAOKVT3F2E2YRS7I6/graph.json","fetch_events":"https://pith.science/api/pith-number/CSCX2RTGCVAOKVT3F2E2YRS7I6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CSCX2RTGCVAOKVT3F2E2YRS7I6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CSCX2RTGCVAOKVT3F2E2YRS7I6/action/storage_attestation","attest_author":"https://pith.science/pith/CSCX2RTGCVAOKVT3F2E2YRS7I6/action/author_attestation","sign_citation":"https://pith.science/pith/CSCX2RTGCVAOKVT3F2E2YRS7I6/action/citation_signature","submit_replication":"https://pith.science/pith/CSCX2RTGCVAOKVT3F2E2YRS7I6/action/replication_record"}},"created_at":"2026-07-05T06:33:52.911065+00:00","updated_at":"2026-07-05T06:33:52.911065+00:00"}