{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YW53ZXV4QFNY5A2X5QMDJA4FBZ","short_pith_number":"pith:YW53ZXV4","schema_version":"1.0","canonical_sha256":"c5bbbcdebc815b8e8357ec183483850e761b25a1b08290937a56dd8b869fbaa8","source":{"kind":"arxiv","id":"2506.02230","version":1},"attestation_state":"computed","paper":{"title":"Towards Machine Unlearning for Paralinguistic Speech Processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Arun Balaji Buduru, Girish, Mohd Mujtaba Akhtar, Muskaan Singh, Orchid Chetia Phukan, Rajesh Sharma, Shubham Singh, Swarup Ranjan Behera, Vandana Rajan","submitted_at":"2025-06-02T20:14:22Z","abstract_excerpt":"In this work, we pioneer the study of Machine Unlearning (MU) for Paralinguistic Speech Processing (PSP). We focus on two key PSP tasks: Speech Emotion Recognition (SER) and Depression Detection (DD). To this end, we propose, SISA++, a novel extension to previous state-of-the-art (SOTA) MU method, SISA by merging models trained on different shards with weight-averaging. With such modifications, we show that SISA++ preserves performance more in comparison to SISA after unlearning in benchmark SER (CREMA-D) and DD (E-DAIC) datasets. Also, to guide future research for easier adoption of MU for PS"},"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":"2506.02230","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-02T20:14:22Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"f81e0b806f91c96fdf0c60ac26896bd08b2b9f31da912de589d4bb0452f43f34","abstract_canon_sha256":"089f2089cbc6b6b46afb9e83cd43dbe78cf3e462857633e0574c7edd3c08541a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:34.946296Z","signature_b64":"/v/nES30VCU+M2KlvlqyhA0lsMi4LyuLMPbIs0v2Rc1l1mgDuE0zSYs4sj1dpIWhIOTP3krHbv/rdVTsTk6fAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5bbbcdebc815b8e8357ec183483850e761b25a1b08290937a56dd8b869fbaa8","last_reissued_at":"2026-07-05T11:14:34.945825Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:34.945825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Machine Unlearning for Paralinguistic Speech Processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Arun Balaji Buduru, Girish, Mohd Mujtaba Akhtar, Muskaan Singh, Orchid Chetia Phukan, Rajesh Sharma, Shubham Singh, Swarup Ranjan Behera, Vandana Rajan","submitted_at":"2025-06-02T20:14:22Z","abstract_excerpt":"In this work, we pioneer the study of Machine Unlearning (MU) for Paralinguistic Speech Processing (PSP). We focus on two key PSP tasks: Speech Emotion Recognition (SER) and Depression Detection (DD). To this end, we propose, SISA++, a novel extension to previous state-of-the-art (SOTA) MU method, SISA by merging models trained on different shards with weight-averaging. With such modifications, we show that SISA++ preserves performance more in comparison to SISA after unlearning in benchmark SER (CREMA-D) and DD (E-DAIC) datasets. Also, to guide future research for easier adoption of MU for PS"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02230","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/2506.02230/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":"2506.02230","created_at":"2026-07-05T11:14:34.945886+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02230v1","created_at":"2026-07-05T11:14:34.945886+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02230","created_at":"2026-07-05T11:14:34.945886+00:00"},{"alias_kind":"pith_short_12","alias_value":"YW53ZXV4QFNY","created_at":"2026-07-05T11:14:34.945886+00:00"},{"alias_kind":"pith_short_16","alias_value":"YW53ZXV4QFNY5A2X","created_at":"2026-07-05T11:14:34.945886+00:00"},{"alias_kind":"pith_short_8","alias_value":"YW53ZXV4","created_at":"2026-07-05T11:14:34.945886+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02230","citing_title":"Towards Machine Unlearning for Paralinguistic Speech Processing","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YW53ZXV4QFNY5A2X5QMDJA4FBZ","json":"https://pith.science/pith/YW53ZXV4QFNY5A2X5QMDJA4FBZ.json","graph_json":"https://pith.science/api/pith-number/YW53ZXV4QFNY5A2X5QMDJA4FBZ/graph.json","events_json":"https://pith.science/api/pith-number/YW53ZXV4QFNY5A2X5QMDJA4FBZ/events.json","paper":"https://pith.science/paper/YW53ZXV4"},"agent_actions":{"view_html":"https://pith.science/pith/YW53ZXV4QFNY5A2X5QMDJA4FBZ","download_json":"https://pith.science/pith/YW53ZXV4QFNY5A2X5QMDJA4FBZ.json","view_paper":"https://pith.science/paper/YW53ZXV4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02230&json=true","fetch_graph":"https://pith.science/api/pith-number/YW53ZXV4QFNY5A2X5QMDJA4FBZ/graph.json","fetch_events":"https://pith.science/api/pith-number/YW53ZXV4QFNY5A2X5QMDJA4FBZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YW53ZXV4QFNY5A2X5QMDJA4FBZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YW53ZXV4QFNY5A2X5QMDJA4FBZ/action/storage_attestation","attest_author":"https://pith.science/pith/YW53ZXV4QFNY5A2X5QMDJA4FBZ/action/author_attestation","sign_citation":"https://pith.science/pith/YW53ZXV4QFNY5A2X5QMDJA4FBZ/action/citation_signature","submit_replication":"https://pith.science/pith/YW53ZXV4QFNY5A2X5QMDJA4FBZ/action/replication_record"}},"created_at":"2026-07-05T11:14:34.945886+00:00","updated_at":"2026-07-05T11:14:34.945886+00:00"}