{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:64KO63P7WUULZUISEFG5NSPQJI","short_pith_number":"pith:64KO63P7","schema_version":"1.0","canonical_sha256":"f714ef6dffb528bcd112214dd6c9f04a3a986df62de89ffcc1f0f0a7416b99df","source":{"kind":"arxiv","id":"2409.15234","version":1},"attestation_state":"computed","paper":{"title":"CA-MHFA: A Context-Aware Multi-Head Factorized Attentive Pooling for SSL-Based Speaker Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jan \\v{C}ernock\\'y, Junyi Peng, Ladislav Mo\\v{s}ner, Lin Zhang, Luk\\'a\\v{s} Burget, Old\\v{r}ich Plchot, Themos Stafylakis","submitted_at":"2024-09-23T17:30:30Z","abstract_excerpt":"Self-supervised learning (SSL) models for speaker verification (SV) have gained significant attention in recent years. However, existing SSL-based SV systems often struggle to capture local temporal dependencies and generalize across different tasks. In this paper, we propose context-aware multi-head factorized attentive pooling (CA-MHFA), a lightweight framework that incorporates contextual information from surrounding frames. CA-MHFA leverages grouped, learnable queries to effectively model contextual dependencies while maintaining efficiency by sharing keys and values across groups. Experim"},"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":"2409.15234","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-23T17:30:30Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"ded63748a7769c21df73ec2c5379c78b9ad9b46289c3cce3ef6ded4ebb5d35e5","abstract_canon_sha256":"f8cef4cfaaf7aead5c82ac951011f6783e55345a3f33d492b086d963d8b858af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:38.214741Z","signature_b64":"+mkrIJTODAcfLTVZKD464vKXU9rXArd5/rris47Y4LloFPnxZJ1ZQ63LsPIuUPmOjfnudc+DbgKL8m1tECf1Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f714ef6dffb528bcd112214dd6c9f04a3a986df62de89ffcc1f0f0a7416b99df","last_reissued_at":"2026-07-05T09:10:38.214370Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:38.214370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CA-MHFA: A Context-Aware Multi-Head Factorized Attentive Pooling for SSL-Based Speaker Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jan \\v{C}ernock\\'y, Junyi Peng, Ladislav Mo\\v{s}ner, Lin Zhang, Luk\\'a\\v{s} Burget, Old\\v{r}ich Plchot, Themos Stafylakis","submitted_at":"2024-09-23T17:30:30Z","abstract_excerpt":"Self-supervised learning (SSL) models for speaker verification (SV) have gained significant attention in recent years. However, existing SSL-based SV systems often struggle to capture local temporal dependencies and generalize across different tasks. In this paper, we propose context-aware multi-head factorized attentive pooling (CA-MHFA), a lightweight framework that incorporates contextual information from surrounding frames. CA-MHFA leverages grouped, learnable queries to effectively model contextual dependencies while maintaining efficiency by sharing keys and values across groups. Experim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15234","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/2409.15234/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":"2409.15234","created_at":"2026-07-05T09:10:38.214431+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.15234v1","created_at":"2026-07-05T09:10:38.214431+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15234","created_at":"2026-07-05T09:10:38.214431+00:00"},{"alias_kind":"pith_short_12","alias_value":"64KO63P7WUUL","created_at":"2026-07-05T09:10:38.214431+00:00"},{"alias_kind":"pith_short_16","alias_value":"64KO63P7WUULZUIS","created_at":"2026-07-05T09:10:38.214431+00:00"},{"alias_kind":"pith_short_8","alias_value":"64KO63P7","created_at":"2026-07-05T09:10:38.214431+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/64KO63P7WUULZUISEFG5NSPQJI","json":"https://pith.science/pith/64KO63P7WUULZUISEFG5NSPQJI.json","graph_json":"https://pith.science/api/pith-number/64KO63P7WUULZUISEFG5NSPQJI/graph.json","events_json":"https://pith.science/api/pith-number/64KO63P7WUULZUISEFG5NSPQJI/events.json","paper":"https://pith.science/paper/64KO63P7"},"agent_actions":{"view_html":"https://pith.science/pith/64KO63P7WUULZUISEFG5NSPQJI","download_json":"https://pith.science/pith/64KO63P7WUULZUISEFG5NSPQJI.json","view_paper":"https://pith.science/paper/64KO63P7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.15234&json=true","fetch_graph":"https://pith.science/api/pith-number/64KO63P7WUULZUISEFG5NSPQJI/graph.json","fetch_events":"https://pith.science/api/pith-number/64KO63P7WUULZUISEFG5NSPQJI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/64KO63P7WUULZUISEFG5NSPQJI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/64KO63P7WUULZUISEFG5NSPQJI/action/storage_attestation","attest_author":"https://pith.science/pith/64KO63P7WUULZUISEFG5NSPQJI/action/author_attestation","sign_citation":"https://pith.science/pith/64KO63P7WUULZUISEFG5NSPQJI/action/citation_signature","submit_replication":"https://pith.science/pith/64KO63P7WUULZUISEFG5NSPQJI/action/replication_record"}},"created_at":"2026-07-05T09:10:38.214431+00:00","updated_at":"2026-07-05T09:10:38.214431+00:00"}