{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:DEGYV5YNHKHBVBFSQGF65UFYUZ","short_pith_number":"pith:DEGYV5YN","canonical_record":{"source":{"id":"2503.10446","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-03-13T15:11:28Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"2ab95862016dd4c01e80b14d4cf6e0b31e84880a7cb81546eef4c701fddc8d76","abstract_canon_sha256":"e53f37a8e0df1d368f795dc83848a726cb1f756b0886c263c3119c67bb046cb6"},"schema_version":"1.0"},"canonical_sha256":"190d8af70d3a8e1a84b2818beed0b8a6485b855a4c4ed38d7668d2cb6c89efb1","source":{"kind":"arxiv","id":"2503.10446","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.10446","created_at":"2026-07-05T10:30:45Z"},{"alias_kind":"arxiv_version","alias_value":"2503.10446v1","created_at":"2026-07-05T10:30:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10446","created_at":"2026-07-05T10:30:45Z"},{"alias_kind":"pith_short_12","alias_value":"DEGYV5YNHKHB","created_at":"2026-07-05T10:30:45Z"},{"alias_kind":"pith_short_16","alias_value":"DEGYV5YNHKHBVBFS","created_at":"2026-07-05T10:30:45Z"},{"alias_kind":"pith_short_8","alias_value":"DEGYV5YN","created_at":"2026-07-05T10:30:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:DEGYV5YNHKHBVBFSQGF65UFYUZ","target":"record","payload":{"canonical_record":{"source":{"id":"2503.10446","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-03-13T15:11:28Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"2ab95862016dd4c01e80b14d4cf6e0b31e84880a7cb81546eef4c701fddc8d76","abstract_canon_sha256":"e53f37a8e0df1d368f795dc83848a726cb1f756b0886c263c3119c67bb046cb6"},"schema_version":"1.0"},"canonical_sha256":"190d8af70d3a8e1a84b2818beed0b8a6485b855a4c4ed38d7668d2cb6c89efb1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:45.484098Z","signature_b64":"VBr4nhnY0VItaK+91DZqVu81fGTAX5o6uS11n6OxL2DUTOkWCIjBUBVFnB1lwbaXASMReOtgqvDTk4jl/ZK0DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"190d8af70d3a8e1a84b2818beed0b8a6485b855a4c4ed38d7668d2cb6c89efb1","last_reissued_at":"2026-07-05T10:30:45.483478Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:45.483478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.10446","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":"2026-07-05T10:30:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y7te7gTRi9W+sXgj3DI/meQR19ny4Wrn++Bov5LaloGxnbySyUA3GlYhyu+CNNUiQjQZFj3kPxJ8MGqWnIINAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:38:49.810374Z"},"content_sha256":"528da19d892593745e87096170f1569e93f748dea4317b11c9c343368c5e9078","schema_version":"1.0","event_id":"sha256:528da19d892593745e87096170f1569e93f748dea4317b11c9c343368c5e9078"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:DEGYV5YNHKHBVBFSQGF65UFYUZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Whisper Speaker Identification: Leveraging Pre-Trained Multilingual Transformers for Robust Speaker Embeddings","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jakaria Islam Emon, Kazi Tamanna Alam, Md Abu Salek","submitted_at":"2025-03-13T15:11:28Z","abstract_excerpt":"Speaker identification in multilingual settings presents unique challenges, particularly when conventional models are predominantly trained on English data. In this paper, we propose WSI (Whisper Speaker Identification), a framework that repurposes the encoder of the Whisper automatic speech recognition model pre trained on extensive multilingual data to generate robust speaker embeddings via a joint loss optimization strategy that leverages online hard triplet mining and self supervised Normalized Temperature-scaled Cross Entropy loss. By capitalizing on Whisper language-agnostic acoustic rep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10446","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/2503.10446/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":"2026-07-05T10:30:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MpJKn9c3xitrkVrSxjzS8s249mmfaYEXOruzDvTA4li8tj37Zgqbbjm+j0qo8yX8x+l7wH8ANt1jBLWxaYgXCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:38:49.810925Z"},"content_sha256":"4c4b080735cc9aec9230fe0a54687d2854fc48aa608151eff8f4516430bf7e10","schema_version":"1.0","event_id":"sha256:4c4b080735cc9aec9230fe0a54687d2854fc48aa608151eff8f4516430bf7e10"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DEGYV5YNHKHBVBFSQGF65UFYUZ/bundle.json","state_url":"https://pith.science/pith/DEGYV5YNHKHBVBFSQGF65UFYUZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DEGYV5YNHKHBVBFSQGF65UFYUZ/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":"2026-08-07T05:38:49Z","links":{"resolver":"https://pith.science/pith/DEGYV5YNHKHBVBFSQGF65UFYUZ","bundle":"https://pith.science/pith/DEGYV5YNHKHBVBFSQGF65UFYUZ/bundle.json","state":"https://pith.science/pith/DEGYV5YNHKHBVBFSQGF65UFYUZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DEGYV5YNHKHBVBFSQGF65UFYUZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DEGYV5YNHKHBVBFSQGF65UFYUZ","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":"e53f37a8e0df1d368f795dc83848a726cb1f756b0886c263c3119c67bb046cb6","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-03-13T15:11:28Z","title_canon_sha256":"2ab95862016dd4c01e80b14d4cf6e0b31e84880a7cb81546eef4c701fddc8d76"},"schema_version":"1.0","source":{"id":"2503.10446","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.10446","created_at":"2026-07-05T10:30:45Z"},{"alias_kind":"arxiv_version","alias_value":"2503.10446v1","created_at":"2026-07-05T10:30:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10446","created_at":"2026-07-05T10:30:45Z"},{"alias_kind":"pith_short_12","alias_value":"DEGYV5YNHKHB","created_at":"2026-07-05T10:30:45Z"},{"alias_kind":"pith_short_16","alias_value":"DEGYV5YNHKHBVBFS","created_at":"2026-07-05T10:30:45Z"},{"alias_kind":"pith_short_8","alias_value":"DEGYV5YN","created_at":"2026-07-05T10:30:45Z"}],"graph_snapshots":[{"event_id":"sha256:4c4b080735cc9aec9230fe0a54687d2854fc48aa608151eff8f4516430bf7e10","target":"graph","created_at":"2026-07-05T10:30:45Z","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/2503.10446/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speaker identification in multilingual settings presents unique challenges, particularly when conventional models are predominantly trained on English data. In this paper, we propose WSI (Whisper Speaker Identification), a framework that repurposes the encoder of the Whisper automatic speech recognition model pre trained on extensive multilingual data to generate robust speaker embeddings via a joint loss optimization strategy that leverages online hard triplet mining and self supervised Normalized Temperature-scaled Cross Entropy loss. By capitalizing on Whisper language-agnostic acoustic rep","authors_text":"Jakaria Islam Emon, Kazi Tamanna Alam, Md Abu Salek","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-03-13T15:11:28Z","title":"Whisper Speaker Identification: Leveraging Pre-Trained Multilingual Transformers for Robust Speaker Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10446","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":"sha256:528da19d892593745e87096170f1569e93f748dea4317b11c9c343368c5e9078","target":"record","created_at":"2026-07-05T10:30:45Z","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":"e53f37a8e0df1d368f795dc83848a726cb1f756b0886c263c3119c67bb046cb6","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-03-13T15:11:28Z","title_canon_sha256":"2ab95862016dd4c01e80b14d4cf6e0b31e84880a7cb81546eef4c701fddc8d76"},"schema_version":"1.0","source":{"id":"2503.10446","kind":"arxiv","version":1}},"canonical_sha256":"190d8af70d3a8e1a84b2818beed0b8a6485b855a4c4ed38d7668d2cb6c89efb1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"190d8af70d3a8e1a84b2818beed0b8a6485b855a4c4ed38d7668d2cb6c89efb1","first_computed_at":"2026-07-05T10:30:45.483478Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:30:45.483478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VBr4nhnY0VItaK+91DZqVu81fGTAX5o6uS11n6OxL2DUTOkWCIjBUBVFnB1lwbaXASMReOtgqvDTk4jl/ZK0DA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:30:45.484098Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.10446","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:528da19d892593745e87096170f1569e93f748dea4317b11c9c343368c5e9078","sha256:4c4b080735cc9aec9230fe0a54687d2854fc48aa608151eff8f4516430bf7e10"],"state_sha256":"a0d0eb5819a91160b95c25b27d5f588a430afd7375dce2d6af5379d716e610d1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7UB0IwWi/VDjiSV5AYfiE99pMe4NOWwN9fLau6aw9UQfry2h2L8eKRVjpBJO89/t5P0halrgja93qtTZoqm1Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T05:38:49.815290Z","bundle_sha256":"fcc017c07a637646a0138d54fe1772f3ddca0a380e0ddf76f150bef141443d84"}}