{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RW3JTPB5AVB5ASFCZUMXE4RVLN","short_pith_number":"pith:RW3JTPB5","schema_version":"1.0","canonical_sha256":"8db699bc3d0543d048a2cd197272355b4ae7a3adb9655b718895b45ecbe23300","source":{"kind":"arxiv","id":"2606.03283","version":1},"attestation_state":"computed","paper":{"title":"SpeakerCard-1M: An Evidence-Grounded Speaker Card Corpus for In-the-Wild Speaker Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Dading Chong, Hang Su, Jan \\v{C}ernock\\'y, Junjie Li, Junyi Peng, Kong Aik Lee, Lichun Fan, Old\\v{r}ich Plchot, Shuai Wang, Themos Stafylakis, Xiao Song","submitted_at":"2026-06-02T07:49:30Z","abstract_excerpt":"Modern speaker verification (SV) systems rely on speaker embeddings that are effective but difficult to interpret or query in natural language. Most existing speech-text corpora target controllable synthesis or utterance-level captioning, and provide limited speaker-level supervision for in-the-wild speaker recognition. This paper introduces SpeakerCard-1M, a bilingual speaker-centric resource for evidence-grounded SV, derived from VoxCeleb1/2 and CN-Celeb1/2, where the \"-1M\" suffix refers to the 1.78M utterance-level captions contained in the release. We adopt a tool-first, LLM-last approach:"},"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":"2606.03283","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-02T07:49:30Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"4c96f908dd18584a985a277a8a7d6f5ec3f770e0b7574cc1d0b52b44dfd4d18f","abstract_canon_sha256":"ce064b7bd3ecd298ff37b0e4002bcc1daa64ec405ee7a23147a9ffb2ba61d161"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:38.160384Z","signature_b64":"iuVbbizpMKNVbKetVFBJT92EydBSEAUEE5qDIw6kgvOOWoZCWJGstZLfKzXPFXdgiGL3ihGOsFbzwr/MdyXQCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8db699bc3d0543d048a2cd197272355b4ae7a3adb9655b718895b45ecbe23300","last_reissued_at":"2026-06-03T01:05:38.159959Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:38.159959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpeakerCard-1M: An Evidence-Grounded Speaker Card Corpus for In-the-Wild Speaker Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Dading Chong, Hang Su, Jan \\v{C}ernock\\'y, Junjie Li, Junyi Peng, Kong Aik Lee, Lichun Fan, Old\\v{r}ich Plchot, Shuai Wang, Themos Stafylakis, Xiao Song","submitted_at":"2026-06-02T07:49:30Z","abstract_excerpt":"Modern speaker verification (SV) systems rely on speaker embeddings that are effective but difficult to interpret or query in natural language. Most existing speech-text corpora target controllable synthesis or utterance-level captioning, and provide limited speaker-level supervision for in-the-wild speaker recognition. This paper introduces SpeakerCard-1M, a bilingual speaker-centric resource for evidence-grounded SV, derived from VoxCeleb1/2 and CN-Celeb1/2, where the \"-1M\" suffix refers to the 1.78M utterance-level captions contained in the release. We adopt a tool-first, LLM-last approach:"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03283","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/2606.03283/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":"2606.03283","created_at":"2026-06-03T01:05:38.160023+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03283v1","created_at":"2026-06-03T01:05:38.160023+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03283","created_at":"2026-06-03T01:05:38.160023+00:00"},{"alias_kind":"pith_short_12","alias_value":"RW3JTPB5AVB5","created_at":"2026-06-03T01:05:38.160023+00:00"},{"alias_kind":"pith_short_16","alias_value":"RW3JTPB5AVB5ASFC","created_at":"2026-06-03T01:05:38.160023+00:00"},{"alias_kind":"pith_short_8","alias_value":"RW3JTPB5","created_at":"2026-06-03T01:05:38.160023+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/RW3JTPB5AVB5ASFCZUMXE4RVLN","json":"https://pith.science/pith/RW3JTPB5AVB5ASFCZUMXE4RVLN.json","graph_json":"https://pith.science/api/pith-number/RW3JTPB5AVB5ASFCZUMXE4RVLN/graph.json","events_json":"https://pith.science/api/pith-number/RW3JTPB5AVB5ASFCZUMXE4RVLN/events.json","paper":"https://pith.science/paper/RW3JTPB5"},"agent_actions":{"view_html":"https://pith.science/pith/RW3JTPB5AVB5ASFCZUMXE4RVLN","download_json":"https://pith.science/pith/RW3JTPB5AVB5ASFCZUMXE4RVLN.json","view_paper":"https://pith.science/paper/RW3JTPB5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03283&json=true","fetch_graph":"https://pith.science/api/pith-number/RW3JTPB5AVB5ASFCZUMXE4RVLN/graph.json","fetch_events":"https://pith.science/api/pith-number/RW3JTPB5AVB5ASFCZUMXE4RVLN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RW3JTPB5AVB5ASFCZUMXE4RVLN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RW3JTPB5AVB5ASFCZUMXE4RVLN/action/storage_attestation","attest_author":"https://pith.science/pith/RW3JTPB5AVB5ASFCZUMXE4RVLN/action/author_attestation","sign_citation":"https://pith.science/pith/RW3JTPB5AVB5ASFCZUMXE4RVLN/action/citation_signature","submit_replication":"https://pith.science/pith/RW3JTPB5AVB5ASFCZUMXE4RVLN/action/replication_record"}},"created_at":"2026-06-03T01:05:38.160023+00:00","updated_at":"2026-06-03T01:05:38.160023+00:00"}