{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:CUQJKDNWIAABT6BXAKE2FHCEWM","short_pith_number":"pith:CUQJKDNW","canonical_record":{"source":{"id":"2205.02475","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-05-05T07:17:17Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"4751ead32e02efdd8f78326a6f424fb50e96d7f16f0aea3e47f4a5cb8909183d","abstract_canon_sha256":"cb0e9a5c7df8b195ccd46e64ca54d960ed924d63a1743957d5d01b43d70c76dd"},"schema_version":"1.0"},"canonical_sha256":"1520950db6400019f8370289a29c44b321b72d70ec9686e38873a5a7224ae0dd","source":{"kind":"arxiv","id":"2205.02475","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.02475","created_at":"2026-07-05T04:20:37Z"},{"alias_kind":"arxiv_version","alias_value":"2205.02475v1","created_at":"2026-07-05T04:20:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.02475","created_at":"2026-07-05T04:20:37Z"},{"alias_kind":"pith_short_12","alias_value":"CUQJKDNWIAAB","created_at":"2026-07-05T04:20:37Z"},{"alias_kind":"pith_short_16","alias_value":"CUQJKDNWIAABT6BX","created_at":"2026-07-05T04:20:37Z"},{"alias_kind":"pith_short_8","alias_value":"CUQJKDNW","created_at":"2026-07-05T04:20:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:CUQJKDNWIAABT6BXAKE2FHCEWM","target":"record","payload":{"canonical_record":{"source":{"id":"2205.02475","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-05-05T07:17:17Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"4751ead32e02efdd8f78326a6f424fb50e96d7f16f0aea3e47f4a5cb8909183d","abstract_canon_sha256":"cb0e9a5c7df8b195ccd46e64ca54d960ed924d63a1743957d5d01b43d70c76dd"},"schema_version":"1.0"},"canonical_sha256":"1520950db6400019f8370289a29c44b321b72d70ec9686e38873a5a7224ae0dd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:20:37.729158Z","signature_b64":"4dh0lvmapZCtuqyn6gYW8yO11MXY94rjD0WRyPHC8C1uNe7uUdtL03cVwY5c1m4Dn2P696zxLtn1r2ebHxGuBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1520950db6400019f8370289a29c44b321b72d70ec9686e38873a5a7224ae0dd","last_reissued_at":"2026-07-05T04:20:37.728707Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:20:37.728707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.02475","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":"2026-07-05T04:20:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HF5q2TDkeNvMpKUfr3hPK3a2uuHver5XRFHAZEtlRivp4SoWXxw4H+VUUWXVamqjpf0ITQiYtJf0IqmwKPf2CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:01:31.897565Z"},"content_sha256":"a936e1e9c68987c78d664ef6dcc99fe9a4db80840b75cc715350cf5957fc0feb","schema_version":"1.0","event_id":"sha256:a936e1e9c68987c78d664ef6dcc99fe9a4db80840b75cc715350cf5957fc0feb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:CUQJKDNWIAABT6BXAKE2FHCEWM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Speaker Recognition in the Wild","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Anirudh Gupta, Ankur Dhuriya, Harveen Singh Chadha, Neeraj Chhimwal, Priyanshi Shah, Rishabh Gaur, Vivek Raghavan","submitted_at":"2022-05-05T07:17:17Z","abstract_excerpt":"In this paper, we propose a pipeline to find the number of speakers, as well as audios belonging to each of these now identified speakers in a source of audio data where number of speakers or speaker labels are not known a priori. We used this approach as a part of our Data Preparation pipeline for Speech Recognition in Indic Languages (https://github.com/Open-Speech-EkStep/vakyansh-wav2vec2-experimentation). To understand and evaluate the accuracy of our proposed pipeline, we introduce two metrics: Cluster Purity, and Cluster Uniqueness. Cluster Purity quantifies how \"pure\" a cluster is. Clus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.02475","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/2205.02475/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":"2026-07-05T04:20:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bi1jmjmU4/YpnK1A+xc02z/ebrLMJLSPbQO/aGPihgI92xTeJXjtPGO0HtKuzRonsOE6LHPqB8ExBN8EZUVlCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:01:31.897935Z"},"content_sha256":"2c0d0df3a2b90339fd4b0ac697bb8c2b508b485d83ac62210c3a79d3efce7ffa","schema_version":"1.0","event_id":"sha256:2c0d0df3a2b90339fd4b0ac697bb8c2b508b485d83ac62210c3a79d3efce7ffa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CUQJKDNWIAABT6BXAKE2FHCEWM/bundle.json","state_url":"https://pith.science/pith/CUQJKDNWIAABT6BXAKE2FHCEWM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CUQJKDNWIAABT6BXAKE2FHCEWM/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":"2026-07-09T06:01:31Z","links":{"resolver":"https://pith.science/pith/CUQJKDNWIAABT6BXAKE2FHCEWM","bundle":"https://pith.science/pith/CUQJKDNWIAABT6BXAKE2FHCEWM/bundle.json","state":"https://pith.science/pith/CUQJKDNWIAABT6BXAKE2FHCEWM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CUQJKDNWIAABT6BXAKE2FHCEWM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CUQJKDNWIAABT6BXAKE2FHCEWM","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":"cb0e9a5c7df8b195ccd46e64ca54d960ed924d63a1743957d5d01b43d70c76dd","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-05-05T07:17:17Z","title_canon_sha256":"4751ead32e02efdd8f78326a6f424fb50e96d7f16f0aea3e47f4a5cb8909183d"},"schema_version":"1.0","source":{"id":"2205.02475","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.02475","created_at":"2026-07-05T04:20:37Z"},{"alias_kind":"arxiv_version","alias_value":"2205.02475v1","created_at":"2026-07-05T04:20:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.02475","created_at":"2026-07-05T04:20:37Z"},{"alias_kind":"pith_short_12","alias_value":"CUQJKDNWIAAB","created_at":"2026-07-05T04:20:37Z"},{"alias_kind":"pith_short_16","alias_value":"CUQJKDNWIAABT6BX","created_at":"2026-07-05T04:20:37Z"},{"alias_kind":"pith_short_8","alias_value":"CUQJKDNW","created_at":"2026-07-05T04:20:37Z"}],"graph_snapshots":[{"event_id":"sha256:2c0d0df3a2b90339fd4b0ac697bb8c2b508b485d83ac62210c3a79d3efce7ffa","target":"graph","created_at":"2026-07-05T04:20:37Z","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/2205.02475/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose a pipeline to find the number of speakers, as well as audios belonging to each of these now identified speakers in a source of audio data where number of speakers or speaker labels are not known a priori. We used this approach as a part of our Data Preparation pipeline for Speech Recognition in Indic Languages (https://github.com/Open-Speech-EkStep/vakyansh-wav2vec2-experimentation). To understand and evaluate the accuracy of our proposed pipeline, we introduce two metrics: Cluster Purity, and Cluster Uniqueness. Cluster Purity quantifies how \"pure\" a cluster is. Clus","authors_text":"Anirudh Gupta, Ankur Dhuriya, Harveen Singh Chadha, Neeraj Chhimwal, Priyanshi Shah, Rishabh Gaur, Vivek Raghavan","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-05-05T07:17:17Z","title":"Speaker Recognition in the Wild"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.02475","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:a936e1e9c68987c78d664ef6dcc99fe9a4db80840b75cc715350cf5957fc0feb","target":"record","created_at":"2026-07-05T04:20:37Z","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":"cb0e9a5c7df8b195ccd46e64ca54d960ed924d63a1743957d5d01b43d70c76dd","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-05-05T07:17:17Z","title_canon_sha256":"4751ead32e02efdd8f78326a6f424fb50e96d7f16f0aea3e47f4a5cb8909183d"},"schema_version":"1.0","source":{"id":"2205.02475","kind":"arxiv","version":1}},"canonical_sha256":"1520950db6400019f8370289a29c44b321b72d70ec9686e38873a5a7224ae0dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1520950db6400019f8370289a29c44b321b72d70ec9686e38873a5a7224ae0dd","first_computed_at":"2026-07-05T04:20:37.728707Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:20:37.728707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4dh0lvmapZCtuqyn6gYW8yO11MXY94rjD0WRyPHC8C1uNe7uUdtL03cVwY5c1m4Dn2P696zxLtn1r2ebHxGuBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:20:37.729158Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.02475","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a936e1e9c68987c78d664ef6dcc99fe9a4db80840b75cc715350cf5957fc0feb","sha256:2c0d0df3a2b90339fd4b0ac697bb8c2b508b485d83ac62210c3a79d3efce7ffa"],"state_sha256":"ff73ccc2a2ebe52b43892c86160f9f50f2a122346ef52c8f33c65af86d7ef939"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/bEEYCsU9ZNC5Kr8V3Scl0lZiuGQ/LOlLVppoJ8OQ7TVxrBfMD6z9+ZlYe/t9PprKdHT/sPdj2Sl9x66lWsXCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T06:01:31.900116Z","bundle_sha256":"6357257b07361b7cecd237d030d6c589bb930c7b7bc175185978cb02f75bd948"}}