{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:U5IYKNGAXD4QBG4I2IAJH23OZL","short_pith_number":"pith:U5IYKNGA","canonical_record":{"source":{"id":"2407.04652","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-05T17:07:58Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"cd20436813b5c6da8bbab5cad4f94a255a0626d3a184d764fe1477d25846e0c4","abstract_canon_sha256":"fa02bc663418fffa83eaefdab718014d2df9a23b47a01e403f50c578588fe540"},"schema_version":"1.0"},"canonical_sha256":"a7518534c0b8f9009b88d20093eb6ecad03452a1498f7a3277abdd1233445a65","source":{"kind":"arxiv","id":"2407.04652","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.04652","created_at":"2026-07-05T08:40:36Z"},{"alias_kind":"arxiv_version","alias_value":"2407.04652v1","created_at":"2026-07-05T08:40:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04652","created_at":"2026-07-05T08:40:36Z"},{"alias_kind":"pith_short_12","alias_value":"U5IYKNGAXD4Q","created_at":"2026-07-05T08:40:36Z"},{"alias_kind":"pith_short_16","alias_value":"U5IYKNGAXD4QBG4I","created_at":"2026-07-05T08:40:36Z"},{"alias_kind":"pith_short_8","alias_value":"U5IYKNGA","created_at":"2026-07-05T08:40:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:U5IYKNGAXD4QBG4I2IAJH23OZL","target":"record","payload":{"canonical_record":{"source":{"id":"2407.04652","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-05T17:07:58Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"cd20436813b5c6da8bbab5cad4f94a255a0626d3a184d764fe1477d25846e0c4","abstract_canon_sha256":"fa02bc663418fffa83eaefdab718014d2df9a23b47a01e403f50c578588fe540"},"schema_version":"1.0"},"canonical_sha256":"a7518534c0b8f9009b88d20093eb6ecad03452a1498f7a3277abdd1233445a65","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:40:36.703204Z","signature_b64":"4PhrWA5+pruqIfmvOYFac682hP9xgSu4pSea3itVqgRJNRSRuhJg8qZAqimaoDFFPxSqKiYkrSksNI52A7O+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7518534c0b8f9009b88d20093eb6ecad03452a1498f7a3277abdd1233445a65","last_reissued_at":"2026-07-05T08:40:36.702643Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:40:36.702643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.04652","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":"2026-07-05T08:40:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L6iQkrf7Rm+l2q9tF8cz0303/DaP20mI6PCGIcJ9qvDHaDoiwBaWTg9nvt0WNpm4LnIXDDSSRXtCyuTHVTvdCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T12:46:09.665925Z"},"content_sha256":"b2a659554aa7286083554ef84fe97bbce44f65f4cbb00f7fd2af462d470641e3","schema_version":"1.0","event_id":"sha256:b2a659554aa7286083554ef84fe97bbce44f65f4cbb00f7fd2af462d470641e3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:U5IYKNGAXD4QBG4I2IAJH23OZL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pretraining End-to-End Keyword Search with Automatically Discovered Acoustic Units","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Bolaji Yusuf, Jan \"Honza\" \\v{C}ernock\\'y, Murat Sara\\c{c}lar","submitted_at":"2024-07-05T17:07:58Z","abstract_excerpt":"End-to-end (E2E) keyword search (KWS) has emerged as an alternative and complimentary approach to conventional keyword search which depends on the output of automatic speech recognition (ASR) systems. While E2E methods greatly simplify the KWS pipeline, they generally have worse performance than their ASR-based counterparts, which can benefit from pretraining with untranscribed data. In this work, we propose a method for pretraining E2E KWS systems with untranscribed data, which involves using acoustic unit discovery (AUD) to obtain discrete units for untranscribed data and then learning to lo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04652","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/2407.04652/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":"2026-07-05T08:40:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S2pNNZhWqFsX0K3QvcWkowzJHFcaAR0lLdPAhUwBscSlN+NHpI+LXBmUQ8vNatqVoOBjvMgWwF2wDNE4dvHzAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T12:46:09.666699Z"},"content_sha256":"69062b7f42b2fe3b5c6a8b609e0440aa73d94efa167ccc682cffaa36ee518c2d","schema_version":"1.0","event_id":"sha256:69062b7f42b2fe3b5c6a8b609e0440aa73d94efa167ccc682cffaa36ee518c2d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U5IYKNGAXD4QBG4I2IAJH23OZL/bundle.json","state_url":"https://pith.science/pith/U5IYKNGAXD4QBG4I2IAJH23OZL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U5IYKNGAXD4QBG4I2IAJH23OZL/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":"2026-08-15T12:46:09Z","links":{"resolver":"https://pith.science/pith/U5IYKNGAXD4QBG4I2IAJH23OZL","bundle":"https://pith.science/pith/U5IYKNGAXD4QBG4I2IAJH23OZL/bundle.json","state":"https://pith.science/pith/U5IYKNGAXD4QBG4I2IAJH23OZL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U5IYKNGAXD4QBG4I2IAJH23OZL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:U5IYKNGAXD4QBG4I2IAJH23OZL","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":"fa02bc663418fffa83eaefdab718014d2df9a23b47a01e403f50c578588fe540","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-05T17:07:58Z","title_canon_sha256":"cd20436813b5c6da8bbab5cad4f94a255a0626d3a184d764fe1477d25846e0c4"},"schema_version":"1.0","source":{"id":"2407.04652","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.04652","created_at":"2026-07-05T08:40:36Z"},{"alias_kind":"arxiv_version","alias_value":"2407.04652v1","created_at":"2026-07-05T08:40:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04652","created_at":"2026-07-05T08:40:36Z"},{"alias_kind":"pith_short_12","alias_value":"U5IYKNGAXD4Q","created_at":"2026-07-05T08:40:36Z"},{"alias_kind":"pith_short_16","alias_value":"U5IYKNGAXD4QBG4I","created_at":"2026-07-05T08:40:36Z"},{"alias_kind":"pith_short_8","alias_value":"U5IYKNGA","created_at":"2026-07-05T08:40:36Z"}],"graph_snapshots":[{"event_id":"sha256:69062b7f42b2fe3b5c6a8b609e0440aa73d94efa167ccc682cffaa36ee518c2d","target":"graph","created_at":"2026-07-05T08:40:36Z","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/2407.04652/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"End-to-end (E2E) keyword search (KWS) has emerged as an alternative and complimentary approach to conventional keyword search which depends on the output of automatic speech recognition (ASR) systems. While E2E methods greatly simplify the KWS pipeline, they generally have worse performance than their ASR-based counterparts, which can benefit from pretraining with untranscribed data. In this work, we propose a method for pretraining E2E KWS systems with untranscribed data, which involves using acoustic unit discovery (AUD) to obtain discrete units for untranscribed data and then learning to lo","authors_text":"Bolaji Yusuf, Jan \"Honza\" \\v{C}ernock\\'y, Murat Sara\\c{c}lar","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-05T17:07:58Z","title":"Pretraining End-to-End Keyword Search with Automatically Discovered Acoustic Units"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04652","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:b2a659554aa7286083554ef84fe97bbce44f65f4cbb00f7fd2af462d470641e3","target":"record","created_at":"2026-07-05T08:40:36Z","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":"fa02bc663418fffa83eaefdab718014d2df9a23b47a01e403f50c578588fe540","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-05T17:07:58Z","title_canon_sha256":"cd20436813b5c6da8bbab5cad4f94a255a0626d3a184d764fe1477d25846e0c4"},"schema_version":"1.0","source":{"id":"2407.04652","kind":"arxiv","version":1}},"canonical_sha256":"a7518534c0b8f9009b88d20093eb6ecad03452a1498f7a3277abdd1233445a65","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7518534c0b8f9009b88d20093eb6ecad03452a1498f7a3277abdd1233445a65","first_computed_at":"2026-07-05T08:40:36.702643Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:40:36.702643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4PhrWA5+pruqIfmvOYFac682hP9xgSu4pSea3itVqgRJNRSRuhJg8qZAqimaoDFFPxSqKiYkrSksNI52A7O+CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:40:36.703204Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.04652","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2a659554aa7286083554ef84fe97bbce44f65f4cbb00f7fd2af462d470641e3","sha256:69062b7f42b2fe3b5c6a8b609e0440aa73d94efa167ccc682cffaa36ee518c2d"],"state_sha256":"844f19b30b51cff33840db74b58df09f0f3876ce2ddb1d3dccb648b26aef8caa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sCRjb37fs994ScdMcCIyVHDns3d+ojl9b9BMR2bL6RBv0ktCqKM/0K9NzX1ov7TdfEdLh7Qx7zZkbpinS3O7Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T12:46:09.671683Z","bundle_sha256":"6e83809a62a280057d0b10f905f244194f4517db6faec5e8a2506c583879253e"}}