{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:HCGTJJMD7UD3O7RRZSVEU7M7GL","short_pith_number":"pith:HCGTJJMD","canonical_record":{"source":{"id":"2105.11084","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-24T04:10:47Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"75d5a8f65b37e79eb4654ba2c2dfe7c0c90abc283a81e299884a345c191047b1","abstract_canon_sha256":"bf1148fa49a7bcbca81d10dad93fcd6625dc2eeeca4f50f41dbe0ba3b583a9b8"},"schema_version":"1.0"},"canonical_sha256":"388d34a583fd07b77e31ccaa4a7d9f32eb0f8bc3232a479f418239672169ab6c","source":{"kind":"arxiv","id":"2105.11084","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.11084","created_at":"2026-07-05T04:19:31Z"},{"alias_kind":"arxiv_version","alias_value":"2105.11084v3","created_at":"2026-07-05T04:19:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.11084","created_at":"2026-07-05T04:19:31Z"},{"alias_kind":"pith_short_12","alias_value":"HCGTJJMD7UD3","created_at":"2026-07-05T04:19:31Z"},{"alias_kind":"pith_short_16","alias_value":"HCGTJJMD7UD3O7RR","created_at":"2026-07-05T04:19:31Z"},{"alias_kind":"pith_short_8","alias_value":"HCGTJJMD","created_at":"2026-07-05T04:19:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:HCGTJJMD7UD3O7RRZSVEU7M7GL","target":"record","payload":{"canonical_record":{"source":{"id":"2105.11084","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-24T04:10:47Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"75d5a8f65b37e79eb4654ba2c2dfe7c0c90abc283a81e299884a345c191047b1","abstract_canon_sha256":"bf1148fa49a7bcbca81d10dad93fcd6625dc2eeeca4f50f41dbe0ba3b583a9b8"},"schema_version":"1.0"},"canonical_sha256":"388d34a583fd07b77e31ccaa4a7d9f32eb0f8bc3232a479f418239672169ab6c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:19:31.675024Z","signature_b64":"nt/AE7LW+P4RItOrESGdx3QrnBE9zaJUXalM47dcW461C1XarBviLgVdDcpvQpVrpODm8LnOf9Uv2lVAc90nAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"388d34a583fd07b77e31ccaa4a7d9f32eb0f8bc3232a479f418239672169ab6c","last_reissued_at":"2026-07-05T04:19:31.674622Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:19:31.674622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.11084","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:19:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lYPg9SyijEq1idNWAmHJZNuDaGrsgR2oIuyb2IEAkgG7v2f/BwcAC75fxZH3AsPdHzOLnMvef0sMjNM6v0rIBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T22:48:39.596764Z"},"content_sha256":"2d56525048d6e2bb349b83389fcfab9091bc8e76d24895cf9d3b8f5d5bb0a0f1","schema_version":"1.0","event_id":"sha256:2d56525048d6e2bb349b83389fcfab9091bc8e76d24895cf9d3b8f5d5bb0a0f1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:HCGTJJMD7UD3O7RRZSVEU7M7GL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Alexei Baevski, Alexis Conneau, Michael Auli, Wei-Ning Hsu","submitted_at":"2021-05-24T04:10:47Z","abstract_excerpt":"Despite rapid progress in the recent past, current speech recognition systems still require labeled training data which limits this technology to a small fraction of the languages spoken around the globe. This paper describes wav2vec-U, short for wav2vec Unsupervised, a method to train speech recognition models without any labeled data. We leverage self-supervised speech representations to segment unlabeled audio and learn a mapping from these representations to phonemes via adversarial training. The right representations are key to the success of our method. Compared to the best previous unsu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.11084","kind":"arxiv","version":3},"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/2105.11084/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":"2026-07-05T04:19:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bggmq13wUiqifcc/tlDGTkGw5ayeWGi7et9/XRZViXKkgUoUqByaL7WdwKnGjgIRQzEphHzJYkISFSjjoGOfCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T22:48:39.597272Z"},"content_sha256":"14bf4bc307dff8aacddb662e0d8d121bb7e9b1d8058699ce305e8e2c44d1e941","schema_version":"1.0","event_id":"sha256:14bf4bc307dff8aacddb662e0d8d121bb7e9b1d8058699ce305e8e2c44d1e941"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HCGTJJMD7UD3O7RRZSVEU7M7GL/bundle.json","state_url":"https://pith.science/pith/HCGTJJMD7UD3O7RRZSVEU7M7GL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HCGTJJMD7UD3O7RRZSVEU7M7GL/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":"2026-08-06T22:48:39Z","links":{"resolver":"https://pith.science/pith/HCGTJJMD7UD3O7RRZSVEU7M7GL","bundle":"https://pith.science/pith/HCGTJJMD7UD3O7RRZSVEU7M7GL/bundle.json","state":"https://pith.science/pith/HCGTJJMD7UD3O7RRZSVEU7M7GL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HCGTJJMD7UD3O7RRZSVEU7M7GL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:HCGTJJMD7UD3O7RRZSVEU7M7GL","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":"bf1148fa49a7bcbca81d10dad93fcd6625dc2eeeca4f50f41dbe0ba3b583a9b8","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-24T04:10:47Z","title_canon_sha256":"75d5a8f65b37e79eb4654ba2c2dfe7c0c90abc283a81e299884a345c191047b1"},"schema_version":"1.0","source":{"id":"2105.11084","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.11084","created_at":"2026-07-05T04:19:31Z"},{"alias_kind":"arxiv_version","alias_value":"2105.11084v3","created_at":"2026-07-05T04:19:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.11084","created_at":"2026-07-05T04:19:31Z"},{"alias_kind":"pith_short_12","alias_value":"HCGTJJMD7UD3","created_at":"2026-07-05T04:19:31Z"},{"alias_kind":"pith_short_16","alias_value":"HCGTJJMD7UD3O7RR","created_at":"2026-07-05T04:19:31Z"},{"alias_kind":"pith_short_8","alias_value":"HCGTJJMD","created_at":"2026-07-05T04:19:31Z"}],"graph_snapshots":[{"event_id":"sha256:14bf4bc307dff8aacddb662e0d8d121bb7e9b1d8058699ce305e8e2c44d1e941","target":"graph","created_at":"2026-07-05T04:19:31Z","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/2105.11084/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite rapid progress in the recent past, current speech recognition systems still require labeled training data which limits this technology to a small fraction of the languages spoken around the globe. This paper describes wav2vec-U, short for wav2vec Unsupervised, a method to train speech recognition models without any labeled data. We leverage self-supervised speech representations to segment unlabeled audio and learn a mapping from these representations to phonemes via adversarial training. The right representations are key to the success of our method. Compared to the best previous unsu","authors_text":"Alexei Baevski, Alexis Conneau, Michael Auli, Wei-Ning Hsu","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-24T04:10:47Z","title":"Unsupervised Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.11084","kind":"arxiv","version":3},"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":"sha256:2d56525048d6e2bb349b83389fcfab9091bc8e76d24895cf9d3b8f5d5bb0a0f1","target":"record","created_at":"2026-07-05T04:19:31Z","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":"bf1148fa49a7bcbca81d10dad93fcd6625dc2eeeca4f50f41dbe0ba3b583a9b8","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-24T04:10:47Z","title_canon_sha256":"75d5a8f65b37e79eb4654ba2c2dfe7c0c90abc283a81e299884a345c191047b1"},"schema_version":"1.0","source":{"id":"2105.11084","kind":"arxiv","version":3}},"canonical_sha256":"388d34a583fd07b77e31ccaa4a7d9f32eb0f8bc3232a479f418239672169ab6c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"388d34a583fd07b77e31ccaa4a7d9f32eb0f8bc3232a479f418239672169ab6c","first_computed_at":"2026-07-05T04:19:31.674622Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:19:31.674622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nt/AE7LW+P4RItOrESGdx3QrnBE9zaJUXalM47dcW461C1XarBviLgVdDcpvQpVrpODm8LnOf9Uv2lVAc90nAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:19:31.675024Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.11084","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d56525048d6e2bb349b83389fcfab9091bc8e76d24895cf9d3b8f5d5bb0a0f1","sha256:14bf4bc307dff8aacddb662e0d8d121bb7e9b1d8058699ce305e8e2c44d1e941"],"state_sha256":"a7c575b632c2365ce0db00f796d22e00452ac18898bd0dd5b26cb22907b48d58"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"djJVOC88NA4mhZdlWHvhC+pu1R5z2yrUl6sq2gIM7xnDEdmWaHWnjdEbXuiilH3oguqpIhvSjYj+dr7fi49SBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T22:48:39.602636Z","bundle_sha256":"08ab8df5578ecdec19daf64afa75b7d8445cd28ae0adc8cd025af70bc4e9ae20"}}