{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:T6P6QVBWNUNP63MNHGOFI4XMDT","short_pith_number":"pith:T6P6QVBW","schema_version":"1.0","canonical_sha256":"9f9fe854366d1aff6d8d399c5472ec1ceb6f34625aa177f728045b930d1ea354","source":{"kind":"arxiv","id":"1912.07875","version":1},"attestation_state":"computed","paper":{"title":"Libri-Light: A Benchmark for ASR with Limited or No Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Abdelrahman Mohamed, Armand Joulin, Christian Fuegen, Emmanuel Dupoux, Evgeny Kharitonov, Gabriel Synnaeve, Jacob Kahn, Julien Karadayi, Morgane Rivi\\`ere, Pierre-Emmanuel Mazar\\'e, Qiantong Xu, Ronan Collobert, Tatiana Likhomanenko, Vitaliy Liptchinsky, Weiyi Zheng","submitted_at":"2019-12-17T08:47:30Z","abstract_excerpt":"We introduce a new collection of spoken English audio suitable for training speech recognition systems under limited or no supervision. It is derived from open-source audio books from the LibriVox project. It contains over 60K hours of audio, which is, to our knowledge, the largest freely-available corpus of speech. The audio has been segmented using voice activity detection and is tagged with SNR, speaker ID and genre descriptions. Additionally, we provide baseline systems and evaluation metrics working under three settings: (1) the zero resource/unsupervised setting (ABX), (2) the semi-super"},"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":"1912.07875","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-12-17T08:47:30Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"2e5fc45e0ab41d38156385b42676c60f538d54986c12092bf486ce01e6acbd57","abstract_canon_sha256":"cdf7707c78c61ea401254151315e1a126f61f7271015ac2f526b93495cf65669"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:01:01.836723Z","signature_b64":"KDQGWMcxZERz0VUmFzi45tT+8MzLRnGuSYB9l3+UtLeJpzuNDg9tMkoQKuQ6po/ic9NXsoG31A1+fWoBMmp+Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f9fe854366d1aff6d8d399c5472ec1ceb6f34625aa177f728045b930d1ea354","last_reissued_at":"2026-07-05T01:01:01.836322Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:01:01.836322Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Libri-Light: A Benchmark for ASR with Limited or No Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Abdelrahman Mohamed, Armand Joulin, Christian Fuegen, Emmanuel Dupoux, Evgeny Kharitonov, Gabriel Synnaeve, Jacob Kahn, Julien Karadayi, Morgane Rivi\\`ere, Pierre-Emmanuel Mazar\\'e, Qiantong Xu, Ronan Collobert, Tatiana Likhomanenko, Vitaliy Liptchinsky, Weiyi Zheng","submitted_at":"2019-12-17T08:47:30Z","abstract_excerpt":"We introduce a new collection of spoken English audio suitable for training speech recognition systems under limited or no supervision. It is derived from open-source audio books from the LibriVox project. It contains over 60K hours of audio, which is, to our knowledge, the largest freely-available corpus of speech. The audio has been segmented using voice activity detection and is tagged with SNR, speaker ID and genre descriptions. Additionally, we provide baseline systems and evaluation metrics working under three settings: (1) the zero resource/unsupervised setting (ABX), (2) the semi-super"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.07875","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/1912.07875/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":"1912.07875","created_at":"2026-07-05T01:01:01.836375+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.07875v1","created_at":"2026-07-05T01:01:01.836375+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.07875","created_at":"2026-07-05T01:01:01.836375+00:00"},{"alias_kind":"pith_short_12","alias_value":"T6P6QVBWNUNP","created_at":"2026-07-05T01:01:01.836375+00:00"},{"alias_kind":"pith_short_16","alias_value":"T6P6QVBWNUNP63MN","created_at":"2026-07-05T01:01:01.836375+00:00"},{"alias_kind":"pith_short_8","alias_value":"T6P6QVBW","created_at":"2026-07-05T01:01:01.836375+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.17841","citing_title":"TEDI: Trustworthy and Ethical Dataset Indicators to Analyze and Compare Dataset Documentation","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T6P6QVBWNUNP63MNHGOFI4XMDT","json":"https://pith.science/pith/T6P6QVBWNUNP63MNHGOFI4XMDT.json","graph_json":"https://pith.science/api/pith-number/T6P6QVBWNUNP63MNHGOFI4XMDT/graph.json","events_json":"https://pith.science/api/pith-number/T6P6QVBWNUNP63MNHGOFI4XMDT/events.json","paper":"https://pith.science/paper/T6P6QVBW"},"agent_actions":{"view_html":"https://pith.science/pith/T6P6QVBWNUNP63MNHGOFI4XMDT","download_json":"https://pith.science/pith/T6P6QVBWNUNP63MNHGOFI4XMDT.json","view_paper":"https://pith.science/paper/T6P6QVBW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.07875&json=true","fetch_graph":"https://pith.science/api/pith-number/T6P6QVBWNUNP63MNHGOFI4XMDT/graph.json","fetch_events":"https://pith.science/api/pith-number/T6P6QVBWNUNP63MNHGOFI4XMDT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T6P6QVBWNUNP63MNHGOFI4XMDT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T6P6QVBWNUNP63MNHGOFI4XMDT/action/storage_attestation","attest_author":"https://pith.science/pith/T6P6QVBWNUNP63MNHGOFI4XMDT/action/author_attestation","sign_citation":"https://pith.science/pith/T6P6QVBWNUNP63MNHGOFI4XMDT/action/citation_signature","submit_replication":"https://pith.science/pith/T6P6QVBWNUNP63MNHGOFI4XMDT/action/replication_record"}},"created_at":"2026-07-05T01:01:01.836375+00:00","updated_at":"2026-07-05T01:01:01.836375+00:00"}