{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:R3MKID6QKX6GSTHVIQPL7M74JU","short_pith_number":"pith:R3MKID6Q","schema_version":"1.0","canonical_sha256":"8ed8a40fd055fc694cf5441ebfb3fc4d1ffb4a077922cbdd7f989c311f682601","source":{"kind":"arxiv","id":"2001.11128","version":1},"attestation_state":"computed","paper":{"title":"Learning Robust and Multilingual Speech Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.CL","authors_text":"Aaron van den Oord, Chris Dyer, Kazuya Kawakami, Luyu Wang, Phil Blunsom","submitted_at":"2020-01-29T23:24:56Z","abstract_excerpt":"Unsupervised speech representation learning has shown remarkable success at finding representations that correlate with phonetic structures and improve downstream speech recognition performance. However, most research has been focused on evaluating the representations in terms of their ability to improve the performance of speech recognition systems on read English (e.g. Wall Street Journal and LibriSpeech). This evaluation methodology overlooks two important desiderata that speech representations should have: robustness to domain shifts and transferability to other languages. In this paper we"},"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":"2001.11128","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-01-29T23:24:56Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"c02683f34a1841891ae92b1ccc85002078d1bf514210a1d49918854ebed2ff39","abstract_canon_sha256":"4d67f5a2737ec46da805ebf5c16742658735f981713e00ea7e323ed49229cd7a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:37:20.859634Z","signature_b64":"gwTnByHbcGOeMW90eeiYmxEtYBJ4HnqqwwSm011cxfx1/5dCaDfOG/pemqrzzr4MAhhc/dE9//yMW3Ixqj/zBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ed8a40fd055fc694cf5441ebfb3fc4d1ffb4a077922cbdd7f989c311f682601","last_reissued_at":"2026-07-05T00:37:20.859131Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:37:20.859131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Robust and Multilingual Speech Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.CL","authors_text":"Aaron van den Oord, Chris Dyer, Kazuya Kawakami, Luyu Wang, Phil Blunsom","submitted_at":"2020-01-29T23:24:56Z","abstract_excerpt":"Unsupervised speech representation learning has shown remarkable success at finding representations that correlate with phonetic structures and improve downstream speech recognition performance. However, most research has been focused on evaluating the representations in terms of their ability to improve the performance of speech recognition systems on read English (e.g. Wall Street Journal and LibriSpeech). This evaluation methodology overlooks two important desiderata that speech representations should have: robustness to domain shifts and transferability to other languages. In this paper we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.11128","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/2001.11128/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":"2001.11128","created_at":"2026-07-05T00:37:20.859194+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.11128v1","created_at":"2026-07-05T00:37:20.859194+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.11128","created_at":"2026-07-05T00:37:20.859194+00:00"},{"alias_kind":"pith_short_12","alias_value":"R3MKID6QKX6G","created_at":"2026-07-05T00:37:20.859194+00:00"},{"alias_kind":"pith_short_16","alias_value":"R3MKID6QKX6GSTHV","created_at":"2026-07-05T00:37:20.859194+00:00"},{"alias_kind":"pith_short_8","alias_value":"R3MKID6Q","created_at":"2026-07-05T00:37:20.859194+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01381","citing_title":"A framework for analyzing concept representations in neural models","ref_index":180,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R3MKID6QKX6GSTHVIQPL7M74JU","json":"https://pith.science/pith/R3MKID6QKX6GSTHVIQPL7M74JU.json","graph_json":"https://pith.science/api/pith-number/R3MKID6QKX6GSTHVIQPL7M74JU/graph.json","events_json":"https://pith.science/api/pith-number/R3MKID6QKX6GSTHVIQPL7M74JU/events.json","paper":"https://pith.science/paper/R3MKID6Q"},"agent_actions":{"view_html":"https://pith.science/pith/R3MKID6QKX6GSTHVIQPL7M74JU","download_json":"https://pith.science/pith/R3MKID6QKX6GSTHVIQPL7M74JU.json","view_paper":"https://pith.science/paper/R3MKID6Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.11128&json=true","fetch_graph":"https://pith.science/api/pith-number/R3MKID6QKX6GSTHVIQPL7M74JU/graph.json","fetch_events":"https://pith.science/api/pith-number/R3MKID6QKX6GSTHVIQPL7M74JU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R3MKID6QKX6GSTHVIQPL7M74JU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R3MKID6QKX6GSTHVIQPL7M74JU/action/storage_attestation","attest_author":"https://pith.science/pith/R3MKID6QKX6GSTHVIQPL7M74JU/action/author_attestation","sign_citation":"https://pith.science/pith/R3MKID6QKX6GSTHVIQPL7M74JU/action/citation_signature","submit_replication":"https://pith.science/pith/R3MKID6QKX6GSTHVIQPL7M74JU/action/replication_record"}},"created_at":"2026-07-05T00:37:20.859194+00:00","updated_at":"2026-07-05T00:37:20.859194+00:00"}