{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FDWEHI42JHB367LXPSE5TUFCGE","short_pith_number":"pith:FDWEHI42","schema_version":"1.0","canonical_sha256":"28ec43a39a49c3bf7d777c89d9d0a23130eb654094b1c7a3ecc5002b44ec3bc4","source":{"kind":"arxiv","id":"2305.17733","version":1},"attestation_state":"computed","paper":{"title":"Investigating Pre-trained Audio Encoders in the Low-Resource Condition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ehsan Shareghi, Gholamreza Haffari, Hao Yang, Jinming Zhao","submitted_at":"2023-05-28T14:15:19Z","abstract_excerpt":"Pre-trained speech encoders have been central to pushing state-of-the-art results across various speech understanding and generation tasks. Nonetheless, the capabilities of these encoders in low-resource settings are yet to be thoroughly explored. To address this, we conduct a comprehensive set of experiments using a representative set of 3 state-of-the-art encoders (Wav2vec2, WavLM, Whisper) in the low-resource setting across 7 speech understanding and generation tasks. We provide various quantitative and qualitative analyses on task performance, convergence speed, and representational proper"},"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":"2305.17733","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-28T14:15:19Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"055f5ad754c2214008e98f82a39729b8e4deb3f6f9b0d7279c7d07ca186e0933","abstract_canon_sha256":"5b6f01606a303ff2cdb0f38d019b2b03140b6e253f4d748412037cbd70778d1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:47.906656Z","signature_b64":"5gbCV6/65Ov+6obnR50PtAck8lnT22MCqBRkb7Vh5wLGD14alrszsvKTlGl5orHf7e7WSqzzYGildY+W8NuWCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28ec43a39a49c3bf7d777c89d9d0a23130eb654094b1c7a3ecc5002b44ec3bc4","last_reissued_at":"2026-07-05T06:14:47.906272Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:47.906272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Investigating Pre-trained Audio Encoders in the Low-Resource Condition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ehsan Shareghi, Gholamreza Haffari, Hao Yang, Jinming Zhao","submitted_at":"2023-05-28T14:15:19Z","abstract_excerpt":"Pre-trained speech encoders have been central to pushing state-of-the-art results across various speech understanding and generation tasks. Nonetheless, the capabilities of these encoders in low-resource settings are yet to be thoroughly explored. To address this, we conduct a comprehensive set of experiments using a representative set of 3 state-of-the-art encoders (Wav2vec2, WavLM, Whisper) in the low-resource setting across 7 speech understanding and generation tasks. We provide various quantitative and qualitative analyses on task performance, convergence speed, and representational proper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17733","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/2305.17733/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":"2305.17733","created_at":"2026-07-05T06:14:47.906331+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.17733v1","created_at":"2026-07-05T06:14:47.906331+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17733","created_at":"2026-07-05T06:14:47.906331+00:00"},{"alias_kind":"pith_short_12","alias_value":"FDWEHI42JHB3","created_at":"2026-07-05T06:14:47.906331+00:00"},{"alias_kind":"pith_short_16","alias_value":"FDWEHI42JHB367LX","created_at":"2026-07-05T06:14:47.906331+00:00"},{"alias_kind":"pith_short_8","alias_value":"FDWEHI42","created_at":"2026-07-05T06:14:47.906331+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.01496","citing_title":"Continual Speech Learning with Fused Speech Features","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FDWEHI42JHB367LXPSE5TUFCGE","json":"https://pith.science/pith/FDWEHI42JHB367LXPSE5TUFCGE.json","graph_json":"https://pith.science/api/pith-number/FDWEHI42JHB367LXPSE5TUFCGE/graph.json","events_json":"https://pith.science/api/pith-number/FDWEHI42JHB367LXPSE5TUFCGE/events.json","paper":"https://pith.science/paper/FDWEHI42"},"agent_actions":{"view_html":"https://pith.science/pith/FDWEHI42JHB367LXPSE5TUFCGE","download_json":"https://pith.science/pith/FDWEHI42JHB367LXPSE5TUFCGE.json","view_paper":"https://pith.science/paper/FDWEHI42","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.17733&json=true","fetch_graph":"https://pith.science/api/pith-number/FDWEHI42JHB367LXPSE5TUFCGE/graph.json","fetch_events":"https://pith.science/api/pith-number/FDWEHI42JHB367LXPSE5TUFCGE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FDWEHI42JHB367LXPSE5TUFCGE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FDWEHI42JHB367LXPSE5TUFCGE/action/storage_attestation","attest_author":"https://pith.science/pith/FDWEHI42JHB367LXPSE5TUFCGE/action/author_attestation","sign_citation":"https://pith.science/pith/FDWEHI42JHB367LXPSE5TUFCGE/action/citation_signature","submit_replication":"https://pith.science/pith/FDWEHI42JHB367LXPSE5TUFCGE/action/replication_record"}},"created_at":"2026-07-05T06:14:47.906331+00:00","updated_at":"2026-07-05T06:14:47.906331+00:00"}