{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:I4C5LIMY4FWYTRXTCURJO5AGNS","short_pith_number":"pith:I4C5LIMY","schema_version":"1.0","canonical_sha256":"4705d5a198e16d89c6f315229774066ca4e95265115d0188452de9d4cf807f34","source":{"kind":"arxiv","id":"2205.15819","version":1},"attestation_state":"computed","paper":{"title":"Do self-supervised speech models develop human-like perception biases?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ewan Dunbar, Juliette Millet","submitted_at":"2022-05-31T14:21:40Z","abstract_excerpt":"Self-supervised models for speech processing form representational spaces without using any external labels. Increasingly, they appear to be a feasible way of at least partially eliminating costly manual annotations, a problem of particular concern for low-resource languages. But what kind of representational spaces do these models construct? Human perception specializes to the sounds of listeners' native languages. Does the same thing happen in self-supervised models? We examine the representational spaces of three kinds of state-of-the-art self-supervised models: wav2vec 2.0, HuBERT and cont"},"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":"2205.15819","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-31T14:21:40Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"4cdfcacff1e1491e7e82b7ca9de95f601599aa3adf836b3b3f8b6c6d7bb104c6","abstract_canon_sha256":"34e99aa02322aaccb4a629cd722b2b2d9449dc2de07812baca30286370c8b308"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:28:02.694727Z","signature_b64":"jW1kgvHV4Pu+u+5/37BzhtXSd0PZ4pmO8cU0LR1UWxYz55S6zXGZAu7HuS+n6vz+iec5vnEU66l1G11eVVCWAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4705d5a198e16d89c6f315229774066ca4e95265115d0188452de9d4cf807f34","last_reissued_at":"2026-07-05T04:28:02.694211Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:28:02.694211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do self-supervised speech models develop human-like perception biases?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ewan Dunbar, Juliette Millet","submitted_at":"2022-05-31T14:21:40Z","abstract_excerpt":"Self-supervised models for speech processing form representational spaces without using any external labels. Increasingly, they appear to be a feasible way of at least partially eliminating costly manual annotations, a problem of particular concern for low-resource languages. But what kind of representational spaces do these models construct? Human perception specializes to the sounds of listeners' native languages. Does the same thing happen in self-supervised models? We examine the representational spaces of three kinds of state-of-the-art self-supervised models: wav2vec 2.0, HuBERT and cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15819","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/2205.15819/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":"2205.15819","created_at":"2026-07-05T04:28:02.694286+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.15819v1","created_at":"2026-07-05T04:28:02.694286+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15819","created_at":"2026-07-05T04:28:02.694286+00:00"},{"alias_kind":"pith_short_12","alias_value":"I4C5LIMY4FWY","created_at":"2026-07-05T04:28:02.694286+00:00"},{"alias_kind":"pith_short_16","alias_value":"I4C5LIMY4FWYTRXT","created_at":"2026-07-05T04:28:02.694286+00:00"},{"alias_kind":"pith_short_8","alias_value":"I4C5LIMY","created_at":"2026-07-05T04:28:02.694286+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11542","citing_title":"Pretrained self-supervised speech models can recognize unseen consonants","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I4C5LIMY4FWYTRXTCURJO5AGNS","json":"https://pith.science/pith/I4C5LIMY4FWYTRXTCURJO5AGNS.json","graph_json":"https://pith.science/api/pith-number/I4C5LIMY4FWYTRXTCURJO5AGNS/graph.json","events_json":"https://pith.science/api/pith-number/I4C5LIMY4FWYTRXTCURJO5AGNS/events.json","paper":"https://pith.science/paper/I4C5LIMY"},"agent_actions":{"view_html":"https://pith.science/pith/I4C5LIMY4FWYTRXTCURJO5AGNS","download_json":"https://pith.science/pith/I4C5LIMY4FWYTRXTCURJO5AGNS.json","view_paper":"https://pith.science/paper/I4C5LIMY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.15819&json=true","fetch_graph":"https://pith.science/api/pith-number/I4C5LIMY4FWYTRXTCURJO5AGNS/graph.json","fetch_events":"https://pith.science/api/pith-number/I4C5LIMY4FWYTRXTCURJO5AGNS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I4C5LIMY4FWYTRXTCURJO5AGNS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I4C5LIMY4FWYTRXTCURJO5AGNS/action/storage_attestation","attest_author":"https://pith.science/pith/I4C5LIMY4FWYTRXTCURJO5AGNS/action/author_attestation","sign_citation":"https://pith.science/pith/I4C5LIMY4FWYTRXTCURJO5AGNS/action/citation_signature","submit_replication":"https://pith.science/pith/I4C5LIMY4FWYTRXTCURJO5AGNS/action/replication_record"}},"created_at":"2026-07-05T04:28:02.694286+00:00","updated_at":"2026-07-05T04:28:02.694286+00:00"}