{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:LCQHOB224GDECUR4JQOTXVI5RH","short_pith_number":"pith:LCQHOB22","schema_version":"1.0","canonical_sha256":"58a077075ae18641523c4c1d3bd51d89dc17fbfd7f705a99f586b7cf86f029b8","source":{"kind":"arxiv","id":"2107.04734","version":3},"attestation_state":"computed","paper":{"title":"Layer-wise Analysis of a Self-supervised Speech Representation Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ankita Pasad, Ju-chieh Chou, Karen Livescu","submitted_at":"2021-07-10T02:13:25Z","abstract_excerpt":"Recently proposed self-supervised learning approaches have been successful for pre-training speech representation models. The utility of these learned representations has been observed empirically, but not much has been studied about the type or extent of information encoded in the pre-trained representations themselves. Developing such insights can help understand the capabilities and limits of these models and enable the research community to more efficiently develop their usage for downstream applications. In this work, we begin to fill this gap by examining one recent and successful pre-tr"},"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":"2107.04734","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-07-10T02:13:25Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"c3970522a4f87e463540296c41fb1b01de1b1ce094b85951c2d22ae17208c900","abstract_canon_sha256":"301399e938c9e2f67cc490c12f0b5e72f094e0e30dd87269561285f229c5c629"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:21:53.035730Z","signature_b64":"nTRtfYaXSLErCJhT7OlZXLgRPqYcLvbhlKKVKYHfkZ9Kq3ex6hujPPzDTFmlgj2DfM3eDOEutioGE3ye1RNxCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58a077075ae18641523c4c1d3bd51d89dc17fbfd7f705a99f586b7cf86f029b8","last_reissued_at":"2026-07-05T05:21:53.035225Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:21:53.035225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Layer-wise Analysis of a Self-supervised Speech Representation Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ankita Pasad, Ju-chieh Chou, Karen Livescu","submitted_at":"2021-07-10T02:13:25Z","abstract_excerpt":"Recently proposed self-supervised learning approaches have been successful for pre-training speech representation models. The utility of these learned representations has been observed empirically, but not much has been studied about the type or extent of information encoded in the pre-trained representations themselves. Developing such insights can help understand the capabilities and limits of these models and enable the research community to more efficiently develop their usage for downstream applications. In this work, we begin to fill this gap by examining one recent and successful pre-tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.04734","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/2107.04734/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":"2107.04734","created_at":"2026-07-05T05:21:53.035283+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.04734v3","created_at":"2026-07-05T05:21:53.035283+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.04734","created_at":"2026-07-05T05:21:53.035283+00:00"},{"alias_kind":"pith_short_12","alias_value":"LCQHOB224GDE","created_at":"2026-07-05T05:21:53.035283+00:00"},{"alias_kind":"pith_short_16","alias_value":"LCQHOB224GDECUR4","created_at":"2026-07-05T05:21:53.035283+00:00"},{"alias_kind":"pith_short_8","alias_value":"LCQHOB22","created_at":"2026-07-05T05:21:53.035283+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27206","citing_title":"Syntactic Belief Update as the Driver of Garden Path Processing Difficulty","ref_index":192,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12809","citing_title":"Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces","ref_index":202,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22631","citing_title":"Identifying and typifying demographic unfairness in phoneme-level embeddings of self-supervised speech recognition models","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LCQHOB224GDECUR4JQOTXVI5RH","json":"https://pith.science/pith/LCQHOB224GDECUR4JQOTXVI5RH.json","graph_json":"https://pith.science/api/pith-number/LCQHOB224GDECUR4JQOTXVI5RH/graph.json","events_json":"https://pith.science/api/pith-number/LCQHOB224GDECUR4JQOTXVI5RH/events.json","paper":"https://pith.science/paper/LCQHOB22"},"agent_actions":{"view_html":"https://pith.science/pith/LCQHOB224GDECUR4JQOTXVI5RH","download_json":"https://pith.science/pith/LCQHOB224GDECUR4JQOTXVI5RH.json","view_paper":"https://pith.science/paper/LCQHOB22","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.04734&json=true","fetch_graph":"https://pith.science/api/pith-number/LCQHOB224GDECUR4JQOTXVI5RH/graph.json","fetch_events":"https://pith.science/api/pith-number/LCQHOB224GDECUR4JQOTXVI5RH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LCQHOB224GDECUR4JQOTXVI5RH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LCQHOB224GDECUR4JQOTXVI5RH/action/storage_attestation","attest_author":"https://pith.science/pith/LCQHOB224GDECUR4JQOTXVI5RH/action/author_attestation","sign_citation":"https://pith.science/pith/LCQHOB224GDECUR4JQOTXVI5RH/action/citation_signature","submit_replication":"https://pith.science/pith/LCQHOB224GDECUR4JQOTXVI5RH/action/replication_record"}},"created_at":"2026-07-05T05:21:53.035283+00:00","updated_at":"2026-07-05T05:21:53.035283+00:00"}