{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IDNYCH3DX2A5I4YITTYJX3FFH5","short_pith_number":"pith:IDNYCH3D","schema_version":"1.0","canonical_sha256":"40db811f63be81d473089cf09beca53f556f4fcfcc8a248a47b7bb54474d07f3","source":{"kind":"arxiv","id":"2508.12255","version":1},"attestation_state":"computed","paper":{"title":"What do Speech Foundation Models Learn? Analysis and Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Ankita Pasad","submitted_at":"2025-08-17T06:31:34Z","abstract_excerpt":"Speech foundation models (SFMs) are designed to serve as general-purpose representations for a wide range of speech-processing tasks. The last five years have seen an influx of increasingly successful self-supervised and supervised pre-trained models with impressive performance on various downstream tasks.\n  Although the zoo of SFMs continues to grow, our understanding of the knowledge they acquire lags behind. This thesis presents a lightweight analysis framework using statistical tools and training-free tasks to investigate the acoustic and linguistic knowledge encoded in SFM layers. We cond"},"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":"2508.12255","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-17T06:31:34Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"bf7d0c1ee04d903810b333d3229d73193aa7802472d29da86f3e6ad7002480ad","abstract_canon_sha256":"87ecac4f7671bd3d9b32077fa21445275ae061055c6c891121c71dd8309271bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:02.436898Z","signature_b64":"VshCrY4uelCtxXY680Ey5v10o2ei0wxlTwo95LIqp6XcQ5jQRLYBc4UTTD4xYJPZcAUBYp0EfWoeV4pRK4iYCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40db811f63be81d473089cf09beca53f556f4fcfcc8a248a47b7bb54474d07f3","last_reissued_at":"2026-07-05T11:55:02.436472Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:02.436472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What do Speech Foundation Models Learn? Analysis and Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Ankita Pasad","submitted_at":"2025-08-17T06:31:34Z","abstract_excerpt":"Speech foundation models (SFMs) are designed to serve as general-purpose representations for a wide range of speech-processing tasks. The last five years have seen an influx of increasingly successful self-supervised and supervised pre-trained models with impressive performance on various downstream tasks.\n  Although the zoo of SFMs continues to grow, our understanding of the knowledge they acquire lags behind. This thesis presents a lightweight analysis framework using statistical tools and training-free tasks to investigate the acoustic and linguistic knowledge encoded in SFM layers. We cond"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12255","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/2508.12255/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":"2508.12255","created_at":"2026-07-05T11:55:02.436531+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.12255v1","created_at":"2026-07-05T11:55:02.436531+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12255","created_at":"2026-07-05T11:55:02.436531+00:00"},{"alias_kind":"pith_short_12","alias_value":"IDNYCH3DX2A5","created_at":"2026-07-05T11:55:02.436531+00:00"},{"alias_kind":"pith_short_16","alias_value":"IDNYCH3DX2A5I4YI","created_at":"2026-07-05T11:55:02.436531+00:00"},{"alias_kind":"pith_short_8","alias_value":"IDNYCH3D","created_at":"2026-07-05T11:55:02.436531+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IDNYCH3DX2A5I4YITTYJX3FFH5","json":"https://pith.science/pith/IDNYCH3DX2A5I4YITTYJX3FFH5.json","graph_json":"https://pith.science/api/pith-number/IDNYCH3DX2A5I4YITTYJX3FFH5/graph.json","events_json":"https://pith.science/api/pith-number/IDNYCH3DX2A5I4YITTYJX3FFH5/events.json","paper":"https://pith.science/paper/IDNYCH3D"},"agent_actions":{"view_html":"https://pith.science/pith/IDNYCH3DX2A5I4YITTYJX3FFH5","download_json":"https://pith.science/pith/IDNYCH3DX2A5I4YITTYJX3FFH5.json","view_paper":"https://pith.science/paper/IDNYCH3D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.12255&json=true","fetch_graph":"https://pith.science/api/pith-number/IDNYCH3DX2A5I4YITTYJX3FFH5/graph.json","fetch_events":"https://pith.science/api/pith-number/IDNYCH3DX2A5I4YITTYJX3FFH5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IDNYCH3DX2A5I4YITTYJX3FFH5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IDNYCH3DX2A5I4YITTYJX3FFH5/action/storage_attestation","attest_author":"https://pith.science/pith/IDNYCH3DX2A5I4YITTYJX3FFH5/action/author_attestation","sign_citation":"https://pith.science/pith/IDNYCH3DX2A5I4YITTYJX3FFH5/action/citation_signature","submit_replication":"https://pith.science/pith/IDNYCH3DX2A5I4YITTYJX3FFH5/action/replication_record"}},"created_at":"2026-07-05T11:55:02.436531+00:00","updated_at":"2026-07-05T11:55:02.436531+00:00"}