{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4BZWNLZT6P6LVFKOXJPO7KQ7M4","short_pith_number":"pith:4BZWNLZT","schema_version":"1.0","canonical_sha256":"e07366af33f3fcba954eba5eefaa1f6705507f09b64d89e3f0a56d66e6c079b4","source":{"kind":"arxiv","id":"2506.02584","version":1},"attestation_state":"computed","paper":{"title":"Prosodic Structure Beyond Lexical Content: A Study of Self-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.CL","authors_text":"Catherine Lai, Christoph Minixhofer, Peter Bell, Sarenne Wallbridge","submitted_at":"2025-06-03T08:04:03Z","abstract_excerpt":"People exploit the predictability of lexical structures during text comprehension. Though predictable structure is also present in speech, the degree to which prosody, e.g. intonation, tempo, and loudness, contributes to such structure independently of the lexical content is unclear. This study leverages self-supervised learning (SSL) to examine the temporal granularity of structures in the acoustic correlates of prosody. Representations from our proposed Masked Prosody Model can predict perceptual labels dependent on local information, such as word boundaries, but provide the most value for l"},"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":"2506.02584","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T08:04:03Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"b34541c3eb0c594b9907594bb3bb5f7fe461e6e3244733988a356735a4da5e62","abstract_canon_sha256":"fb1b9eed57925958895168406cb15f6a216fc9fa3eeb88c845458c9ea3ad6cec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:04.753530Z","signature_b64":"g8ta30ZL08s8SztH6y99OigP9bSsO7DnVOF9yZQHv66asETQ/LHKjT0bUb2yNQ0I8Qkf762LAlIr7a2AYl/yBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e07366af33f3fcba954eba5eefaa1f6705507f09b64d89e3f0a56d66e6c079b4","last_reissued_at":"2026-07-05T11:15:04.753036Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:04.753036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prosodic Structure Beyond Lexical Content: A Study of Self-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.CL","authors_text":"Catherine Lai, Christoph Minixhofer, Peter Bell, Sarenne Wallbridge","submitted_at":"2025-06-03T08:04:03Z","abstract_excerpt":"People exploit the predictability of lexical structures during text comprehension. Though predictable structure is also present in speech, the degree to which prosody, e.g. intonation, tempo, and loudness, contributes to such structure independently of the lexical content is unclear. This study leverages self-supervised learning (SSL) to examine the temporal granularity of structures in the acoustic correlates of prosody. Representations from our proposed Masked Prosody Model can predict perceptual labels dependent on local information, such as word boundaries, but provide the most value for l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02584","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/2506.02584/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":"2506.02584","created_at":"2026-07-05T11:15:04.753091+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02584v1","created_at":"2026-07-05T11:15:04.753091+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02584","created_at":"2026-07-05T11:15:04.753091+00:00"},{"alias_kind":"pith_short_12","alias_value":"4BZWNLZT6P6L","created_at":"2026-07-05T11:15:04.753091+00:00"},{"alias_kind":"pith_short_16","alias_value":"4BZWNLZT6P6LVFKO","created_at":"2026-07-05T11:15:04.753091+00:00"},{"alias_kind":"pith_short_8","alias_value":"4BZWNLZT","created_at":"2026-07-05T11:15:04.753091+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.13229","citing_title":"ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4BZWNLZT6P6LVFKOXJPO7KQ7M4","json":"https://pith.science/pith/4BZWNLZT6P6LVFKOXJPO7KQ7M4.json","graph_json":"https://pith.science/api/pith-number/4BZWNLZT6P6LVFKOXJPO7KQ7M4/graph.json","events_json":"https://pith.science/api/pith-number/4BZWNLZT6P6LVFKOXJPO7KQ7M4/events.json","paper":"https://pith.science/paper/4BZWNLZT"},"agent_actions":{"view_html":"https://pith.science/pith/4BZWNLZT6P6LVFKOXJPO7KQ7M4","download_json":"https://pith.science/pith/4BZWNLZT6P6LVFKOXJPO7KQ7M4.json","view_paper":"https://pith.science/paper/4BZWNLZT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02584&json=true","fetch_graph":"https://pith.science/api/pith-number/4BZWNLZT6P6LVFKOXJPO7KQ7M4/graph.json","fetch_events":"https://pith.science/api/pith-number/4BZWNLZT6P6LVFKOXJPO7KQ7M4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4BZWNLZT6P6LVFKOXJPO7KQ7M4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4BZWNLZT6P6LVFKOXJPO7KQ7M4/action/storage_attestation","attest_author":"https://pith.science/pith/4BZWNLZT6P6LVFKOXJPO7KQ7M4/action/author_attestation","sign_citation":"https://pith.science/pith/4BZWNLZT6P6LVFKOXJPO7KQ7M4/action/citation_signature","submit_replication":"https://pith.science/pith/4BZWNLZT6P6LVFKOXJPO7KQ7M4/action/replication_record"}},"created_at":"2026-07-05T11:15:04.753091+00:00","updated_at":"2026-07-05T11:15:04.753091+00:00"}