{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZVZITOL3CND3Z7ZGLHBCC3A4DQ","short_pith_number":"pith:ZVZITOL3","schema_version":"1.0","canonical_sha256":"cd7289b97b1347bcff2659c2216c1c1c0e32e6af54c6e538bf443fabda8decd2","source":{"kind":"arxiv","id":"2608.11587","version":1},"attestation_state":"computed","paper":{"title":"Robust Multi-Tier Infant-Centered Audio Understanding with Whisper via Structured Speaker Conditioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"eess.AS","authors_text":"Bashima Islam, Jialu Li, Kexin Hu, Mark Hasegawa-Johnson, Mohammad Nur Hossain Khan, Nancy L. McElwain, Xulin Fan","submitted_at":"2026-08-12T02:55:21Z","abstract_excerpt":"Recent advances in model design and self-supervised audio representations have improved speech and audio understanding, yet infant-centered naturalistic recordings remain challenging due to limited labeled data, low signal-to-noise ratio, and cross-family domain shifts. We present a family-conditioned, multi-tier audio tagger that combines a LoRA-finetuned Whisper encoder with a lightweight, target-speaker-aware Transformer for long-context inference and framewise prediction across tiers. To improve temporal coherence, we incorporate a simple sequence-level smoothing loss, and to enhance robus"},"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":"2608.11587","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-08-12T02:55:21Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"473cc880e4e88a20303696248d5e5216adad03f412f89ebf6bbb9c995f10854e","abstract_canon_sha256":"7f839b214e460f7a1626bf6f2646fbd0988904217fddb858f660802cefdf0d0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-13T00:22:14.866315Z","signature_b64":"S8nZXk4/RkJ3eXgfs1jC93qg7/xlGUlkg5T4qSx7aUPoWyeSTbcosa5Ykm49Vu7FHTJI1Rhu32q866ssyvTxCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd7289b97b1347bcff2659c2216c1c1c0e32e6af54c6e538bf443fabda8decd2","last_reissued_at":"2026-08-13T00:22:14.864590Z","signature_status":"signed_v1","first_computed_at":"2026-08-13T00:22:14.864590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Multi-Tier Infant-Centered Audio Understanding with Whisper via Structured Speaker Conditioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"eess.AS","authors_text":"Bashima Islam, Jialu Li, Kexin Hu, Mark Hasegawa-Johnson, Mohammad Nur Hossain Khan, Nancy L. McElwain, Xulin Fan","submitted_at":"2026-08-12T02:55:21Z","abstract_excerpt":"Recent advances in model design and self-supervised audio representations have improved speech and audio understanding, yet infant-centered naturalistic recordings remain challenging due to limited labeled data, low signal-to-noise ratio, and cross-family domain shifts. We present a family-conditioned, multi-tier audio tagger that combines a LoRA-finetuned Whisper encoder with a lightweight, target-speaker-aware Transformer for long-context inference and framewise prediction across tiers. To improve temporal coherence, we incorporate a simple sequence-level smoothing loss, and to enhance robus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11587","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/2608.11587/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":"2608.11587","created_at":"2026-08-13T00:22:14.865042+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.11587v1","created_at":"2026-08-13T00:22:14.865042+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11587","created_at":"2026-08-13T00:22:14.865042+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZVZITOL3CND3","created_at":"2026-08-13T00:22:14.865042+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZVZITOL3CND3Z7ZG","created_at":"2026-08-13T00:22:14.865042+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZVZITOL3","created_at":"2026-08-13T00:22:14.865042+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.11587","citing_title":"Robust Multi-Tier Infant-Centered Audio Understanding with Whisper via Structured Speaker Conditioning","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZVZITOL3CND3Z7ZGLHBCC3A4DQ","json":"https://pith.science/pith/ZVZITOL3CND3Z7ZGLHBCC3A4DQ.json","graph_json":"https://pith.science/api/pith-number/ZVZITOL3CND3Z7ZGLHBCC3A4DQ/graph.json","events_json":"https://pith.science/api/pith-number/ZVZITOL3CND3Z7ZGLHBCC3A4DQ/events.json","paper":"https://pith.science/paper/ZVZITOL3"},"agent_actions":{"view_html":"https://pith.science/pith/ZVZITOL3CND3Z7ZGLHBCC3A4DQ","download_json":"https://pith.science/pith/ZVZITOL3CND3Z7ZGLHBCC3A4DQ.json","view_paper":"https://pith.science/paper/ZVZITOL3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.11587&json=true","fetch_graph":"https://pith.science/api/pith-number/ZVZITOL3CND3Z7ZGLHBCC3A4DQ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZVZITOL3CND3Z7ZGLHBCC3A4DQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZVZITOL3CND3Z7ZGLHBCC3A4DQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZVZITOL3CND3Z7ZGLHBCC3A4DQ/action/storage_attestation","attest_author":"https://pith.science/pith/ZVZITOL3CND3Z7ZGLHBCC3A4DQ/action/author_attestation","sign_citation":"https://pith.science/pith/ZVZITOL3CND3Z7ZGLHBCC3A4DQ/action/citation_signature","submit_replication":"https://pith.science/pith/ZVZITOL3CND3Z7ZGLHBCC3A4DQ/action/replication_record"}},"created_at":"2026-08-13T00:22:14.865042+00:00","updated_at":"2026-08-13T00:22:14.865042+00:00"}