{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZVZITOL3CND3Z7ZGLHBCC3A4DQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7f839b214e460f7a1626bf6f2646fbd0988904217fddb858f660802cefdf0d0c","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-08-12T02:55:21Z","title_canon_sha256":"473cc880e4e88a20303696248d5e5216adad03f412f89ebf6bbb9c995f10854e"},"schema_version":"1.0","source":{"id":"2608.11587","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.11587","created_at":"2026-08-13T00:22:14Z"},{"alias_kind":"arxiv_version","alias_value":"2608.11587v1","created_at":"2026-08-13T00:22:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11587","created_at":"2026-08-13T00:22:14Z"},{"alias_kind":"pith_short_12","alias_value":"ZVZITOL3CND3","created_at":"2026-08-13T00:22:14Z"},{"alias_kind":"pith_short_16","alias_value":"ZVZITOL3CND3Z7ZG","created_at":"2026-08-13T00:22:14Z"},{"alias_kind":"pith_short_8","alias_value":"ZVZITOL3","created_at":"2026-08-13T00:22:14Z"}],"graph_snapshots":[{"event_id":"sha256:1c6ef571c37968a8a371c52dcbb68886f3984e15206a69a3692e41e5a9f1befe","target":"graph","created_at":"2026-08-13T00:22:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2608.11587/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bashima Islam, Jialu Li, Kexin Hu, Mark Hasegawa-Johnson, Mohammad Nur Hossain Khan, Nancy L. McElwain, Xulin Fan","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-08-12T02:55:21Z","title":"Robust Multi-Tier Infant-Centered Audio Understanding with Whisper via Structured Speaker Conditioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11587","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:538b44b74177cb8cf7732dabe8190effcf84cea6e6210d71b9bd07936ed0dda2","target":"record","created_at":"2026-08-13T00:22:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7f839b214e460f7a1626bf6f2646fbd0988904217fddb858f660802cefdf0d0c","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-08-12T02:55:21Z","title_canon_sha256":"473cc880e4e88a20303696248d5e5216adad03f412f89ebf6bbb9c995f10854e"},"schema_version":"1.0","source":{"id":"2608.11587","kind":"arxiv","version":1}},"canonical_sha256":"cd7289b97b1347bcff2659c2216c1c1c0e32e6af54c6e538bf443fabda8decd2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd7289b97b1347bcff2659c2216c1c1c0e32e6af54c6e538bf443fabda8decd2","first_computed_at":"2026-08-13T00:22:14.864590Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-13T00:22:14.864590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S8nZXk4/RkJ3eXgfs1jC93qg7/xlGUlkg5T4qSx7aUPoWyeSTbcosa5Ykm49Vu7FHTJI1Rhu32q866ssyvTxCg==","signature_status":"signed_v1","signed_at":"2026-08-13T00:22:14.866315Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.11587","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:538b44b74177cb8cf7732dabe8190effcf84cea6e6210d71b9bd07936ed0dda2","sha256:1c6ef571c37968a8a371c52dcbb68886f3984e15206a69a3692e41e5a9f1befe"],"state_sha256":"980922f907cab429a18564e9d7e3389930c60a1100b2ce40c7b71bb6ab42422b"}