{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VUTG6WJ5JS4MK2AHM4GBS4QWC5","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":"bb25066e81dfa97a23a2925bdbe8858bd548ac5126cb6def05d933f6547a4c0a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-14T12:00:13Z","title_canon_sha256":"e275329ac4e6cefd85f7a36dbccd8249a133636e295ea1749c48698f622a84ec"},"schema_version":"1.0","source":{"id":"2605.14736","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14736","created_at":"2026-05-17T23:38:58Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14736v1","created_at":"2026-05-17T23:38:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14736","created_at":"2026-05-17T23:38:58Z"},{"alias_kind":"pith_short_12","alias_value":"VUTG6WJ5JS4M","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"VUTG6WJ5JS4MK2AH","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"VUTG6WJ5","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:7a8a50bf3b059701e1155f94eb4eff9d52bfe4238c93bb24abe38a1177e3b97d","target":"graph","created_at":"2026-05-17T23:38:58Z","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"},"paper":{"abstract_excerpt":"Target speech extraction remains difficult for compact devices because monaural neural models lack spatial evidence and classical beamformers lose resolving power when the microphone aperture is only a few centimetres. We present IsoNet, a user-selectable audio-visual target speech extraction system for a compact 4-microphone array. IsoNet combines complex multi-channel STFT features, GCC-PHAT spatial cues, face-conditioned visual embeddings, and auxiliary direction-of-arrival supervision inside a U-Net mask estimation network. Three curriculum variants were trained on 25,000 simulated VoxCele","authors_text":"Binita Adhikari, Dinanath Pathya, Ishwor Raj Pokharel, Sajen Maharjan","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-14T12:00:13Z","title":"IsoNet: Spatially-aware audio-visual target speech extraction in complex acoustic environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.14736","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:da4f3e617b13a3a1eacbd5dfc2d1df5c9c78e2927bba9e2774c1157b9e090da6","target":"record","created_at":"2026-05-17T23:38:58Z","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":"bb25066e81dfa97a23a2925bdbe8858bd548ac5126cb6def05d933f6547a4c0a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-14T12:00:13Z","title_canon_sha256":"e275329ac4e6cefd85f7a36dbccd8249a133636e295ea1749c48698f622a84ec"},"schema_version":"1.0","source":{"id":"2605.14736","kind":"arxiv","version":1}},"canonical_sha256":"ad266f593d4cb8c56807670c1972161778bd81384e37ab5bfd73d263f0fd061b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad266f593d4cb8c56807670c1972161778bd81384e37ab5bfd73d263f0fd061b","first_computed_at":"2026-05-17T23:38:58.979465Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:58.979465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KUo//GwUDtKny/ZuhDsHWMeEt12CLC8rWYHHNSjfARrU3VYMhy4E3dZxWcn7Mia/JVcrOoh5tBvBKAOipl7SDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:58.980056Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14736","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da4f3e617b13a3a1eacbd5dfc2d1df5c9c78e2927bba9e2774c1157b9e090da6","sha256:7a8a50bf3b059701e1155f94eb4eff9d52bfe4238c93bb24abe38a1177e3b97d"],"state_sha256":"85ccbd73f3d38c64b220fef9625ef838bb396366988b1d2b45878ad22e008a93"}