{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VUTG6WJ5JS4MK2AHM4GBS4QWC5","short_pith_number":"pith:VUTG6WJ5","canonical_record":{"source":{"id":"2605.14736","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-14T12:00:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e275329ac4e6cefd85f7a36dbccd8249a133636e295ea1749c48698f622a84ec","abstract_canon_sha256":"bb25066e81dfa97a23a2925bdbe8858bd548ac5126cb6def05d933f6547a4c0a"},"schema_version":"1.0"},"canonical_sha256":"ad266f593d4cb8c56807670c1972161778bd81384e37ab5bfd73d263f0fd061b","source":{"kind":"arxiv","id":"2605.14736","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VUTG6WJ5JS4MK2AHM4GBS4QWC5","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14736","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-14T12:00:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e275329ac4e6cefd85f7a36dbccd8249a133636e295ea1749c48698f622a84ec","abstract_canon_sha256":"bb25066e81dfa97a23a2925bdbe8858bd548ac5126cb6def05d933f6547a4c0a"},"schema_version":"1.0"},"canonical_sha256":"ad266f593d4cb8c56807670c1972161778bd81384e37ab5bfd73d263f0fd061b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:58.980056Z","signature_b64":"KUo//GwUDtKny/ZuhDsHWMeEt12CLC8rWYHHNSjfARrU3VYMhy4E3dZxWcn7Mia/JVcrOoh5tBvBKAOipl7SDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad266f593d4cb8c56807670c1972161778bd81384e37ab5bfd73d263f0fd061b","last_reissued_at":"2026-05-17T23:38:58.979465Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:58.979465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14736","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wR1fB9NiZzylqDrcDGrKHrdIWhc8Sy13IikCYG0sYVX6pgEN/CfkM5nXQC8EeN+cSr48ct1WZI5O0SypK3U4AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T16:12:23.768676Z"},"content_sha256":"da4f3e617b13a3a1eacbd5dfc2d1df5c9c78e2927bba9e2774c1157b9e090da6","schema_version":"1.0","event_id":"sha256:da4f3e617b13a3a1eacbd5dfc2d1df5c9c78e2927bba9e2774c1157b9e090da6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VUTG6WJ5JS4MK2AHM4GBS4QWC5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"IsoNet: Spatially-aware audio-visual target speech extraction in complex acoustic environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SD","authors_text":"Binita Adhikari, Dinanath Pathya, Ishwor Raj Pokharel, Sajen Maharjan","submitted_at":"2026-05-14T12:00:13Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.14736","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HjSao+e2cRNNXuUZp18ylgl6aQgTP5/uUQu7K9l73lFKR73odDmF3aQjHJHlpj5ZRJYVOEvPIuqpcbz9Ht/EBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T16:12:23.769020Z"},"content_sha256":"7a8a50bf3b059701e1155f94eb4eff9d52bfe4238c93bb24abe38a1177e3b97d","schema_version":"1.0","event_id":"sha256:7a8a50bf3b059701e1155f94eb4eff9d52bfe4238c93bb24abe38a1177e3b97d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VUTG6WJ5JS4MK2AHM4GBS4QWC5/bundle.json","state_url":"https://pith.science/pith/VUTG6WJ5JS4MK2AHM4GBS4QWC5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VUTG6WJ5JS4MK2AHM4GBS4QWC5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-26T16:12:23Z","links":{"resolver":"https://pith.science/pith/VUTG6WJ5JS4MK2AHM4GBS4QWC5","bundle":"https://pith.science/pith/VUTG6WJ5JS4MK2AHM4GBS4QWC5/bundle.json","state":"https://pith.science/pith/VUTG6WJ5JS4MK2AHM4GBS4QWC5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VUTG6WJ5JS4MK2AHM4GBS4QWC5/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ef8XL0wSwSCvRThb2wtlR66g0LeyJ4gWFJ3HV2iylYvr/DmK/0PHEhmIw7mmO8CHe769Dmr4niM8gs7KtEddDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T16:12:23.771079Z","bundle_sha256":"5c3081fe8976a683e8d415be949b2a224ff9d916f2168259063ac97f399d3497"}}