{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZX3BEW2YBJJSGA6PBLBXR4DBLF","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":"8f930e2a949f05413cfd27438412ebc844de5b15b03cc01ea73cf59fb7683a11","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-01T08:46:11Z","title_canon_sha256":"1dc009945ad7770ddbf77a3f2ca94b1e334ecb4261686e91960f01a766c776c9"},"schema_version":"1.0","source":{"id":"2606.01909","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01909","created_at":"2026-06-02T02:05:00Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01909v1","created_at":"2026-06-02T02:05:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01909","created_at":"2026-06-02T02:05:00Z"},{"alias_kind":"pith_short_12","alias_value":"ZX3BEW2YBJJS","created_at":"2026-06-02T02:05:00Z"},{"alias_kind":"pith_short_16","alias_value":"ZX3BEW2YBJJSGA6P","created_at":"2026-06-02T02:05:00Z"},{"alias_kind":"pith_short_8","alias_value":"ZX3BEW2Y","created_at":"2026-06-02T02:05:00Z"}],"graph_snapshots":[{"event_id":"sha256:f5e8a961e5170e75a25151eea48803956487d1245fd12d6737dc85a2ae0ed8e8","target":"graph","created_at":"2026-06-02T02:05:00Z","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/2606.01909/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Echo, a proof-of-concept audio system built around a single 25 M-parameter ViT encoder. The encoder is pretrained with a JEPA objective and then specialised by stages to carry speaker identity, phonetic content, and dynamic source routing in the same 512-dimensional latent space, with no per-task fine-tuning at deployment. Light heads handle diarization (ArcFace + VBx) and dynamic source separation (null-target K-set prediction). On synthetic VoxCeleb2 mixtures with unknown K, the canonical stack reaches 15.00% blind DER, 97.80% PIT separation accuracy with +9.52 dB latent SI-SDR, a","authors_text":"Louis Mouchon","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-01T08:46:11Z","title":"Echo: A Joint-Embedding Predictive Architecture for Speaker Diarization and Speech Recognition in a Shared Latent Space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01909","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":"sha256:450f68db6b1533333c0ad38bcf90e9883d0792ad13b4b2da3e419f17f06fe1f0","target":"record","created_at":"2026-06-02T02:05:00Z","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":"8f930e2a949f05413cfd27438412ebc844de5b15b03cc01ea73cf59fb7683a11","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-01T08:46:11Z","title_canon_sha256":"1dc009945ad7770ddbf77a3f2ca94b1e334ecb4261686e91960f01a766c776c9"},"schema_version":"1.0","source":{"id":"2606.01909","kind":"arxiv","version":1}},"canonical_sha256":"cdf6125b580a532303cf0ac378f061596dd846cb2d7f66499fd0b6585b7a4279","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cdf6125b580a532303cf0ac378f061596dd846cb2d7f66499fd0b6585b7a4279","first_computed_at":"2026-06-02T02:05:00.150629Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:05:00.150629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/FJ6VPzcOk9iBS78vNiFBh/YKYvPnV9GMsJFXUmmr8G3B2JKEo3zxycTvX5VrGpJiTwbx0iK9Di71kNZYz3mDA==","signature_status":"signed_v1","signed_at":"2026-06-02T02:05:00.151024Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.01909","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:450f68db6b1533333c0ad38bcf90e9883d0792ad13b4b2da3e419f17f06fe1f0","sha256:f5e8a961e5170e75a25151eea48803956487d1245fd12d6737dc85a2ae0ed8e8"],"state_sha256":"cacaef80514b59098ae58bfe23b8ea054caca40b6a09a196ebfe476db48d55c3"}