{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZX3BEW2YBJJSGA6PBLBXR4DBLF","short_pith_number":"pith:ZX3BEW2Y","schema_version":"1.0","canonical_sha256":"cdf6125b580a532303cf0ac378f061596dd846cb2d7f66499fd0b6585b7a4279","source":{"kind":"arxiv","id":"2606.01909","version":1},"attestation_state":"computed","paper":{"title":"Echo: A Joint-Embedding Predictive Architecture for Speaker Diarization and Speech Recognition in a Shared Latent Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Louis Mouchon","submitted_at":"2026-06-01T08:46:11Z","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"},"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":"2606.01909","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-01T08:46:11Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"1dc009945ad7770ddbf77a3f2ca94b1e334ecb4261686e91960f01a766c776c9","abstract_canon_sha256":"8f930e2a949f05413cfd27438412ebc844de5b15b03cc01ea73cf59fb7683a11"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:05:00.151024Z","signature_b64":"/FJ6VPzcOk9iBS78vNiFBh/YKYvPnV9GMsJFXUmmr8G3B2JKEo3zxycTvX5VrGpJiTwbx0iK9Di71kNZYz3mDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdf6125b580a532303cf0ac378f061596dd846cb2d7f66499fd0b6585b7a4279","last_reissued_at":"2026-06-02T02:05:00.150629Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:05:00.150629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Echo: A Joint-Embedding Predictive Architecture for Speaker Diarization and Speech Recognition in a Shared Latent Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Louis Mouchon","submitted_at":"2026-06-01T08:46:11Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01909","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/2606.01909/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":"2606.01909","created_at":"2026-06-02T02:05:00.150696+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01909v1","created_at":"2026-06-02T02:05:00.150696+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01909","created_at":"2026-06-02T02:05:00.150696+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZX3BEW2YBJJS","created_at":"2026-06-02T02:05:00.150696+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZX3BEW2YBJJSGA6P","created_at":"2026-06-02T02:05:00.150696+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZX3BEW2Y","created_at":"2026-06-02T02:05:00.150696+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZX3BEW2YBJJSGA6PBLBXR4DBLF","json":"https://pith.science/pith/ZX3BEW2YBJJSGA6PBLBXR4DBLF.json","graph_json":"https://pith.science/api/pith-number/ZX3BEW2YBJJSGA6PBLBXR4DBLF/graph.json","events_json":"https://pith.science/api/pith-number/ZX3BEW2YBJJSGA6PBLBXR4DBLF/events.json","paper":"https://pith.science/paper/ZX3BEW2Y"},"agent_actions":{"view_html":"https://pith.science/pith/ZX3BEW2YBJJSGA6PBLBXR4DBLF","download_json":"https://pith.science/pith/ZX3BEW2YBJJSGA6PBLBXR4DBLF.json","view_paper":"https://pith.science/paper/ZX3BEW2Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01909&json=true","fetch_graph":"https://pith.science/api/pith-number/ZX3BEW2YBJJSGA6PBLBXR4DBLF/graph.json","fetch_events":"https://pith.science/api/pith-number/ZX3BEW2YBJJSGA6PBLBXR4DBLF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZX3BEW2YBJJSGA6PBLBXR4DBLF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZX3BEW2YBJJSGA6PBLBXR4DBLF/action/storage_attestation","attest_author":"https://pith.science/pith/ZX3BEW2YBJJSGA6PBLBXR4DBLF/action/author_attestation","sign_citation":"https://pith.science/pith/ZX3BEW2YBJJSGA6PBLBXR4DBLF/action/citation_signature","submit_replication":"https://pith.science/pith/ZX3BEW2YBJJSGA6PBLBXR4DBLF/action/replication_record"}},"created_at":"2026-06-02T02:05:00.150696+00:00","updated_at":"2026-06-02T02:05:00.150696+00:00"}