{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:7SMNMVJCZIILXIOGGZW3752UKW","short_pith_number":"pith:7SMNMVJC","canonical_record":{"source":{"id":"2604.03219","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2026-04-03T17:46:17Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"1d3460bf8a729aa28105543e7f3dc9b44465459ff32c8630a63adf8a3c5de4e1","abstract_canon_sha256":"798069f89262b5ca4208d8fd28fa522cc6a59da69c749feda774f07e9d57db94"},"schema_version":"1.0"},"canonical_sha256":"fc98d65522ca10bba1c6366dbff754558142ab46f40bb98d03930cc1e27c06ac","source":{"kind":"arxiv","id":"2604.03219","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.03219","created_at":"2026-06-23T02:13:23Z"},{"alias_kind":"arxiv_version","alias_value":"2604.03219v2","created_at":"2026-06-23T02:13:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.03219","created_at":"2026-06-23T02:13:23Z"},{"alias_kind":"pith_short_12","alias_value":"7SMNMVJCZIIL","created_at":"2026-06-23T02:13:23Z"},{"alias_kind":"pith_short_16","alias_value":"7SMNMVJCZIILXIOG","created_at":"2026-06-23T02:13:23Z"},{"alias_kind":"pith_short_8","alias_value":"7SMNMVJC","created_at":"2026-06-23T02:13:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:7SMNMVJCZIILXIOGGZW3752UKW","target":"record","payload":{"canonical_record":{"source":{"id":"2604.03219","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2026-04-03T17:46:17Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"1d3460bf8a729aa28105543e7f3dc9b44465459ff32c8630a63adf8a3c5de4e1","abstract_canon_sha256":"798069f89262b5ca4208d8fd28fa522cc6a59da69c749feda774f07e9d57db94"},"schema_version":"1.0"},"canonical_sha256":"fc98d65522ca10bba1c6366dbff754558142ab46f40bb98d03930cc1e27c06ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:23.339368Z","signature_b64":"NrhKRiNBYjem3sPQAg37WPcjEqUvh3rXYN/WO5r8W2SFL6ZBWkXyZvMS3ojY+B0uve5Dy952Xa56n2YBsRf6Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc98d65522ca10bba1c6366dbff754558142ab46f40bb98d03930cc1e27c06ac","last_reissued_at":"2026-06-23T02:13:23.339025Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:23.339025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.03219","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T02:13:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xw4R2YUMSEYHzUD3y5N0PdE2RjQyAZd6XM1+9CLq39Jn4MXXjmVExbZl8f+L19n/KA7v/E+rlSYE2WFHdyCBDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T15:29:37.312216Z"},"content_sha256":"f0428b30f19ad6f0301faadb45b7abd33ac3c09fc8272e50c7e19cbd8f27c66d","schema_version":"1.0","event_id":"sha256:f0428b30f19ad6f0301faadb45b7abd33ac3c09fc8272e50c7e19cbd8f27c66d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:7SMNMVJCZIILXIOGGZW3752UKW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unmixing The Crowd: Learning Persistent Speaker Representations from Mixture-Derived Multi-Speaker Embeddings","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"A model learns to predict speaker embeddings directly from noisy mixtures, enabling target speech extraction without any enrollment recording.","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Dhruv Jain, Hao-Wen Dong, Meysam Asgari, Sidharth Sidharth","submitted_at":"2026-04-03T17:46:17Z","abstract_excerpt":"We study whether persistent conversational speaker structure can be extracted directly from local overlapping speech mixtures. We propose a teacher-student framework that learns mixture-derived multi-speaker embeddings using only short overlapping segments and permutation-invariant latent supervision. Despite never being explicitly trained for speaker tracking, diarization, or conversational memory, the learned embedding space supports long-form speaker re-identification when combined with a lightweight online memory mechanism during inference. We additionally observe that the learned represen"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our model maps a noisy mixture directly to a small set of candidate speaker embeddings trained to align with a strong single-speaker speaker-embedding space via permutation-invariant teacher supervision.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That embeddings predicted from the mixture alone will align sufficiently with the single-speaker embedding space to serve as effective control signals for downstream extraction without any enrollment data.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A neural model predicts a set of speaker embeddings from noisy mixtures to enable enrollment-free target speech extraction, outperforming baselines on LibriMix and generalizing to real recordings.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A model learns to predict speaker embeddings directly from noisy mixtures, enabling target speech extraction without any enrollment recording.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9d931b6c47b39b46cc54836b5e23e8ea88d5f77de79c43d5d3e2d4ea1b0c03a6"},"source":{"id":"2604.03219","kind":"arxiv","version":2},"verdict":{"id":"dca9a624-37ed-4531-9bc3-e2253a3f4d48","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T17:55:23.394562Z","strongest_claim":"Our model maps a noisy mixture directly to a small set of candidate speaker embeddings trained to align with a strong single-speaker speaker-embedding space via permutation-invariant teacher supervision.","one_line_summary":"A neural model predicts a set of speaker embeddings from noisy mixtures to enable enrollment-free target speech extraction, outperforming baselines on LibriMix and generalizing to real recordings.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That embeddings predicted from the mixture alone will align sufficiently with the single-speaker embedding space to serve as effective control signals for downstream extraction without any enrollment data.","pith_extraction_headline":"A model learns to predict speaker embeddings directly from noisy mixtures, enabling target speech extraction without any enrollment recording."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.03219/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":2,"snapshot_sha256":"765ffad865f890138bd07d1f47f356460c202d5f18f5bcaddf5114ae196d83cb"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"dca9a624-37ed-4531-9bc3-e2253a3f4d48"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T02:13:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iLI8e0oLuyZsgNRTvJziRo4JwS9e36m0zRo1SPLm13px7kPR5kh83DBcMPgUlifEE26/dxw/O61zDKE1DtJpBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T15:29:37.312695Z"},"content_sha256":"2b7780756811da252230d52b6b4c2241687e15380c621133aa2118c2870d4d87","schema_version":"1.0","event_id":"sha256:2b7780756811da252230d52b6b4c2241687e15380c621133aa2118c2870d4d87"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7SMNMVJCZIILXIOGGZW3752UKW/bundle.json","state_url":"https://pith.science/pith/7SMNMVJCZIILXIOGGZW3752UKW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7SMNMVJCZIILXIOGGZW3752UKW/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":"2026-07-02T15:29:37Z","links":{"resolver":"https://pith.science/pith/7SMNMVJCZIILXIOGGZW3752UKW","bundle":"https://pith.science/pith/7SMNMVJCZIILXIOGGZW3752UKW/bundle.json","state":"https://pith.science/pith/7SMNMVJCZIILXIOGGZW3752UKW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7SMNMVJCZIILXIOGGZW3752UKW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7SMNMVJCZIILXIOGGZW3752UKW","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":"798069f89262b5ca4208d8fd28fa522cc6a59da69c749feda774f07e9d57db94","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2026-04-03T17:46:17Z","title_canon_sha256":"1d3460bf8a729aa28105543e7f3dc9b44465459ff32c8630a63adf8a3c5de4e1"},"schema_version":"1.0","source":{"id":"2604.03219","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.03219","created_at":"2026-06-23T02:13:23Z"},{"alias_kind":"arxiv_version","alias_value":"2604.03219v2","created_at":"2026-06-23T02:13:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.03219","created_at":"2026-06-23T02:13:23Z"},{"alias_kind":"pith_short_12","alias_value":"7SMNMVJCZIIL","created_at":"2026-06-23T02:13:23Z"},{"alias_kind":"pith_short_16","alias_value":"7SMNMVJCZIILXIOG","created_at":"2026-06-23T02:13:23Z"},{"alias_kind":"pith_short_8","alias_value":"7SMNMVJC","created_at":"2026-06-23T02:13:23Z"}],"graph_snapshots":[{"event_id":"sha256:2b7780756811da252230d52b6b4c2241687e15380c621133aa2118c2870d4d87","target":"graph","created_at":"2026-06-23T02:13:23Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Our model maps a noisy mixture directly to a small set of candidate speaker embeddings trained to align with a strong single-speaker speaker-embedding space via permutation-invariant teacher supervision."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That embeddings predicted from the mixture alone will align sufficiently with the single-speaker embedding space to serve as effective control signals for downstream extraction without any enrollment data."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A neural model predicts a set of speaker embeddings from noisy mixtures to enable enrollment-free target speech extraction, outperforming baselines on LibriMix and generalizing to real recordings."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A model learns to predict speaker embeddings directly from noisy mixtures, enabling target speech extraction without any enrollment recording."}],"snapshot_sha256":"9d931b6c47b39b46cc54836b5e23e8ea88d5f77de79c43d5d3e2d4ea1b0c03a6"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"765ffad865f890138bd07d1f47f356460c202d5f18f5bcaddf5114ae196d83cb"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.03219/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study whether persistent conversational speaker structure can be extracted directly from local overlapping speech mixtures. We propose a teacher-student framework that learns mixture-derived multi-speaker embeddings using only short overlapping segments and permutation-invariant latent supervision. Despite never being explicitly trained for speaker tracking, diarization, or conversational memory, the learned embedding space supports long-form speaker re-identification when combined with a lightweight online memory mechanism during inference. We additionally observe that the learned represen","authors_text":"Dhruv Jain, Hao-Wen Dong, Meysam Asgari, Sidharth Sidharth","cross_cats":["cs.SD"],"headline":"A model learns to predict speaker embeddings directly from noisy mixtures, enabling target speech extraction without any enrollment recording.","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2026-04-03T17:46:17Z","title":"Unmixing The Crowd: Learning Persistent Speaker Representations from Mixture-Derived Multi-Speaker Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.03219","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-13T17:55:23.394562Z","id":"dca9a624-37ed-4531-9bc3-e2253a3f4d48","model_set":{"reader":"grok-4.3"},"one_line_summary":"A neural model predicts a set of speaker embeddings from noisy mixtures to enable enrollment-free target speech extraction, outperforming baselines on LibriMix and generalizing to real recordings.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A model learns to predict speaker embeddings directly from noisy mixtures, enabling target speech extraction without any enrollment recording.","strongest_claim":"Our model maps a noisy mixture directly to a small set of candidate speaker embeddings trained to align with a strong single-speaker speaker-embedding space via permutation-invariant teacher supervision.","weakest_assumption":"That embeddings predicted from the mixture alone will align sufficiently with the single-speaker embedding space to serve as effective control signals for downstream extraction without any enrollment data."}},"verdict_id":"dca9a624-37ed-4531-9bc3-e2253a3f4d48"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f0428b30f19ad6f0301faadb45b7abd33ac3c09fc8272e50c7e19cbd8f27c66d","target":"record","created_at":"2026-06-23T02:13:23Z","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":"798069f89262b5ca4208d8fd28fa522cc6a59da69c749feda774f07e9d57db94","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2026-04-03T17:46:17Z","title_canon_sha256":"1d3460bf8a729aa28105543e7f3dc9b44465459ff32c8630a63adf8a3c5de4e1"},"schema_version":"1.0","source":{"id":"2604.03219","kind":"arxiv","version":2}},"canonical_sha256":"fc98d65522ca10bba1c6366dbff754558142ab46f40bb98d03930cc1e27c06ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc98d65522ca10bba1c6366dbff754558142ab46f40bb98d03930cc1e27c06ac","first_computed_at":"2026-06-23T02:13:23.339025Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:23.339025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NrhKRiNBYjem3sPQAg37WPcjEqUvh3rXYN/WO5r8W2SFL6ZBWkXyZvMS3ojY+B0uve5Dy952Xa56n2YBsRf6Dw==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:23.339368Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.03219","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0428b30f19ad6f0301faadb45b7abd33ac3c09fc8272e50c7e19cbd8f27c66d","sha256:2b7780756811da252230d52b6b4c2241687e15380c621133aa2118c2870d4d87"],"state_sha256":"6f14026f9fb2cf2db794edb0d934a16b3c055309ca8b95e6c121a643811200e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+4N26cXMCjSxPIv81gTbiPNhL4Y5o7G4Gb8ALnQKbDU4o+CVKWwibpczgfnpnrqoglZCCLstaAeSm1T0U7LJAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T15:29:37.314941Z","bundle_sha256":"2a5e431c73e5246623a15d41639f6555fc5ae289326d5e81bef5719040bbdad8"}}