{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:N34ADC4CL4XHOF5IAOUACNDM6M","short_pith_number":"pith:N34ADC4C","canonical_record":{"source":{"id":"2508.20474","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-08-28T06:50:57Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"31805a1ba74a3e998915fad102feb2f52fd6202998179abf70d37de9c50052b8","abstract_canon_sha256":"cccedf6ae1a57631cff0014d73a848b298721833c79e6e3df1b1b20d308b4f75"},"schema_version":"1.0"},"canonical_sha256":"6ef8018b825f2e7717a803a801346cf30edd3489f4a62ff046d285c59647b76b","source":{"kind":"arxiv","id":"2508.20474","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.20474","created_at":"2026-05-18T02:45:13Z"},{"alias_kind":"arxiv_version","alias_value":"2508.20474v2","created_at":"2026-05-18T02:45:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20474","created_at":"2026-05-18T02:45:13Z"},{"alias_kind":"pith_short_12","alias_value":"N34ADC4CL4XH","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"N34ADC4CL4XHOF5I","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"N34ADC4C","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:N34ADC4CL4XHOF5IAOUACNDM6M","target":"record","payload":{"canonical_record":{"source":{"id":"2508.20474","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-08-28T06:50:57Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"31805a1ba74a3e998915fad102feb2f52fd6202998179abf70d37de9c50052b8","abstract_canon_sha256":"cccedf6ae1a57631cff0014d73a848b298721833c79e6e3df1b1b20d308b4f75"},"schema_version":"1.0"},"canonical_sha256":"6ef8018b825f2e7717a803a801346cf30edd3489f4a62ff046d285c59647b76b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:45:13.101137Z","signature_b64":"UQ5hdXdHlwSIe1Uj54IhM5XcJLik63OplKuUZKJXGPmo3HjPlKhGNe9TxnYu2t+1batbu1fh16y4udi9WpRjDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ef8018b825f2e7717a803a801346cf30edd3489f4a62ff046d285c59647b76b","last_reissued_at":"2026-05-18T02:45:13.100540Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:45:13.100540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.20474","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":"2026-05-18T02:45:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1rCP1PVJC+lGlxBTGhsUlZB8wzfAJbVPeMaHBs12Z5/xghwHEEd/QhPPumrhAvrOPVPIIYEGzoUerk52K3X4Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T05:00:31.898881Z"},"content_sha256":"48f92c5d4b6817c98637ecb1dc1ebfe54b26e1ce84e93eaa6d29a6146c2b7246","schema_version":"1.0","event_id":"sha256:48f92c5d4b6817c98637ecb1dc1ebfe54b26e1ce84e93eaa6d29a6146c2b7246"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:N34ADC4CL4XHOF5IAOUACNDM6M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unifying Diarization, Separation, and ASR with Multi-Speaker Encoder","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chyi-Jiunn Lin, Muhammad Shakeel, Shinji Watanabe, Yifan Peng, Yui Sudo","submitted_at":"2025-08-28T06:50:57Z","abstract_excerpt":"This paper presents a unified multi-speaker encoder (UME), a novel architecture that jointly learns representations for speaker diarization (SD), speech separation (SS), and multi-speaker automatic speech recognition (ASR) tasks using a shared speech foundational encoder. We leverage the hidden representations from multiple layers of UME as a residual weighted-sum encoding (RWSE) to effectively use information from different semantic levels, contributing to bottom-up alignment between tasks. This joint training approach captures the inherent interdependencies among the tasks, enhancing overall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20474","kind":"arxiv","version":2},"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":"2026-05-18T02:45:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9WGuiYyk3ZNgsku1GUXhhQv7/xwxRPZ5FIqF53q4kCo+wHdFfQDb2EK8fjecrtyT1BhCJNsAfKG/koWw0VyPCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T05:00:31.899233Z"},"content_sha256":"c1161b0a22525f9a73f9a9ac711d6294e9ebae6f6ff2c31e9c961f1b626a48b4","schema_version":"1.0","event_id":"sha256:c1161b0a22525f9a73f9a9ac711d6294e9ebae6f6ff2c31e9c961f1b626a48b4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N34ADC4CL4XHOF5IAOUACNDM6M/bundle.json","state_url":"https://pith.science/pith/N34ADC4CL4XHOF5IAOUACNDM6M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N34ADC4CL4XHOF5IAOUACNDM6M/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":"2026-05-21T05:00:31Z","links":{"resolver":"https://pith.science/pith/N34ADC4CL4XHOF5IAOUACNDM6M","bundle":"https://pith.science/pith/N34ADC4CL4XHOF5IAOUACNDM6M/bundle.json","state":"https://pith.science/pith/N34ADC4CL4XHOF5IAOUACNDM6M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N34ADC4CL4XHOF5IAOUACNDM6M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:N34ADC4CL4XHOF5IAOUACNDM6M","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":"cccedf6ae1a57631cff0014d73a848b298721833c79e6e3df1b1b20d308b4f75","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-08-28T06:50:57Z","title_canon_sha256":"31805a1ba74a3e998915fad102feb2f52fd6202998179abf70d37de9c50052b8"},"schema_version":"1.0","source":{"id":"2508.20474","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.20474","created_at":"2026-05-18T02:45:13Z"},{"alias_kind":"arxiv_version","alias_value":"2508.20474v2","created_at":"2026-05-18T02:45:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20474","created_at":"2026-05-18T02:45:13Z"},{"alias_kind":"pith_short_12","alias_value":"N34ADC4CL4XH","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"N34ADC4CL4XHOF5I","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"N34ADC4C","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:c1161b0a22525f9a73f9a9ac711d6294e9ebae6f6ff2c31e9c961f1b626a48b4","target":"graph","created_at":"2026-05-18T02:45:13Z","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":"This paper presents a unified multi-speaker encoder (UME), a novel architecture that jointly learns representations for speaker diarization (SD), speech separation (SS), and multi-speaker automatic speech recognition (ASR) tasks using a shared speech foundational encoder. We leverage the hidden representations from multiple layers of UME as a residual weighted-sum encoding (RWSE) to effectively use information from different semantic levels, contributing to bottom-up alignment between tasks. This joint training approach captures the inherent interdependencies among the tasks, enhancing overall","authors_text":"Chyi-Jiunn Lin, Muhammad Shakeel, Shinji Watanabe, Yifan Peng, Yui Sudo","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-08-28T06:50:57Z","title":"Unifying Diarization, Separation, and ASR with Multi-Speaker Encoder"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20474","kind":"arxiv","version":2},"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":"sha256:48f92c5d4b6817c98637ecb1dc1ebfe54b26e1ce84e93eaa6d29a6146c2b7246","target":"record","created_at":"2026-05-18T02:45:13Z","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":"cccedf6ae1a57631cff0014d73a848b298721833c79e6e3df1b1b20d308b4f75","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-08-28T06:50:57Z","title_canon_sha256":"31805a1ba74a3e998915fad102feb2f52fd6202998179abf70d37de9c50052b8"},"schema_version":"1.0","source":{"id":"2508.20474","kind":"arxiv","version":2}},"canonical_sha256":"6ef8018b825f2e7717a803a801346cf30edd3489f4a62ff046d285c59647b76b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ef8018b825f2e7717a803a801346cf30edd3489f4a62ff046d285c59647b76b","first_computed_at":"2026-05-18T02:45:13.100540Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:45:13.100540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UQ5hdXdHlwSIe1Uj54IhM5XcJLik63OplKuUZKJXGPmo3HjPlKhGNe9TxnYu2t+1batbu1fh16y4udi9WpRjDA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:45:13.101137Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.20474","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:48f92c5d4b6817c98637ecb1dc1ebfe54b26e1ce84e93eaa6d29a6146c2b7246","sha256:c1161b0a22525f9a73f9a9ac711d6294e9ebae6f6ff2c31e9c961f1b626a48b4"],"state_sha256":"d7777fc2c41b74bd3995123036707d9dc09d6d4b35c7e36434654a00f0f48d23"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j0yyYei/1oTIeMwjtXiiUmLpDhZxLHX7KTG312mssAhm87gjVmqwbp9U3IDlRYd9ghwiS6CFaKXLQ9V2fm7pCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T05:00:31.901382Z","bundle_sha256":"de55897810e656c003b60d13b523e14d3dafa0a73aa0331987ea5af65f008e1e"}}