{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UORIPP7DXKXEB6WDSTJAPKN6NS","short_pith_number":"pith:UORIPP7D","canonical_record":{"source":{"id":"2501.00114","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-12-30T19:24:15Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"484ece3d6ef9ecba35788d3bdc08d7749bdd66b147757f03e3b75869ac7bc355","abstract_canon_sha256":"bc596f9135221d85a3479adf8c8effc4bf2de248d0db54bbcd1b7fe0672bd94c"},"schema_version":"1.0"},"canonical_sha256":"a3a287bfe3baae40fac394d207a9be6cb8dd45e0e8f9d5a484795ce84f71aa17","source":{"kind":"arxiv","id":"2501.00114","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.00114","created_at":"2026-07-05T09:55:39Z"},{"alias_kind":"arxiv_version","alias_value":"2501.00114v1","created_at":"2026-07-05T09:55:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00114","created_at":"2026-07-05T09:55:39Z"},{"alias_kind":"pith_short_12","alias_value":"UORIPP7DXKXE","created_at":"2026-07-05T09:55:39Z"},{"alias_kind":"pith_short_16","alias_value":"UORIPP7DXKXEB6WD","created_at":"2026-07-05T09:55:39Z"},{"alias_kind":"pith_short_8","alias_value":"UORIPP7D","created_at":"2026-07-05T09:55:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UORIPP7DXKXEB6WDSTJAPKN6NS","target":"record","payload":{"canonical_record":{"source":{"id":"2501.00114","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-12-30T19:24:15Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"484ece3d6ef9ecba35788d3bdc08d7749bdd66b147757f03e3b75869ac7bc355","abstract_canon_sha256":"bc596f9135221d85a3479adf8c8effc4bf2de248d0db54bbcd1b7fe0672bd94c"},"schema_version":"1.0"},"canonical_sha256":"a3a287bfe3baae40fac394d207a9be6cb8dd45e0e8f9d5a484795ce84f71aa17","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:39.301459Z","signature_b64":"oUNtm3uTzvwtxbI3Z3KnjwXyFrECNdBAyD10OQiof7zsveqSqwFUIT4Kx5268igSrnx6c3zGAdPH/c98E8uaBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3a287bfe3baae40fac394d207a9be6cb8dd45e0e8f9d5a484795ce84f71aa17","last_reissued_at":"2026-07-05T09:55:39.300913Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:39.300913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.00114","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":"2026-07-05T09:55:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7CAflZE8nN17PUIzFZYuSLYYnz91bU3aa73Y45VSzHVlqzF/rBLiFG2WWyWH6WludxStlxn/Zow/IZ4WYN9cAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T11:42:57.389370Z"},"content_sha256":"3dd770a5244ba9c996aba63989fdc18a445ba607f6af8257566d2a6451b3a7af","schema_version":"1.0","event_id":"sha256:3dd770a5244ba9c996aba63989fdc18a445ba607f6af8257566d2a6451b3a7af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UORIPP7DXKXEB6WDSTJAPKN6NS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DiCoW: Diarization-Conditioned Whisper for Target Speaker Automatic Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Alexander Polok, Bolaji Yusuf, Dominik Klement, Federico Landini, Jan \\v{C}ernock\\'y, Jiangyu Han, Luk\\'a\\v{s} Burget, Martin Kocour, Matthew Wiesner, Sanjeev Khudanpur","submitted_at":"2024-12-30T19:24:15Z","abstract_excerpt":"Speaker-attributed automatic speech recognition (ASR) in multi-speaker environments remains a significant challenge, particularly when systems conditioned on speaker embeddings fail to generalize to unseen speakers. In this work, we propose Diarization-Conditioned Whisper (DiCoW), a novel approach to target-speaker ASR that leverages speaker diarization outputs as conditioning information. DiCoW extends the pre-trained Whisper model by integrating diarization labels directly, eliminating reliance on speaker embeddings and reducing the need for extensive speaker-specific training data. Our meth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00114","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/2501.00114/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:55:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v+Awv9qskTpjyaBITBazS/GWTcOGq5qgx6Hx3u175WY5Ay7qnbBUZdMNO3NPJ3spyhf3vvEfPw3LpaqJl3glAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T11:42:57.389941Z"},"content_sha256":"2e4ae9d6969bf962dbad2a9c098a8955b774d43730bb443e35d1312c0ec66dec","schema_version":"1.0","event_id":"sha256:2e4ae9d6969bf962dbad2a9c098a8955b774d43730bb443e35d1312c0ec66dec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UORIPP7DXKXEB6WDSTJAPKN6NS/bundle.json","state_url":"https://pith.science/pith/UORIPP7DXKXEB6WDSTJAPKN6NS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UORIPP7DXKXEB6WDSTJAPKN6NS/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":"2026-08-15T11:42:57Z","links":{"resolver":"https://pith.science/pith/UORIPP7DXKXEB6WDSTJAPKN6NS","bundle":"https://pith.science/pith/UORIPP7DXKXEB6WDSTJAPKN6NS/bundle.json","state":"https://pith.science/pith/UORIPP7DXKXEB6WDSTJAPKN6NS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UORIPP7DXKXEB6WDSTJAPKN6NS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UORIPP7DXKXEB6WDSTJAPKN6NS","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":"bc596f9135221d85a3479adf8c8effc4bf2de248d0db54bbcd1b7fe0672bd94c","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-12-30T19:24:15Z","title_canon_sha256":"484ece3d6ef9ecba35788d3bdc08d7749bdd66b147757f03e3b75869ac7bc355"},"schema_version":"1.0","source":{"id":"2501.00114","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.00114","created_at":"2026-07-05T09:55:39Z"},{"alias_kind":"arxiv_version","alias_value":"2501.00114v1","created_at":"2026-07-05T09:55:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00114","created_at":"2026-07-05T09:55:39Z"},{"alias_kind":"pith_short_12","alias_value":"UORIPP7DXKXE","created_at":"2026-07-05T09:55:39Z"},{"alias_kind":"pith_short_16","alias_value":"UORIPP7DXKXEB6WD","created_at":"2026-07-05T09:55:39Z"},{"alias_kind":"pith_short_8","alias_value":"UORIPP7D","created_at":"2026-07-05T09:55:39Z"}],"graph_snapshots":[{"event_id":"sha256:2e4ae9d6969bf962dbad2a9c098a8955b774d43730bb443e35d1312c0ec66dec","target":"graph","created_at":"2026-07-05T09:55:39Z","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/2501.00114/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speaker-attributed automatic speech recognition (ASR) in multi-speaker environments remains a significant challenge, particularly when systems conditioned on speaker embeddings fail to generalize to unseen speakers. In this work, we propose Diarization-Conditioned Whisper (DiCoW), a novel approach to target-speaker ASR that leverages speaker diarization outputs as conditioning information. DiCoW extends the pre-trained Whisper model by integrating diarization labels directly, eliminating reliance on speaker embeddings and reducing the need for extensive speaker-specific training data. Our meth","authors_text":"Alexander Polok, Bolaji Yusuf, Dominik Klement, Federico Landini, Jan \\v{C}ernock\\'y, Jiangyu Han, Luk\\'a\\v{s} Burget, Martin Kocour, Matthew Wiesner, Sanjeev Khudanpur","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-12-30T19:24:15Z","title":"DiCoW: Diarization-Conditioned Whisper for Target Speaker Automatic Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00114","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":"sha256:3dd770a5244ba9c996aba63989fdc18a445ba607f6af8257566d2a6451b3a7af","target":"record","created_at":"2026-07-05T09:55:39Z","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":"bc596f9135221d85a3479adf8c8effc4bf2de248d0db54bbcd1b7fe0672bd94c","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-12-30T19:24:15Z","title_canon_sha256":"484ece3d6ef9ecba35788d3bdc08d7749bdd66b147757f03e3b75869ac7bc355"},"schema_version":"1.0","source":{"id":"2501.00114","kind":"arxiv","version":1}},"canonical_sha256":"a3a287bfe3baae40fac394d207a9be6cb8dd45e0e8f9d5a484795ce84f71aa17","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3a287bfe3baae40fac394d207a9be6cb8dd45e0e8f9d5a484795ce84f71aa17","first_computed_at":"2026-07-05T09:55:39.300913Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:55:39.300913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oUNtm3uTzvwtxbI3Z3KnjwXyFrECNdBAyD10OQiof7zsveqSqwFUIT4Kx5268igSrnx6c3zGAdPH/c98E8uaBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:55:39.301459Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.00114","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3dd770a5244ba9c996aba63989fdc18a445ba607f6af8257566d2a6451b3a7af","sha256:2e4ae9d6969bf962dbad2a9c098a8955b774d43730bb443e35d1312c0ec66dec"],"state_sha256":"139502a59a38bd6068ef495500cbbe0b4452a7c5eaf58e4290c1c88df6456f60"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k/VDn1B6nlQ6L5/4JcZ4uldFVo0l3ZFzAiD11XDLqRGFkVDGNtNnkoaDfdAorfsAninPfaxLwsaRencVQmOjAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T11:42:57.394040Z","bundle_sha256":"ba5ba61b5f1e85c11762737593d416dd1ed1509fe8c50ce1500a37a697e9bfa1"}}