{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:TF22HCBSXUPF2BW52QMQZGMCEX","short_pith_number":"pith:TF22HCBS","canonical_record":{"source":{"id":"2606.02400","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-01T15:47:01Z","cross_cats_sorted":[],"title_canon_sha256":"7c1beabc1bff16a874fb9905f247554523e4b1a19718d38923ca17dea47c0b32","abstract_canon_sha256":"5fb761012469097562df57bd25ecb051fae3ad306316199adef6c8fac3b5d4ed"},"schema_version":"1.0"},"canonical_sha256":"9975a38832bd1e5d06ddd4190c998225c6917c4366b0eeaeac77c7d8c24f092d","source":{"kind":"arxiv","id":"2606.02400","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.02400","created_at":"2026-06-02T03:04:58Z"},{"alias_kind":"arxiv_version","alias_value":"2606.02400v1","created_at":"2026-06-02T03:04:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02400","created_at":"2026-06-02T03:04:58Z"},{"alias_kind":"pith_short_12","alias_value":"TF22HCBSXUPF","created_at":"2026-06-02T03:04:58Z"},{"alias_kind":"pith_short_16","alias_value":"TF22HCBSXUPF2BW5","created_at":"2026-06-02T03:04:58Z"},{"alias_kind":"pith_short_8","alias_value":"TF22HCBS","created_at":"2026-06-02T03:04:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:TF22HCBSXUPF2BW52QMQZGMCEX","target":"record","payload":{"canonical_record":{"source":{"id":"2606.02400","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-01T15:47:01Z","cross_cats_sorted":[],"title_canon_sha256":"7c1beabc1bff16a874fb9905f247554523e4b1a19718d38923ca17dea47c0b32","abstract_canon_sha256":"5fb761012469097562df57bd25ecb051fae3ad306316199adef6c8fac3b5d4ed"},"schema_version":"1.0"},"canonical_sha256":"9975a38832bd1e5d06ddd4190c998225c6917c4366b0eeaeac77c7d8c24f092d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T03:04:58.176684Z","signature_b64":"LAq56OnLYjdLEgWEdr3h8UUbtahcFkTS4zrszqnn43DBTvjPSOs5OCGX1ypRgJCSkKH4ECgX7h0YHZPIlpNlBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9975a38832bd1e5d06ddd4190c998225c6917c4366b0eeaeac77c7d8c24f092d","last_reissued_at":"2026-06-02T03:04:58.176261Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T03:04:58.176261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.02400","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":"2026-06-02T03:04:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lj1fR6iZM8IGbMCJw9ESBSXYwYbS4fzqZsbcTfqQxibcOjqxfw1/yjiIvxZCqpPZJqRMWaEd0GSS6rcUBZbGAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T21:08:34.539291Z"},"content_sha256":"8de5b41792320ff73b67fa53ab9d388d1fa9fa48e3183df54cc20e78e5aa5c47","schema_version":"1.0","event_id":"sha256:8de5b41792320ff73b67fa53ab9d388d1fa9fa48e3183df54cc20e78e5aa5c47"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:TF22HCBSXUPF2BW52QMQZGMCEX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SoulX-Transcriber: A Robust End-to-End Framework for Multi-Speaker Speech Transcription","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Chuang Ding, Hanke Xie, Hanlin Wen, Hao Meng, Haopeng Lin, Jiale Qian, Jun Wu, Lei Xie, Ming Tao, Shunshun Yin, Xinsheng Wang, Yuhang Dai, Zhennan Lin","submitted_at":"2026-06-01T15:47:01Z","abstract_excerpt":"Recent advances in Automatic Speech Recognition (ASR) and Large Language Models (LLMs) have significantly improved speech understanding capabilities. However, multi-speaker speech transcription remains challenging task, constrained by highly similar speaker voices, rapid turn-taking transitions, overlapping utterances and inaccurate speaker boundary segmentation. These challenges become particularly pronounced in real-world conversational audio, where speaker dynamics and acoustic conditions are highly variable. This technical report presents SoulX-Transcriber, a unified multi-speaker transcri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02400","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/2606.02400/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":"2026-06-02T03:04:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Whlkk0kHpl7YMAUuxl3FNExyYUxIUPGuEc/0GmZrUqyi+iM5PfH9PZHXV4AkMQ7Qf7BbzyzoZgTF8jP5IhOkBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T21:08:34.539725Z"},"content_sha256":"40cb9860db00763902645458741b64acc5feea054c5447cccc71108fecef4cf8","schema_version":"1.0","event_id":"sha256:40cb9860db00763902645458741b64acc5feea054c5447cccc71108fecef4cf8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TF22HCBSXUPF2BW52QMQZGMCEX/bundle.json","state_url":"https://pith.science/pith/TF22HCBSXUPF2BW52QMQZGMCEX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TF22HCBSXUPF2BW52QMQZGMCEX/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":"2026-06-04T21:08:34Z","links":{"resolver":"https://pith.science/pith/TF22HCBSXUPF2BW52QMQZGMCEX","bundle":"https://pith.science/pith/TF22HCBSXUPF2BW52QMQZGMCEX/bundle.json","state":"https://pith.science/pith/TF22HCBSXUPF2BW52QMQZGMCEX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TF22HCBSXUPF2BW52QMQZGMCEX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TF22HCBSXUPF2BW52QMQZGMCEX","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":"5fb761012469097562df57bd25ecb051fae3ad306316199adef6c8fac3b5d4ed","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-01T15:47:01Z","title_canon_sha256":"7c1beabc1bff16a874fb9905f247554523e4b1a19718d38923ca17dea47c0b32"},"schema_version":"1.0","source":{"id":"2606.02400","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.02400","created_at":"2026-06-02T03:04:58Z"},{"alias_kind":"arxiv_version","alias_value":"2606.02400v1","created_at":"2026-06-02T03:04:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02400","created_at":"2026-06-02T03:04:58Z"},{"alias_kind":"pith_short_12","alias_value":"TF22HCBSXUPF","created_at":"2026-06-02T03:04:58Z"},{"alias_kind":"pith_short_16","alias_value":"TF22HCBSXUPF2BW5","created_at":"2026-06-02T03:04:58Z"},{"alias_kind":"pith_short_8","alias_value":"TF22HCBS","created_at":"2026-06-02T03:04:58Z"}],"graph_snapshots":[{"event_id":"sha256:40cb9860db00763902645458741b64acc5feea054c5447cccc71108fecef4cf8","target":"graph","created_at":"2026-06-02T03:04:58Z","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/2606.02400/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in Automatic Speech Recognition (ASR) and Large Language Models (LLMs) have significantly improved speech understanding capabilities. However, multi-speaker speech transcription remains challenging task, constrained by highly similar speaker voices, rapid turn-taking transitions, overlapping utterances and inaccurate speaker boundary segmentation. These challenges become particularly pronounced in real-world conversational audio, where speaker dynamics and acoustic conditions are highly variable. This technical report presents SoulX-Transcriber, a unified multi-speaker transcri","authors_text":"Chuang Ding, Hanke Xie, Hanlin Wen, Hao Meng, Haopeng Lin, Jiale Qian, Jun Wu, Lei Xie, Ming Tao, Shunshun Yin, Xinsheng Wang, Yuhang Dai, Zhennan Lin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-01T15:47:01Z","title":"SoulX-Transcriber: A Robust End-to-End Framework for Multi-Speaker Speech Transcription"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02400","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":"sha256:8de5b41792320ff73b67fa53ab9d388d1fa9fa48e3183df54cc20e78e5aa5c47","target":"record","created_at":"2026-06-02T03:04:58Z","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":"5fb761012469097562df57bd25ecb051fae3ad306316199adef6c8fac3b5d4ed","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-01T15:47:01Z","title_canon_sha256":"7c1beabc1bff16a874fb9905f247554523e4b1a19718d38923ca17dea47c0b32"},"schema_version":"1.0","source":{"id":"2606.02400","kind":"arxiv","version":1}},"canonical_sha256":"9975a38832bd1e5d06ddd4190c998225c6917c4366b0eeaeac77c7d8c24f092d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9975a38832bd1e5d06ddd4190c998225c6917c4366b0eeaeac77c7d8c24f092d","first_computed_at":"2026-06-02T03:04:58.176261Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T03:04:58.176261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LAq56OnLYjdLEgWEdr3h8UUbtahcFkTS4zrszqnn43DBTvjPSOs5OCGX1ypRgJCSkKH4ECgX7h0YHZPIlpNlBg==","signature_status":"signed_v1","signed_at":"2026-06-02T03:04:58.176684Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.02400","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8de5b41792320ff73b67fa53ab9d388d1fa9fa48e3183df54cc20e78e5aa5c47","sha256:40cb9860db00763902645458741b64acc5feea054c5447cccc71108fecef4cf8"],"state_sha256":"ed751bafd5bc40d8d7cd665488c7b729fa543eab85e97620577e80e8d22a11b8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HtKWCcGviiutGW+dtSbDqJNf085JEOf1fjMN4n/zO3d5+o1iNTPythIn3e1Yx2IPtspZM1ngdegifS8Ek9nSCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T21:08:34.541814Z","bundle_sha256":"aee03a7a80f50b3216bec708350200ddf6ef2a00ef16fe9ac393d78013523a10"}}