{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2M6WQJNBZQLJBPGY4KFR4LMA2G","short_pith_number":"pith:2M6WQJNB","canonical_record":{"source":{"id":"2412.15649","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-12-20T08:05:55Z","cross_cats_sorted":[],"title_canon_sha256":"33eafac155c01e7f8d7610a2d6540060e3174021a6f5f0f2b0bc0969980ab7b7","abstract_canon_sha256":"33527fbbec7a1e952540f8887e5724682fad2aa7692cd7720c177bf12451308f"},"schema_version":"1.0"},"canonical_sha256":"d33d6825a1cc1690bcd8e28b1e2d80d1a778810d97771ae5d99adc953dad0aee","source":{"kind":"arxiv","id":"2412.15649","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15649","created_at":"2026-07-05T09:52:27Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15649v1","created_at":"2026-07-05T09:52:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15649","created_at":"2026-07-05T09:52:27Z"},{"alias_kind":"pith_short_12","alias_value":"2M6WQJNBZQLJ","created_at":"2026-07-05T09:52:27Z"},{"alias_kind":"pith_short_16","alias_value":"2M6WQJNBZQLJBPGY","created_at":"2026-07-05T09:52:27Z"},{"alias_kind":"pith_short_8","alias_value":"2M6WQJNB","created_at":"2026-07-05T09:52:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2M6WQJNBZQLJBPGY4KFR4LMA2G","target":"record","payload":{"canonical_record":{"source":{"id":"2412.15649","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-12-20T08:05:55Z","cross_cats_sorted":[],"title_canon_sha256":"33eafac155c01e7f8d7610a2d6540060e3174021a6f5f0f2b0bc0969980ab7b7","abstract_canon_sha256":"33527fbbec7a1e952540f8887e5724682fad2aa7692cd7720c177bf12451308f"},"schema_version":"1.0"},"canonical_sha256":"d33d6825a1cc1690bcd8e28b1e2d80d1a778810d97771ae5d99adc953dad0aee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:27.671171Z","signature_b64":"l+WvR3UAhIrqiKvYgyjpXqAooU62DoLjn12YhBXXVcIWe78pmJnJzzx9oMNpOO8MT4ZDNBo1LpJZBUIDiSD/CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d33d6825a1cc1690bcd8e28b1e2d80d1a778810d97771ae5d99adc953dad0aee","last_reissued_at":"2026-07-05T09:52:27.670589Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:27.670589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.15649","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":"2026-07-05T09:52:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ShN+41to8LiBRW2ZZhdqA+PhiJerhqVlZkoEz4lFEjMzR+EInEVdiaT1k34wwg0+sKiOrKX+kAdQhMnlduHuCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:00:39.412551Z"},"content_sha256":"14d2ecbf529992b3cc5df28bac945d4224bf5620043d11984e47a8da681d62b3","schema_version":"1.0","event_id":"sha256:14d2ecbf529992b3cc5df28bac945d4224bf5620043d11984e47a8da681d62b3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2M6WQJNBZQLJBPGY4KFR4LMA2G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Jinyu Li, Kai Yu, Ruiqi Yan, Ruiyang Xu, Shujie Liu, Wenxi Chen, Xie Chen, Xiquan Li, Yan Lu, Yanqiao Zhu, Yifan Yang, Yuxuan Hu, Yuzhe Liang, Zhanxun Liu, Zhikang Niu, Ziyang Ma","submitted_at":"2024-12-20T08:05:55Z","abstract_excerpt":"Recent advancements highlight the potential of end-to-end real-time spoken dialogue systems, showcasing their low latency and high quality. In this paper, we introduce SLAM-Omni, a timbre-controllable, end-to-end voice interaction system with single-stage training. SLAM-Omni achieves zero-shot timbre control by modeling spoken language with semantic tokens and decoupling speaker information to a vocoder. By predicting grouped speech semantic tokens at each step, our method significantly reduces the sequence length of audio tokens, accelerating both training and inference. Additionally, we prop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15649","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/2412.15649/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":"2026-07-05T09:52:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FJ8ZhoxcdwwsP73AJCdSM4JSruMWfR2HIh1kLBZv6jrlT3xPLOXjj5kfLz0ESopbevmJzMZKga9K4kSj47buDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:00:39.413051Z"},"content_sha256":"c2c0a1cb838717b52e113ce39ed1a0a046ed52c0b5a151d6cdf6252fb4abd385","schema_version":"1.0","event_id":"sha256:c2c0a1cb838717b52e113ce39ed1a0a046ed52c0b5a151d6cdf6252fb4abd385"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2M6WQJNBZQLJBPGY4KFR4LMA2G/bundle.json","state_url":"https://pith.science/pith/2M6WQJNBZQLJBPGY4KFR4LMA2G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2M6WQJNBZQLJBPGY4KFR4LMA2G/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":"2026-08-06T07:00:39Z","links":{"resolver":"https://pith.science/pith/2M6WQJNBZQLJBPGY4KFR4LMA2G","bundle":"https://pith.science/pith/2M6WQJNBZQLJBPGY4KFR4LMA2G/bundle.json","state":"https://pith.science/pith/2M6WQJNBZQLJBPGY4KFR4LMA2G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2M6WQJNBZQLJBPGY4KFR4LMA2G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2M6WQJNBZQLJBPGY4KFR4LMA2G","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":"33527fbbec7a1e952540f8887e5724682fad2aa7692cd7720c177bf12451308f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-12-20T08:05:55Z","title_canon_sha256":"33eafac155c01e7f8d7610a2d6540060e3174021a6f5f0f2b0bc0969980ab7b7"},"schema_version":"1.0","source":{"id":"2412.15649","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15649","created_at":"2026-07-05T09:52:27Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15649v1","created_at":"2026-07-05T09:52:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15649","created_at":"2026-07-05T09:52:27Z"},{"alias_kind":"pith_short_12","alias_value":"2M6WQJNBZQLJ","created_at":"2026-07-05T09:52:27Z"},{"alias_kind":"pith_short_16","alias_value":"2M6WQJNBZQLJBPGY","created_at":"2026-07-05T09:52:27Z"},{"alias_kind":"pith_short_8","alias_value":"2M6WQJNB","created_at":"2026-07-05T09:52:27Z"}],"graph_snapshots":[{"event_id":"sha256:c2c0a1cb838717b52e113ce39ed1a0a046ed52c0b5a151d6cdf6252fb4abd385","target":"graph","created_at":"2026-07-05T09:52:27Z","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/2412.15649/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements highlight the potential of end-to-end real-time spoken dialogue systems, showcasing their low latency and high quality. In this paper, we introduce SLAM-Omni, a timbre-controllable, end-to-end voice interaction system with single-stage training. SLAM-Omni achieves zero-shot timbre control by modeling spoken language with semantic tokens and decoupling speaker information to a vocoder. By predicting grouped speech semantic tokens at each step, our method significantly reduces the sequence length of audio tokens, accelerating both training and inference. Additionally, we prop","authors_text":"Jinyu Li, Kai Yu, Ruiqi Yan, Ruiyang Xu, Shujie Liu, Wenxi Chen, Xie Chen, Xiquan Li, Yan Lu, Yanqiao Zhu, Yifan Yang, Yuxuan Hu, Yuzhe Liang, Zhanxun Liu, Zhikang Niu, Ziyang Ma","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-12-20T08:05:55Z","title":"SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15649","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":"sha256:14d2ecbf529992b3cc5df28bac945d4224bf5620043d11984e47a8da681d62b3","target":"record","created_at":"2026-07-05T09:52:27Z","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":"33527fbbec7a1e952540f8887e5724682fad2aa7692cd7720c177bf12451308f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-12-20T08:05:55Z","title_canon_sha256":"33eafac155c01e7f8d7610a2d6540060e3174021a6f5f0f2b0bc0969980ab7b7"},"schema_version":"1.0","source":{"id":"2412.15649","kind":"arxiv","version":1}},"canonical_sha256":"d33d6825a1cc1690bcd8e28b1e2d80d1a778810d97771ae5d99adc953dad0aee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d33d6825a1cc1690bcd8e28b1e2d80d1a778810d97771ae5d99adc953dad0aee","first_computed_at":"2026-07-05T09:52:27.670589Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:52:27.670589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l+WvR3UAhIrqiKvYgyjpXqAooU62DoLjn12YhBXXVcIWe78pmJnJzzx9oMNpOO8MT4ZDNBo1LpJZBUIDiSD/CA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:52:27.671171Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.15649","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14d2ecbf529992b3cc5df28bac945d4224bf5620043d11984e47a8da681d62b3","sha256:c2c0a1cb838717b52e113ce39ed1a0a046ed52c0b5a151d6cdf6252fb4abd385"],"state_sha256":"e8b707f1601730352a7f2fce1e5cbc21c2695fcdf14f2a7540011258f31003a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1kYHy/g6EPH6xwFBHv3DVqSkDh8DJzf+RTrWSjNSkPys6PnJVkETJscn/7rBN4KDdAvs5cj2jKhMd1KbEkYjCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T07:00:39.417864Z","bundle_sha256":"cd908a7e666d82b087b0e1b283da92fe1e5d0201fcad18b89b2b6ae4631ec810"}}