{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PMTOIQTMBV2RYMJ2DOTG3KUN6H","short_pith_number":"pith:PMTOIQTM","canonical_record":{"source":{"id":"2308.16692","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-31T12:53:09Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"6a1988a33ed5f266f2073d03467b12e5b85c67f43359356cdf61361242fa147e","abstract_canon_sha256":"733a50eff75d9e9afb1ba189fe85812b6e88e963096efe7dc794bff993d99f8b"},"schema_version":"1.0"},"canonical_sha256":"7b26e4426c0d751c313a1ba66daa8df1f20b486fb1dc2e5ccf2a94ddb9d3423a","source":{"kind":"arxiv","id":"2308.16692","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.16692","created_at":"2026-07-05T07:36:23Z"},{"alias_kind":"arxiv_version","alias_value":"2308.16692v2","created_at":"2026-07-05T07:36:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.16692","created_at":"2026-07-05T07:36:23Z"},{"alias_kind":"pith_short_12","alias_value":"PMTOIQTMBV2R","created_at":"2026-07-05T07:36:23Z"},{"alias_kind":"pith_short_16","alias_value":"PMTOIQTMBV2RYMJ2","created_at":"2026-07-05T07:36:23Z"},{"alias_kind":"pith_short_8","alias_value":"PMTOIQTM","created_at":"2026-07-05T07:36:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PMTOIQTMBV2RYMJ2DOTG3KUN6H","target":"record","payload":{"canonical_record":{"source":{"id":"2308.16692","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-31T12:53:09Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"6a1988a33ed5f266f2073d03467b12e5b85c67f43359356cdf61361242fa147e","abstract_canon_sha256":"733a50eff75d9e9afb1ba189fe85812b6e88e963096efe7dc794bff993d99f8b"},"schema_version":"1.0"},"canonical_sha256":"7b26e4426c0d751c313a1ba66daa8df1f20b486fb1dc2e5ccf2a94ddb9d3423a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:23.499665Z","signature_b64":"+cluaCY7K+p010S7+yzWqDvuofH7mPUM9mRZqqRva/Z9M3ewrCXZ5UaPX3yT0VPeL95js+Y13FRZn2K3go/wDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b26e4426c0d751c313a1ba66daa8df1f20b486fb1dc2e5ccf2a94ddb9d3423a","last_reissued_at":"2026-07-05T07:36:23.499170Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:23.499170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.16692","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":"2026-07-05T07:36:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XSsO0SPA2z9XmPsAVq+6KfKWeYKAzHhGKzx+pr42JKfDsalGZiZo3NVbe1neLAZbsSXbR9yg9mroP59vhiC2AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T13:30:54.444748Z"},"content_sha256":"e4295daebb6581018fa26c66f06a80ca0a8f621ed46d58a0340f219a05c44923","schema_version":"1.0","event_id":"sha256:e4295daebb6581018fa26c66f06a80ca0a8f621ed46d58a0340f219a05c44923"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PMTOIQTMBV2RYMJ2DOTG3KUN6H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Dong Zhang, Shimin Li, Xin Zhang, Xipeng Qiu, Yaqian Zhou","submitted_at":"2023-08-31T12:53:09Z","abstract_excerpt":"Current speech large language models build upon discrete speech representations, which can be categorized into semantic tokens and acoustic tokens. However, existing speech tokens are not specifically designed for speech language modeling. To assess the suitability of speech tokens for building speech language models, we established the first benchmark, SLMTokBench. Our results indicate that neither semantic nor acoustic tokens are ideal for this purpose. Therefore, we propose SpeechTokenizer, a unified speech tokenizer for speech large language models. SpeechTokenizer adopts the Encoder-Decod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.16692","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2308.16692/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":"2026-07-05T07:36:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rJ7clzq28JYD2G7edc0Vva6gPRWeXqNknhcqelijvau4L/pWi99szVz1IntKhnnxZsdJctlqhHstm/F8T8g6BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T13:30:54.445121Z"},"content_sha256":"71e6c26cc752cc1c7cf445ec07f989dc1082a5f6a01baa628ccb5f5389d54c63","schema_version":"1.0","event_id":"sha256:71e6c26cc752cc1c7cf445ec07f989dc1082a5f6a01baa628ccb5f5389d54c63"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PMTOIQTMBV2RYMJ2DOTG3KUN6H/bundle.json","state_url":"https://pith.science/pith/PMTOIQTMBV2RYMJ2DOTG3KUN6H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PMTOIQTMBV2RYMJ2DOTG3KUN6H/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":"2026-07-06T13:30:54Z","links":{"resolver":"https://pith.science/pith/PMTOIQTMBV2RYMJ2DOTG3KUN6H","bundle":"https://pith.science/pith/PMTOIQTMBV2RYMJ2DOTG3KUN6H/bundle.json","state":"https://pith.science/pith/PMTOIQTMBV2RYMJ2DOTG3KUN6H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PMTOIQTMBV2RYMJ2DOTG3KUN6H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PMTOIQTMBV2RYMJ2DOTG3KUN6H","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":"733a50eff75d9e9afb1ba189fe85812b6e88e963096efe7dc794bff993d99f8b","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-31T12:53:09Z","title_canon_sha256":"6a1988a33ed5f266f2073d03467b12e5b85c67f43359356cdf61361242fa147e"},"schema_version":"1.0","source":{"id":"2308.16692","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.16692","created_at":"2026-07-05T07:36:23Z"},{"alias_kind":"arxiv_version","alias_value":"2308.16692v2","created_at":"2026-07-05T07:36:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.16692","created_at":"2026-07-05T07:36:23Z"},{"alias_kind":"pith_short_12","alias_value":"PMTOIQTMBV2R","created_at":"2026-07-05T07:36:23Z"},{"alias_kind":"pith_short_16","alias_value":"PMTOIQTMBV2RYMJ2","created_at":"2026-07-05T07:36:23Z"},{"alias_kind":"pith_short_8","alias_value":"PMTOIQTM","created_at":"2026-07-05T07:36:23Z"}],"graph_snapshots":[{"event_id":"sha256:71e6c26cc752cc1c7cf445ec07f989dc1082a5f6a01baa628ccb5f5389d54c63","target":"graph","created_at":"2026-07-05T07:36:23Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2308.16692/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current speech large language models build upon discrete speech representations, which can be categorized into semantic tokens and acoustic tokens. However, existing speech tokens are not specifically designed for speech language modeling. To assess the suitability of speech tokens for building speech language models, we established the first benchmark, SLMTokBench. Our results indicate that neither semantic nor acoustic tokens are ideal for this purpose. Therefore, we propose SpeechTokenizer, a unified speech tokenizer for speech large language models. SpeechTokenizer adopts the Encoder-Decod","authors_text":"Dong Zhang, Shimin Li, Xin Zhang, Xipeng Qiu, Yaqian Zhou","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-31T12:53:09Z","title":"SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.16692","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:e4295daebb6581018fa26c66f06a80ca0a8f621ed46d58a0340f219a05c44923","target":"record","created_at":"2026-07-05T07:36:23Z","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":"733a50eff75d9e9afb1ba189fe85812b6e88e963096efe7dc794bff993d99f8b","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-31T12:53:09Z","title_canon_sha256":"6a1988a33ed5f266f2073d03467b12e5b85c67f43359356cdf61361242fa147e"},"schema_version":"1.0","source":{"id":"2308.16692","kind":"arxiv","version":2}},"canonical_sha256":"7b26e4426c0d751c313a1ba66daa8df1f20b486fb1dc2e5ccf2a94ddb9d3423a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b26e4426c0d751c313a1ba66daa8df1f20b486fb1dc2e5ccf2a94ddb9d3423a","first_computed_at":"2026-07-05T07:36:23.499170Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:36:23.499170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+cluaCY7K+p010S7+yzWqDvuofH7mPUM9mRZqqRva/Z9M3ewrCXZ5UaPX3yT0VPeL95js+Y13FRZn2K3go/wDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:36:23.499665Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.16692","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4295daebb6581018fa26c66f06a80ca0a8f621ed46d58a0340f219a05c44923","sha256:71e6c26cc752cc1c7cf445ec07f989dc1082a5f6a01baa628ccb5f5389d54c63"],"state_sha256":"e3e1a1e6ea98708b2085398c196593c39caeae50058a8cdf719e502562b1b3c9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i96D7qsHQt/OVdKnUM+EEoRMl/rgt4KRntqI6+TFglUBXb+9OQ2sMrOW6rZf9shO0AEkdFHS4RTfMxxZ+5CMBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T13:30:54.447416Z","bundle_sha256":"1e5ad0a194c668d3c8219e2d34f8b973019eb00ce9226b5fecf5c68094f03097"}}