{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SYJHUXMKBTTMX3LQ5MSFQLME64","short_pith_number":"pith:SYJHUXMK","canonical_record":{"source":{"id":"2409.03701","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-05T16:57:39Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"e6c872528333d26220c398208742008ed6c7cfa32bfac3b98ebf58bedb207085","abstract_canon_sha256":"74cc85ac45f2edd735f43c69c4c19f57c996c60d58e36b36141be368f97d45ab"},"schema_version":"1.0"},"canonical_sha256":"96127a5d8a0ce6cbed70eb24582d84f72427fc23c96379dc0024a1d600c7afe5","source":{"kind":"arxiv","id":"2409.03701","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.03701","created_at":"2026-07-05T09:05:19Z"},{"alias_kind":"arxiv_version","alias_value":"2409.03701v2","created_at":"2026-07-05T09:05:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.03701","created_at":"2026-07-05T09:05:19Z"},{"alias_kind":"pith_short_12","alias_value":"SYJHUXMKBTTM","created_at":"2026-07-05T09:05:19Z"},{"alias_kind":"pith_short_16","alias_value":"SYJHUXMKBTTMX3LQ","created_at":"2026-07-05T09:05:19Z"},{"alias_kind":"pith_short_8","alias_value":"SYJHUXMK","created_at":"2026-07-05T09:05:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SYJHUXMKBTTMX3LQ5MSFQLME64","target":"record","payload":{"canonical_record":{"source":{"id":"2409.03701","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-05T16:57:39Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"e6c872528333d26220c398208742008ed6c7cfa32bfac3b98ebf58bedb207085","abstract_canon_sha256":"74cc85ac45f2edd735f43c69c4c19f57c996c60d58e36b36141be368f97d45ab"},"schema_version":"1.0"},"canonical_sha256":"96127a5d8a0ce6cbed70eb24582d84f72427fc23c96379dc0024a1d600c7afe5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:05:19.075618Z","signature_b64":"0Zs9blh6qPVevMVCuv+C8vgVmNy4kPA+vZPqSR1vhhqTWj3shCx3eBlSRjJP4W58KPF1CLlvawV7a4ioS7CWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96127a5d8a0ce6cbed70eb24582d84f72427fc23c96379dc0024a1d600c7afe5","last_reissued_at":"2026-07-05T09:05:19.075162Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:05:19.075162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.03701","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":"2026-07-05T09:05:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9rVFRI/YddYkr6HxMOxRKAKHjK7R/bqvxDBrYGs1J9uSZ57y13adwNBScQybI/DbtMGpOwqDEblgH01qXo0NDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:13:09.177849Z"},"content_sha256":"f010ab9dcf061a7fb8ba2abe2c058bc2c8aa3a3306f89fe1729a24723c275587","schema_version":"1.0","event_id":"sha256:f010ab9dcf061a7fb8ba2abe2c058bc2c8aa3a3306f89fe1729a24723c275587"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SYJHUXMKBTTMX3LQ5MSFQLME64","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LAST: Language Model Aware Speech Tokenization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Arnon Turetzky, Yossi Adi","submitted_at":"2024-09-05T16:57:39Z","abstract_excerpt":"Speech tokenization serves as the foundation of speech language model (LM), enabling them to perform various tasks such as spoken language modeling, text-to-speech, speech-to-text, etc. Most speech tokenizers are trained independently of the LM training process, relying on separate acoustic models and quantization methods. Following such an approach may create a mismatch between the tokenization process and its usage afterward. In this study, we propose a novel approach to training a speech tokenizer by leveraging objectives from pre-trained textual LMs. We advocate for the integration of this"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.03701","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/2409.03701/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":"2026-07-05T09:05:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L2Rhli3C4Qskx+S5Tu+hTPMHeU6WNT3QNI/yo2H7FfMAPWmkzYJJXMiNyAzSSP/EMBehGDDu8dE/pDPq0UBYBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:13:09.179178Z"},"content_sha256":"3912749e3b63444aabfc71cee746f4009ede1f11971bd7b6ab7fa2e1a2150631","schema_version":"1.0","event_id":"sha256:3912749e3b63444aabfc71cee746f4009ede1f11971bd7b6ab7fa2e1a2150631"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SYJHUXMKBTTMX3LQ5MSFQLME64/bundle.json","state_url":"https://pith.science/pith/SYJHUXMKBTTMX3LQ5MSFQLME64/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SYJHUXMKBTTMX3LQ5MSFQLME64/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":"2026-08-08T19:13:09Z","links":{"resolver":"https://pith.science/pith/SYJHUXMKBTTMX3LQ5MSFQLME64","bundle":"https://pith.science/pith/SYJHUXMKBTTMX3LQ5MSFQLME64/bundle.json","state":"https://pith.science/pith/SYJHUXMKBTTMX3LQ5MSFQLME64/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SYJHUXMKBTTMX3LQ5MSFQLME64/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SYJHUXMKBTTMX3LQ5MSFQLME64","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":"74cc85ac45f2edd735f43c69c4c19f57c996c60d58e36b36141be368f97d45ab","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-05T16:57:39Z","title_canon_sha256":"e6c872528333d26220c398208742008ed6c7cfa32bfac3b98ebf58bedb207085"},"schema_version":"1.0","source":{"id":"2409.03701","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.03701","created_at":"2026-07-05T09:05:19Z"},{"alias_kind":"arxiv_version","alias_value":"2409.03701v2","created_at":"2026-07-05T09:05:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.03701","created_at":"2026-07-05T09:05:19Z"},{"alias_kind":"pith_short_12","alias_value":"SYJHUXMKBTTM","created_at":"2026-07-05T09:05:19Z"},{"alias_kind":"pith_short_16","alias_value":"SYJHUXMKBTTMX3LQ","created_at":"2026-07-05T09:05:19Z"},{"alias_kind":"pith_short_8","alias_value":"SYJHUXMK","created_at":"2026-07-05T09:05:19Z"}],"graph_snapshots":[{"event_id":"sha256:3912749e3b63444aabfc71cee746f4009ede1f11971bd7b6ab7fa2e1a2150631","target":"graph","created_at":"2026-07-05T09:05:19Z","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/2409.03701/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech tokenization serves as the foundation of speech language model (LM), enabling them to perform various tasks such as spoken language modeling, text-to-speech, speech-to-text, etc. Most speech tokenizers are trained independently of the LM training process, relying on separate acoustic models and quantization methods. Following such an approach may create a mismatch between the tokenization process and its usage afterward. In this study, we propose a novel approach to training a speech tokenizer by leveraging objectives from pre-trained textual LMs. We advocate for the integration of this","authors_text":"Arnon Turetzky, Yossi Adi","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-05T16:57:39Z","title":"LAST: Language Model Aware Speech Tokenization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.03701","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:f010ab9dcf061a7fb8ba2abe2c058bc2c8aa3a3306f89fe1729a24723c275587","target":"record","created_at":"2026-07-05T09:05:19Z","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":"74cc85ac45f2edd735f43c69c4c19f57c996c60d58e36b36141be368f97d45ab","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-05T16:57:39Z","title_canon_sha256":"e6c872528333d26220c398208742008ed6c7cfa32bfac3b98ebf58bedb207085"},"schema_version":"1.0","source":{"id":"2409.03701","kind":"arxiv","version":2}},"canonical_sha256":"96127a5d8a0ce6cbed70eb24582d84f72427fc23c96379dc0024a1d600c7afe5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"96127a5d8a0ce6cbed70eb24582d84f72427fc23c96379dc0024a1d600c7afe5","first_computed_at":"2026-07-05T09:05:19.075162Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:05:19.075162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0Zs9blh6qPVevMVCuv+C8vgVmNy4kPA+vZPqSR1vhhqTWj3shCx3eBlSRjJP4W58KPF1CLlvawV7a4ioS7CWBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:05:19.075618Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.03701","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f010ab9dcf061a7fb8ba2abe2c058bc2c8aa3a3306f89fe1729a24723c275587","sha256:3912749e3b63444aabfc71cee746f4009ede1f11971bd7b6ab7fa2e1a2150631"],"state_sha256":"67ff5899e9cf15a68f3ef1e53dccb914bd6b3022c41b8ce33eb612217c57b182"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qxjnl9C5wmA34pptjPw+vpXCKcvVVtAT+lc5i1Iu1rg9s4aL71zLiP6ZTJJiBjwAxf8rQUJA8f0aB7+3Y8UOCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:13:09.190668Z","bundle_sha256":"71409e7dc5ed09b5c09343214de234272cf0d8d4f84cca1f4164652f7b3bcdd4"}}