{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3S6VQLWYOXUDBCZIDQINDHLNCO","short_pith_number":"pith:3S6VQLWY","canonical_record":{"source":{"id":"2406.11037","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-16T18:20:45Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"449cdea13861919621f59d1cb6c5000cb3e41106a8a90dd5759cb53c71e9ac8a","abstract_canon_sha256":"438f837d18ca49aeb6e671dea9e47e5fda031857df29fc38872bd64aa366b54e"},"schema_version":"1.0"},"canonical_sha256":"dcbd582ed875e8308b281c10d19d6d1383b352a94e4a24ccdcce1709f7bb4a5d","source":{"kind":"arxiv","id":"2406.11037","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11037","created_at":"2026-07-05T08:32:47Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11037v1","created_at":"2026-07-05T08:32:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11037","created_at":"2026-07-05T08:32:47Z"},{"alias_kind":"pith_short_12","alias_value":"3S6VQLWYOXUD","created_at":"2026-07-05T08:32:47Z"},{"alias_kind":"pith_short_16","alias_value":"3S6VQLWYOXUDBCZI","created_at":"2026-07-05T08:32:47Z"},{"alias_kind":"pith_short_8","alias_value":"3S6VQLWY","created_at":"2026-07-05T08:32:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3S6VQLWYOXUDBCZIDQINDHLNCO","target":"record","payload":{"canonical_record":{"source":{"id":"2406.11037","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-16T18:20:45Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"449cdea13861919621f59d1cb6c5000cb3e41106a8a90dd5759cb53c71e9ac8a","abstract_canon_sha256":"438f837d18ca49aeb6e671dea9e47e5fda031857df29fc38872bd64aa366b54e"},"schema_version":"1.0"},"canonical_sha256":"dcbd582ed875e8308b281c10d19d6d1383b352a94e4a24ccdcce1709f7bb4a5d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:47.974219Z","signature_b64":"tZEcYC2UpiRcx/3xbDDU5efAe0CIW2Hx5INHvm3xHni6aZahpd4qDQCmZV954eQ2tHpq89UmOtuB1TJvy+E5CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcbd582ed875e8308b281c10d19d6d1383b352a94e4a24ccdcce1709f7bb4a5d","last_reissued_at":"2026-07-05T08:32:47.973765Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:47.973765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.11037","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":"2026-07-05T08:32:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X9dlETJeoAF3ysK6L9hU1lWMgsK0psV2/tASa7GJ+bb44W649GFEJYsyeGuj1f47GY97Cmuu8UElQeRvrq9TDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:04:08.884675Z"},"content_sha256":"e6188999a4de5afbfb2dfbd361273a03429d2ac3e859273e7cdccd6fd15f38bf","schema_version":"1.0","event_id":"sha256:e6188999a4de5afbfb2dfbd361273a03429d2ac3e859273e7cdccd6fd15f38bf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3S6VQLWYOXUDBCZIDQINDHLNCO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NAST: Noise Aware Speech Tokenization for Speech Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Shoval Messica, Yossi Adi","submitted_at":"2024-06-16T18:20:45Z","abstract_excerpt":"Speech tokenization is the task of representing speech signals as a sequence of discrete units. Such representations can be later used for various downstream tasks including automatic speech recognition, text-to-speech, etc. More relevant to this study, such representation serves as the basis of Speech Language Models. In this work, we tackle the task of speech tokenization under the noisy setup and present NAST: Noise Aware Speech Tokenization for Speech Language Models. NAST is composed of three main components: (i) a predictor; (ii) a residual encoder; and (iii) a decoder. We evaluate the e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11037","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/2406.11037/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":"2026-07-05T08:32:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iB5uJuKBtfAqxYa3dUZJ5L/p0LrhsHwWvNvMp3UtB7IaXvkHsMTlB4jZfntKYYNuZ07e5P5PJiXhl7pWi3gXCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:04:08.885189Z"},"content_sha256":"475d967a5d69b4cfb8e40a222bbb27bdcb1056ec631f88491063865026c228b3","schema_version":"1.0","event_id":"sha256:475d967a5d69b4cfb8e40a222bbb27bdcb1056ec631f88491063865026c228b3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3S6VQLWYOXUDBCZIDQINDHLNCO/bundle.json","state_url":"https://pith.science/pith/3S6VQLWYOXUDBCZIDQINDHLNCO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3S6VQLWYOXUDBCZIDQINDHLNCO/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":"2026-08-08T20:04:08Z","links":{"resolver":"https://pith.science/pith/3S6VQLWYOXUDBCZIDQINDHLNCO","bundle":"https://pith.science/pith/3S6VQLWYOXUDBCZIDQINDHLNCO/bundle.json","state":"https://pith.science/pith/3S6VQLWYOXUDBCZIDQINDHLNCO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3S6VQLWYOXUDBCZIDQINDHLNCO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3S6VQLWYOXUDBCZIDQINDHLNCO","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":"438f837d18ca49aeb6e671dea9e47e5fda031857df29fc38872bd64aa366b54e","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-16T18:20:45Z","title_canon_sha256":"449cdea13861919621f59d1cb6c5000cb3e41106a8a90dd5759cb53c71e9ac8a"},"schema_version":"1.0","source":{"id":"2406.11037","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11037","created_at":"2026-07-05T08:32:47Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11037v1","created_at":"2026-07-05T08:32:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11037","created_at":"2026-07-05T08:32:47Z"},{"alias_kind":"pith_short_12","alias_value":"3S6VQLWYOXUD","created_at":"2026-07-05T08:32:47Z"},{"alias_kind":"pith_short_16","alias_value":"3S6VQLWYOXUDBCZI","created_at":"2026-07-05T08:32:47Z"},{"alias_kind":"pith_short_8","alias_value":"3S6VQLWY","created_at":"2026-07-05T08:32:47Z"}],"graph_snapshots":[{"event_id":"sha256:475d967a5d69b4cfb8e40a222bbb27bdcb1056ec631f88491063865026c228b3","target":"graph","created_at":"2026-07-05T08:32:47Z","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/2406.11037/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech tokenization is the task of representing speech signals as a sequence of discrete units. Such representations can be later used for various downstream tasks including automatic speech recognition, text-to-speech, etc. More relevant to this study, such representation serves as the basis of Speech Language Models. In this work, we tackle the task of speech tokenization under the noisy setup and present NAST: Noise Aware Speech Tokenization for Speech Language Models. NAST is composed of three main components: (i) a predictor; (ii) a residual encoder; and (iii) a decoder. We evaluate the e","authors_text":"Shoval Messica, Yossi Adi","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-16T18:20:45Z","title":"NAST: Noise Aware Speech Tokenization for Speech Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11037","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:e6188999a4de5afbfb2dfbd361273a03429d2ac3e859273e7cdccd6fd15f38bf","target":"record","created_at":"2026-07-05T08:32:47Z","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":"438f837d18ca49aeb6e671dea9e47e5fda031857df29fc38872bd64aa366b54e","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-16T18:20:45Z","title_canon_sha256":"449cdea13861919621f59d1cb6c5000cb3e41106a8a90dd5759cb53c71e9ac8a"},"schema_version":"1.0","source":{"id":"2406.11037","kind":"arxiv","version":1}},"canonical_sha256":"dcbd582ed875e8308b281c10d19d6d1383b352a94e4a24ccdcce1709f7bb4a5d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dcbd582ed875e8308b281c10d19d6d1383b352a94e4a24ccdcce1709f7bb4a5d","first_computed_at":"2026-07-05T08:32:47.973765Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:47.973765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tZEcYC2UpiRcx/3xbDDU5efAe0CIW2Hx5INHvm3xHni6aZahpd4qDQCmZV954eQ2tHpq89UmOtuB1TJvy+E5CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:47.974219Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11037","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e6188999a4de5afbfb2dfbd361273a03429d2ac3e859273e7cdccd6fd15f38bf","sha256:475d967a5d69b4cfb8e40a222bbb27bdcb1056ec631f88491063865026c228b3"],"state_sha256":"d06b7b36c6063a4d2d5381ef48ff007821ebd792d249d62f89885cb018379322"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q4FsI0y/0nBVIjeEikwYFXHEe9GGzN1pmCXIpa8CSRT+r4Huf215F/NPwWiks84el4ygemxIIh1wpBdz2VtyCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:04:08.888543Z","bundle_sha256":"3e04fa6c1eb2333d84042e92c0dd3ad94842ce7e1a114ef5330aa47d8f5315f8"}}