{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UYW4CVJZNAX64BD2V64UIODLW4","short_pith_number":"pith:UYW4CVJZ","schema_version":"1.0","canonical_sha256":"a62dc15539682fee047aafb944386bb73baca24dd1b679ac19e5a944998901e6","source":{"kind":"arxiv","id":"2411.08742","version":1},"attestation_state":"computed","paper":{"title":"A Comparative Study of Discrete Speech Tokens for Semantic-Related Tasks with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Dingdong Wang, Dongchao Yang, Helen Meng, Mingyu Cui, Xueyuan Chen","submitted_at":"2024-11-13T16:20:20Z","abstract_excerpt":"With the rise of Speech Large Language Models (Speech LLMs), there has been growing interest in discrete speech tokens for their ability to integrate with text-based tokens seamlessly. Compared to most studies that focus on continuous speech features, although discrete-token based LLMs have shown promising results on certain tasks, the performance gap between these two paradigms is rarely explored. In this paper, we present a fair and thorough comparison between discrete and continuous features across a variety of semantic-related tasks using a light-weight LLM (Qwen1.5-0.5B). Our findings rev"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2411.08742","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-13T16:20:20Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"2a7e9423aa4a3c5f4f9c1e3d52ef23b659e52188ef471e3acb9307112312e3ae","abstract_canon_sha256":"5e249d28a97572e5bbee9940648c2038bde9d41242bd9797f2467f3695287eb9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:35:01.984854Z","signature_b64":"Kb961KaEAs55hFg8J52jRAQyaMtmtb5UTZdKO7fh6lnOwH0Zl/NWntGm6Ksftu/SAv3tu0lDfUWpzqKlt+UeAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a62dc15539682fee047aafb944386bb73baca24dd1b679ac19e5a944998901e6","last_reissued_at":"2026-07-05T09:35:01.984438Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:35:01.984438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comparative Study of Discrete Speech Tokens for Semantic-Related Tasks with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Dingdong Wang, Dongchao Yang, Helen Meng, Mingyu Cui, Xueyuan Chen","submitted_at":"2024-11-13T16:20:20Z","abstract_excerpt":"With the rise of Speech Large Language Models (Speech LLMs), there has been growing interest in discrete speech tokens for their ability to integrate with text-based tokens seamlessly. Compared to most studies that focus on continuous speech features, although discrete-token based LLMs have shown promising results on certain tasks, the performance gap between these two paradigms is rarely explored. In this paper, we present a fair and thorough comparison between discrete and continuous features across a variety of semantic-related tasks using a light-weight LLM (Qwen1.5-0.5B). Our findings rev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.08742","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/2411.08742/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.08742","created_at":"2026-07-05T09:35:01.984488+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.08742v1","created_at":"2026-07-05T09:35:01.984488+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.08742","created_at":"2026-07-05T09:35:01.984488+00:00"},{"alias_kind":"pith_short_12","alias_value":"UYW4CVJZNAX6","created_at":"2026-07-05T09:35:01.984488+00:00"},{"alias_kind":"pith_short_16","alias_value":"UYW4CVJZNAX64BD2","created_at":"2026-07-05T09:35:01.984488+00:00"},{"alias_kind":"pith_short_8","alias_value":"UYW4CVJZ","created_at":"2026-07-05T09:35:01.984488+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08962","citing_title":"MegaScale-Omni: A Hyper-Scale, Workload-Resilient System for MultiModal LLM Training in Production","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09332","citing_title":"Phonemes vs. Projectors: An Investigation of Speech-Language Interfaces for LLM-based ASR","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UYW4CVJZNAX64BD2V64UIODLW4","json":"https://pith.science/pith/UYW4CVJZNAX64BD2V64UIODLW4.json","graph_json":"https://pith.science/api/pith-number/UYW4CVJZNAX64BD2V64UIODLW4/graph.json","events_json":"https://pith.science/api/pith-number/UYW4CVJZNAX64BD2V64UIODLW4/events.json","paper":"https://pith.science/paper/UYW4CVJZ"},"agent_actions":{"view_html":"https://pith.science/pith/UYW4CVJZNAX64BD2V64UIODLW4","download_json":"https://pith.science/pith/UYW4CVJZNAX64BD2V64UIODLW4.json","view_paper":"https://pith.science/paper/UYW4CVJZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.08742&json=true","fetch_graph":"https://pith.science/api/pith-number/UYW4CVJZNAX64BD2V64UIODLW4/graph.json","fetch_events":"https://pith.science/api/pith-number/UYW4CVJZNAX64BD2V64UIODLW4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UYW4CVJZNAX64BD2V64UIODLW4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UYW4CVJZNAX64BD2V64UIODLW4/action/storage_attestation","attest_author":"https://pith.science/pith/UYW4CVJZNAX64BD2V64UIODLW4/action/author_attestation","sign_citation":"https://pith.science/pith/UYW4CVJZNAX64BD2V64UIODLW4/action/citation_signature","submit_replication":"https://pith.science/pith/UYW4CVJZNAX64BD2V64UIODLW4/action/replication_record"}},"created_at":"2026-07-05T09:35:01.984488+00:00","updated_at":"2026-07-05T09:35:01.984488+00:00"}