{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UYW4CVJZNAX64BD2V64UIODLW4","short_pith_number":"pith:UYW4CVJZ","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"},"canonical_sha256":"a62dc15539682fee047aafb944386bb73baca24dd1b679ac19e5a944998901e6","source":{"kind":"arxiv","id":"2411.08742","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.08742","created_at":"2026-07-05T09:35:01Z"},{"alias_kind":"arxiv_version","alias_value":"2411.08742v1","created_at":"2026-07-05T09:35:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.08742","created_at":"2026-07-05T09:35:01Z"},{"alias_kind":"pith_short_12","alias_value":"UYW4CVJZNAX6","created_at":"2026-07-05T09:35:01Z"},{"alias_kind":"pith_short_16","alias_value":"UYW4CVJZNAX64BD2","created_at":"2026-07-05T09:35:01Z"},{"alias_kind":"pith_short_8","alias_value":"UYW4CVJZ","created_at":"2026-07-05T09:35:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UYW4CVJZNAX64BD2V64UIODLW4","target":"record","payload":{"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"},"canonical_sha256":"a62dc15539682fee047aafb944386bb73baca24dd1b679ac19e5a944998901e6","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"},"source_kind":"arxiv","source_id":"2411.08742","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":"2026-07-05T09:35:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oXLR0Cd9DUq1p5LYvf5/xJ+QMMTrhwTgxTzg/1FAiOjcHykKKwyQMR/L9bD2JyUO7KIhCBOYn+S3DW1CaU/FBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:47:27.128280Z"},"content_sha256":"b442a0e345ef3ec834acca170ec5879a8c2582f396028c7a7960e773be9e36a2","schema_version":"1.0","event_id":"sha256:b442a0e345ef3ec834acca170ec5879a8c2582f396028c7a7960e773be9e36a2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UYW4CVJZNAX64BD2V64UIODLW4","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:35:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EY06fKC0zCOZyOC/E1lGd2mGfE0mZUfYfDwiaCL0WxaQX5Rn6qt9xsMSLSV/PtnUMF0HQCUESW6oOEtTrnYdCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:47:27.128874Z"},"content_sha256":"5dbb4a934616ac4a347b0b512f0361d52f4afe639d1ce73fa6fbcb5532a6b8d2","schema_version":"1.0","event_id":"sha256:5dbb4a934616ac4a347b0b512f0361d52f4afe639d1ce73fa6fbcb5532a6b8d2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UYW4CVJZNAX64BD2V64UIODLW4/bundle.json","state_url":"https://pith.science/pith/UYW4CVJZNAX64BD2V64UIODLW4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UYW4CVJZNAX64BD2V64UIODLW4/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":"2026-08-08T22:47:27Z","links":{"resolver":"https://pith.science/pith/UYW4CVJZNAX64BD2V64UIODLW4","bundle":"https://pith.science/pith/UYW4CVJZNAX64BD2V64UIODLW4/bundle.json","state":"https://pith.science/pith/UYW4CVJZNAX64BD2V64UIODLW4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UYW4CVJZNAX64BD2V64UIODLW4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UYW4CVJZNAX64BD2V64UIODLW4","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":"5e249d28a97572e5bbee9940648c2038bde9d41242bd9797f2467f3695287eb9","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-13T16:20:20Z","title_canon_sha256":"2a7e9423aa4a3c5f4f9c1e3d52ef23b659e52188ef471e3acb9307112312e3ae"},"schema_version":"1.0","source":{"id":"2411.08742","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.08742","created_at":"2026-07-05T09:35:01Z"},{"alias_kind":"arxiv_version","alias_value":"2411.08742v1","created_at":"2026-07-05T09:35:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.08742","created_at":"2026-07-05T09:35:01Z"},{"alias_kind":"pith_short_12","alias_value":"UYW4CVJZNAX6","created_at":"2026-07-05T09:35:01Z"},{"alias_kind":"pith_short_16","alias_value":"UYW4CVJZNAX64BD2","created_at":"2026-07-05T09:35:01Z"},{"alias_kind":"pith_short_8","alias_value":"UYW4CVJZ","created_at":"2026-07-05T09:35:01Z"}],"graph_snapshots":[{"event_id":"sha256:5dbb4a934616ac4a347b0b512f0361d52f4afe639d1ce73fa6fbcb5532a6b8d2","target":"graph","created_at":"2026-07-05T09:35:01Z","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/2411.08742/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dingdong Wang, Dongchao Yang, Helen Meng, Mingyu Cui, Xueyuan Chen","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-13T16:20:20Z","title":"A Comparative Study of Discrete Speech Tokens for Semantic-Related Tasks with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.08742","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:b442a0e345ef3ec834acca170ec5879a8c2582f396028c7a7960e773be9e36a2","target":"record","created_at":"2026-07-05T09:35:01Z","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":"5e249d28a97572e5bbee9940648c2038bde9d41242bd9797f2467f3695287eb9","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-13T16:20:20Z","title_canon_sha256":"2a7e9423aa4a3c5f4f9c1e3d52ef23b659e52188ef471e3acb9307112312e3ae"},"schema_version":"1.0","source":{"id":"2411.08742","kind":"arxiv","version":1}},"canonical_sha256":"a62dc15539682fee047aafb944386bb73baca24dd1b679ac19e5a944998901e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a62dc15539682fee047aafb944386bb73baca24dd1b679ac19e5a944998901e6","first_computed_at":"2026-07-05T09:35:01.984438Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:35:01.984438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Kb961KaEAs55hFg8J52jRAQyaMtmtb5UTZdKO7fh6lnOwH0Zl/NWntGm6Ksftu/SAv3tu0lDfUWpzqKlt+UeAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:35:01.984854Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.08742","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b442a0e345ef3ec834acca170ec5879a8c2582f396028c7a7960e773be9e36a2","sha256:5dbb4a934616ac4a347b0b512f0361d52f4afe639d1ce73fa6fbcb5532a6b8d2"],"state_sha256":"56d42932f9304515b118d11a20cae8dfdd99d0725b4fafa68f76d9880bb0816b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TStOsMHgSS5q3dvRt8uG6eJ3LYPxmWgw6RuaOw+sYN8hb3NaLzMovYWikupx87JYTamQE61pP+xyJtof8IAPAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:47:27.132059Z","bundle_sha256":"25da23760798011dba0b652c863d0ba5758f685bffcd4504c2f6267a6ca06b6e"}}