{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7XL7WKHPUZ7OYDEOGJK7C4O5IF","short_pith_number":"pith:7XL7WKHP","canonical_record":{"source":{"id":"2410.24177","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-10-31T17:43:13Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"246c7108d31b2c3e865e0ad6652870971fa54d001137ba49fd5cf8b21e210058","abstract_canon_sha256":"78fafe175b5051e6f3c58b1ae580d4e932cb57ecf756d2379bf1ea5e245f12b3"},"schema_version":"1.0"},"canonical_sha256":"fdd7fb28efa67eec0c8e3255f171dd4169d7ef9423a624bcd420c912643bd10a","source":{"kind":"arxiv","id":"2410.24177","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.24177","created_at":"2026-07-05T09:29:20Z"},{"alias_kind":"arxiv_version","alias_value":"2410.24177v1","created_at":"2026-07-05T09:29:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.24177","created_at":"2026-07-05T09:29:20Z"},{"alias_kind":"pith_short_12","alias_value":"7XL7WKHPUZ7O","created_at":"2026-07-05T09:29:20Z"},{"alias_kind":"pith_short_16","alias_value":"7XL7WKHPUZ7OYDEO","created_at":"2026-07-05T09:29:20Z"},{"alias_kind":"pith_short_8","alias_value":"7XL7WKHP","created_at":"2026-07-05T09:29:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7XL7WKHPUZ7OYDEOGJK7C4O5IF","target":"record","payload":{"canonical_record":{"source":{"id":"2410.24177","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-10-31T17:43:13Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"246c7108d31b2c3e865e0ad6652870971fa54d001137ba49fd5cf8b21e210058","abstract_canon_sha256":"78fafe175b5051e6f3c58b1ae580d4e932cb57ecf756d2379bf1ea5e245f12b3"},"schema_version":"1.0"},"canonical_sha256":"fdd7fb28efa67eec0c8e3255f171dd4169d7ef9423a624bcd420c912643bd10a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:20.911809Z","signature_b64":"1+NPabbItpI188j1hf984wn+3qR7ciqFuC15TMM/G89CaD339saatT0/N7nv9kkdcnHm1heyo3zIN1C3FbG0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdd7fb28efa67eec0c8e3255f171dd4169d7ef9423a624bcd420c912643bd10a","last_reissued_at":"2026-07-05T09:29:20.911285Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:20.911285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.24177","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":"2026-07-05T09:29:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xUdNgMCKuEBHXSRts6M4okYmIV9w77G3xiwqt+7+zgGCiRdIYF8UJcT1JBaDXcYbLwkknvSzCihmE0pbE0FeDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T11:45:51.927237Z"},"content_sha256":"8ba8cbb52e6538cd475f7826e077014f98b35105ef975e309fdbd6b599426d09","schema_version":"1.0","event_id":"sha256:8ba8cbb52e6538cd475f7826e077014f98b35105ef975e309fdbd6b599426d09"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7XL7WKHPUZ7OYDEOGJK7C4O5IF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DC-Spin: A Speaker-invariant Speech Tokenizer for Spoken Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Changhan Wang, Heng-Jui Chang, Hongyu Gong, James Glass, Yu-An Chung","submitted_at":"2024-10-31T17:43:13Z","abstract_excerpt":"Spoken language models (SLMs) have gained increasing attention with advancements in text-based, decoder-only language models. SLMs process text and speech, enabling simultaneous speech understanding and generation. This paper presents Double-Codebook Speaker-invariant Clustering (DC-Spin), which aims to improve speech tokenization by bridging audio signals and SLM tokens. DC-Spin extracts speaker-invariant tokens rich in phonetic information and resilient to input variations, enhancing zero-shot SLM tasks and speech resynthesis. We propose a chunk-wise approach to enable streamable DC-Spin wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.24177","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/2410.24177/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":"2026-07-05T09:29:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b+kIqYAyuSVpjcaJ216egVtBNfpeW3OqwKeQejSjlFQ7y9Ga9LRqR4HGPl4Dmsz3hQ5gX1kCsVGArSvm/MIuCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T11:45:51.927758Z"},"content_sha256":"345d7b5f7f66f3f2538693ec4dedb67198ef117bfcbd0b2e551bdf2d2f136173","schema_version":"1.0","event_id":"sha256:345d7b5f7f66f3f2538693ec4dedb67198ef117bfcbd0b2e551bdf2d2f136173"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7XL7WKHPUZ7OYDEOGJK7C4O5IF/bundle.json","state_url":"https://pith.science/pith/7XL7WKHPUZ7OYDEOGJK7C4O5IF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7XL7WKHPUZ7OYDEOGJK7C4O5IF/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":"2026-08-20T11:45:51Z","links":{"resolver":"https://pith.science/pith/7XL7WKHPUZ7OYDEOGJK7C4O5IF","bundle":"https://pith.science/pith/7XL7WKHPUZ7OYDEOGJK7C4O5IF/bundle.json","state":"https://pith.science/pith/7XL7WKHPUZ7OYDEOGJK7C4O5IF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7XL7WKHPUZ7OYDEOGJK7C4O5IF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7XL7WKHPUZ7OYDEOGJK7C4O5IF","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":"78fafe175b5051e6f3c58b1ae580d4e932cb57ecf756d2379bf1ea5e245f12b3","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-10-31T17:43:13Z","title_canon_sha256":"246c7108d31b2c3e865e0ad6652870971fa54d001137ba49fd5cf8b21e210058"},"schema_version":"1.0","source":{"id":"2410.24177","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.24177","created_at":"2026-07-05T09:29:20Z"},{"alias_kind":"arxiv_version","alias_value":"2410.24177v1","created_at":"2026-07-05T09:29:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.24177","created_at":"2026-07-05T09:29:20Z"},{"alias_kind":"pith_short_12","alias_value":"7XL7WKHPUZ7O","created_at":"2026-07-05T09:29:20Z"},{"alias_kind":"pith_short_16","alias_value":"7XL7WKHPUZ7OYDEO","created_at":"2026-07-05T09:29:20Z"},{"alias_kind":"pith_short_8","alias_value":"7XL7WKHP","created_at":"2026-07-05T09:29:20Z"}],"graph_snapshots":[{"event_id":"sha256:345d7b5f7f66f3f2538693ec4dedb67198ef117bfcbd0b2e551bdf2d2f136173","target":"graph","created_at":"2026-07-05T09:29:20Z","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/2410.24177/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spoken language models (SLMs) have gained increasing attention with advancements in text-based, decoder-only language models. SLMs process text and speech, enabling simultaneous speech understanding and generation. This paper presents Double-Codebook Speaker-invariant Clustering (DC-Spin), which aims to improve speech tokenization by bridging audio signals and SLM tokens. DC-Spin extracts speaker-invariant tokens rich in phonetic information and resilient to input variations, enhancing zero-shot SLM tasks and speech resynthesis. We propose a chunk-wise approach to enable streamable DC-Spin wit","authors_text":"Changhan Wang, Heng-Jui Chang, Hongyu Gong, James Glass, Yu-An Chung","cross_cats":["cs.CL","cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-10-31T17:43:13Z","title":"DC-Spin: A Speaker-invariant Speech Tokenizer for Spoken Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.24177","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":"sha256:8ba8cbb52e6538cd475f7826e077014f98b35105ef975e309fdbd6b599426d09","target":"record","created_at":"2026-07-05T09:29:20Z","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":"78fafe175b5051e6f3c58b1ae580d4e932cb57ecf756d2379bf1ea5e245f12b3","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-10-31T17:43:13Z","title_canon_sha256":"246c7108d31b2c3e865e0ad6652870971fa54d001137ba49fd5cf8b21e210058"},"schema_version":"1.0","source":{"id":"2410.24177","kind":"arxiv","version":1}},"canonical_sha256":"fdd7fb28efa67eec0c8e3255f171dd4169d7ef9423a624bcd420c912643bd10a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fdd7fb28efa67eec0c8e3255f171dd4169d7ef9423a624bcd420c912643bd10a","first_computed_at":"2026-07-05T09:29:20.911285Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:29:20.911285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1+NPabbItpI188j1hf984wn+3qR7ciqFuC15TMM/G89CaD339saatT0/N7nv9kkdcnHm1heyo3zIN1C3FbG0Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:29:20.911809Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.24177","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ba8cbb52e6538cd475f7826e077014f98b35105ef975e309fdbd6b599426d09","sha256:345d7b5f7f66f3f2538693ec4dedb67198ef117bfcbd0b2e551bdf2d2f136173"],"state_sha256":"7cc27a0cbc6d814a45f45fdc6d4279afb978e67f4b13836b28afe50eed6f7838"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2sGQ7zFx/budISzQ1Yo+h9x1bcDwRvT4NiMvKEmwLY6d2nRYdEjQ6uNdDL5nfpIvrCnfCEuqkb6V+q9w5RbLDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T11:45:51.932561Z","bundle_sha256":"4d3062e3f1ad3ea6a6ae4506a52fe7f1f97ab98da88236fe54312ef44caa7c3b"}}