{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CPZOMSG4QH4EPHKJEW5PCRLDIH","short_pith_number":"pith:CPZOMSG4","canonical_record":{"source":{"id":"2406.10735","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-15T20:43:07Z","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"title_canon_sha256":"d99b7d5218b5c2c6f0b9395fd5e2c7cd6b6a3019c42d1dbb72b23066df16a669","abstract_canon_sha256":"9269a8813786192b55b4f615699901d0936fa3d4d05c48fa827990bce91cfde1"},"schema_version":"1.0"},"canonical_sha256":"13f2e648dc81f8479d4925baf1456341d48fb1dc09ac6aa75211c28ff1f0fe08","source":{"kind":"arxiv","id":"2406.10735","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10735","created_at":"2026-07-05T08:32:21Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10735v1","created_at":"2026-07-05T08:32:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10735","created_at":"2026-07-05T08:32:21Z"},{"alias_kind":"pith_short_12","alias_value":"CPZOMSG4QH4E","created_at":"2026-07-05T08:32:21Z"},{"alias_kind":"pith_short_16","alias_value":"CPZOMSG4QH4EPHKJ","created_at":"2026-07-05T08:32:21Z"},{"alias_kind":"pith_short_8","alias_value":"CPZOMSG4","created_at":"2026-07-05T08:32:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CPZOMSG4QH4EPHKJEW5PCRLDIH","target":"record","payload":{"canonical_record":{"source":{"id":"2406.10735","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-15T20:43:07Z","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"title_canon_sha256":"d99b7d5218b5c2c6f0b9395fd5e2c7cd6b6a3019c42d1dbb72b23066df16a669","abstract_canon_sha256":"9269a8813786192b55b4f615699901d0936fa3d4d05c48fa827990bce91cfde1"},"schema_version":"1.0"},"canonical_sha256":"13f2e648dc81f8479d4925baf1456341d48fb1dc09ac6aa75211c28ff1f0fe08","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:21.294664Z","signature_b64":"3kTkXzzQofgB+UhW2AYaLIUbgIh0LhuJbCRBdibuo9E7IjFYNFIsbtwWXerPD4iG66TJdBF0BtIzUl8KrjmzCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13f2e648dc81f8479d4925baf1456341d48fb1dc09ac6aa75211c28ff1f0fe08","last_reissued_at":"2026-07-05T08:32:21.294183Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:21.294183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.10735","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":"2026-07-05T08:32:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lQTc7qj04brPKcQhUiK6xN7nL7phiROo77P0ym2cfT12yvY4/G5PRqf6KMevGcdh9sEiS8sEyRi4wPrUqBGCDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T01:46:49.275489Z"},"content_sha256":"4c46cff26659fe5930722f252a6734bb5cdce2ffb8aca361af17f2ef98351248","schema_version":"1.0","event_id":"sha256:4c46cff26659fe5930722f252a6734bb5cdce2ffb8aca361af17f2ef98351248"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CPZOMSG4QH4EPHKJEW5PCRLDIH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How Should We Extract Discrete Audio Tokens from Self-Supervised Models?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Artem Ploujnikov, Cem Subakan, Jarod Duret, Luca Della Libera, Mirco Ravanelli, Pooneh Mousavi, Salah Zaiem","submitted_at":"2024-06-15T20:43:07Z","abstract_excerpt":"Discrete audio tokens have recently gained attention for their potential to bridge the gap between audio and language processing. Ideal audio tokens must preserve content, paralinguistic elements, speaker identity, and many other audio details. Current audio tokenization methods fall into two categories: Semantic tokens, acquired through quantization of Self-Supervised Learning (SSL) models, and Neural compression-based tokens (codecs). Although previous studies have benchmarked codec models to identify optimal configurations, the ideal setup for quantizing pretrained SSL models remains unclea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10735","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/2406.10735/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":"2026-07-05T08:32:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PtfonK6kT5TklmZUxjV24Oz2+blBn0+yXhUZV7jBNcPFxa1BncXa8atL1biXl3ZoxILa8d+r6q5zXJiMAe7fCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T01:46:49.276535Z"},"content_sha256":"b53b42e95c3161eb1ad964cc022e86a356e2ee94de1497988c31ed5893d50fd6","schema_version":"1.0","event_id":"sha256:b53b42e95c3161eb1ad964cc022e86a356e2ee94de1497988c31ed5893d50fd6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CPZOMSG4QH4EPHKJEW5PCRLDIH/bundle.json","state_url":"https://pith.science/pith/CPZOMSG4QH4EPHKJEW5PCRLDIH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CPZOMSG4QH4EPHKJEW5PCRLDIH/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":"2026-08-22T01:46:49Z","links":{"resolver":"https://pith.science/pith/CPZOMSG4QH4EPHKJEW5PCRLDIH","bundle":"https://pith.science/pith/CPZOMSG4QH4EPHKJEW5PCRLDIH/bundle.json","state":"https://pith.science/pith/CPZOMSG4QH4EPHKJEW5PCRLDIH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CPZOMSG4QH4EPHKJEW5PCRLDIH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CPZOMSG4QH4EPHKJEW5PCRLDIH","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":"9269a8813786192b55b4f615699901d0936fa3d4d05c48fa827990bce91cfde1","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-15T20:43:07Z","title_canon_sha256":"d99b7d5218b5c2c6f0b9395fd5e2c7cd6b6a3019c42d1dbb72b23066df16a669"},"schema_version":"1.0","source":{"id":"2406.10735","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10735","created_at":"2026-07-05T08:32:21Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10735v1","created_at":"2026-07-05T08:32:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10735","created_at":"2026-07-05T08:32:21Z"},{"alias_kind":"pith_short_12","alias_value":"CPZOMSG4QH4E","created_at":"2026-07-05T08:32:21Z"},{"alias_kind":"pith_short_16","alias_value":"CPZOMSG4QH4EPHKJ","created_at":"2026-07-05T08:32:21Z"},{"alias_kind":"pith_short_8","alias_value":"CPZOMSG4","created_at":"2026-07-05T08:32:21Z"}],"graph_snapshots":[{"event_id":"sha256:b53b42e95c3161eb1ad964cc022e86a356e2ee94de1497988c31ed5893d50fd6","target":"graph","created_at":"2026-07-05T08:32:21Z","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/2406.10735/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Discrete audio tokens have recently gained attention for their potential to bridge the gap between audio and language processing. Ideal audio tokens must preserve content, paralinguistic elements, speaker identity, and many other audio details. Current audio tokenization methods fall into two categories: Semantic tokens, acquired through quantization of Self-Supervised Learning (SSL) models, and Neural compression-based tokens (codecs). Although previous studies have benchmarked codec models to identify optimal configurations, the ideal setup for quantizing pretrained SSL models remains unclea","authors_text":"Artem Ploujnikov, Cem Subakan, Jarod Duret, Luca Della Libera, Mirco Ravanelli, Pooneh Mousavi, Salah Zaiem","cross_cats":["cs.AI","cs.CL","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-15T20:43:07Z","title":"How Should We Extract Discrete Audio Tokens from Self-Supervised Models?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10735","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":"sha256:4c46cff26659fe5930722f252a6734bb5cdce2ffb8aca361af17f2ef98351248","target":"record","created_at":"2026-07-05T08:32:21Z","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":"9269a8813786192b55b4f615699901d0936fa3d4d05c48fa827990bce91cfde1","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-15T20:43:07Z","title_canon_sha256":"d99b7d5218b5c2c6f0b9395fd5e2c7cd6b6a3019c42d1dbb72b23066df16a669"},"schema_version":"1.0","source":{"id":"2406.10735","kind":"arxiv","version":1}},"canonical_sha256":"13f2e648dc81f8479d4925baf1456341d48fb1dc09ac6aa75211c28ff1f0fe08","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"13f2e648dc81f8479d4925baf1456341d48fb1dc09ac6aa75211c28ff1f0fe08","first_computed_at":"2026-07-05T08:32:21.294183Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:21.294183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3kTkXzzQofgB+UhW2AYaLIUbgIh0LhuJbCRBdibuo9E7IjFYNFIsbtwWXerPD4iG66TJdBF0BtIzUl8KrjmzCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:21.294664Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.10735","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c46cff26659fe5930722f252a6734bb5cdce2ffb8aca361af17f2ef98351248","sha256:b53b42e95c3161eb1ad964cc022e86a356e2ee94de1497988c31ed5893d50fd6"],"state_sha256":"d7cda478da8fef6d6d31181228b2be72d35f7b69beba2ea879762509b0a8060b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HzizpLl1DlpWhNjNd9h1HonokVLBFXEQgdsccoSRjc+gxenS7DE5FcmJjPbngvGFWKVAbl7Wduyld3br8UT1Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T01:46:49.282648Z","bundle_sha256":"930b3bbb919c341edee7808033ca7992a02d70f2f9660485bdd06f0d56860da5"}}