{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:B4QKLSTUFRPCTORJJIQEATVNEC","short_pith_number":"pith:B4QKLSTU","canonical_record":{"source":{"id":"2606.04418","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-03T03:56:14Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"011101bf421dc040bfcfe5b77c9c0da51b5142ae1cd6dc5863fc43d7e44b690d","abstract_canon_sha256":"15f742f7f7634e63de1b05483ff235b406a4d9724fd83a2e8271ccf0f066de39"},"schema_version":"1.0"},"canonical_sha256":"0f20a5ca742c5e29ba294a20404ead20b66a9b5b7fab216a3f9f90f2dbee7b29","source":{"kind":"arxiv","id":"2606.04418","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04418","created_at":"2026-06-04T01:09:07Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04418v1","created_at":"2026-06-04T01:09:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04418","created_at":"2026-06-04T01:09:07Z"},{"alias_kind":"pith_short_12","alias_value":"B4QKLSTUFRPC","created_at":"2026-06-04T01:09:07Z"},{"alias_kind":"pith_short_16","alias_value":"B4QKLSTUFRPCTORJ","created_at":"2026-06-04T01:09:07Z"},{"alias_kind":"pith_short_8","alias_value":"B4QKLSTU","created_at":"2026-06-04T01:09:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:B4QKLSTUFRPCTORJJIQEATVNEC","target":"record","payload":{"canonical_record":{"source":{"id":"2606.04418","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-03T03:56:14Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"011101bf421dc040bfcfe5b77c9c0da51b5142ae1cd6dc5863fc43d7e44b690d","abstract_canon_sha256":"15f742f7f7634e63de1b05483ff235b406a4d9724fd83a2e8271ccf0f066de39"},"schema_version":"1.0"},"canonical_sha256":"0f20a5ca742c5e29ba294a20404ead20b66a9b5b7fab216a3f9f90f2dbee7b29","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:07.387661Z","signature_b64":"Yv1mpJeJGbKpIWYxMtBpqMewxkpHz6+wrC+oXDg/RiTO6DVhuYUtoQ5x4I5ZpVXwr99IbMhonoZmdKDWEDjmBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f20a5ca742c5e29ba294a20404ead20b66a9b5b7fab216a3f9f90f2dbee7b29","last_reissued_at":"2026-06-04T01:09:07.387185Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:07.387185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.04418","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":"2026-06-04T01:09:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1th6YIHwKsnylXBvsFiTS9sQjhKuFgfOl6TBjlsqBe96ygb+J0mg3LnDUCD/12FJW/claI0cOTFwV1pm6ahhCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T08:12:54.143406Z"},"content_sha256":"e2392546e2c7137026b2cf62006314ac67581cd4d96cbae43f73fa9cc50fbe28","schema_version":"1.0","event_id":"sha256:e2392546e2c7137026b2cf62006314ac67581cd4d96cbae43f73fa9cc50fbe28"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:B4QKLSTUFRPCTORJJIQEATVNEC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CleanCodec: Efficient and Robust Speech Tokenization via Perceptually Guided Encoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Eugene Kwek, Feng Liu, Rui Zhang, Wenpeng Yin","submitted_at":"2026-06-03T03:56:14Z","abstract_excerpt":"Neural audio codecs are a key component of speech processing pipelines, compressing audio into discrete tokens for downstream modeling. However, existing codecs struggle to balance reconstruction quality with token efficiency, often encoding perceptually irrelevant information such as background noise and recording artifacts at the expense of linguistically and acoustically meaningful content. We reframe audio tokenization as a selective information bottleneck problem and propose CleanCodec, a denoising audio codec which learns to encode only perceptually important features and discard imperce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04418","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/2606.04418/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":"2026-06-04T01:09:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k+gBYDw1IPFxVCDkOxxO0x3pWjT0BQf+afCd65wf62Ch5brlLk0osU/Eavp0e8ze0aPN6dgkanXKsyACLyjECQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T08:12:54.143779Z"},"content_sha256":"5bdf2d67b846b5b3f432c6a4702f7e234552be68c46833adff18169ac2c0037e","schema_version":"1.0","event_id":"sha256:5bdf2d67b846b5b3f432c6a4702f7e234552be68c46833adff18169ac2c0037e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B4QKLSTUFRPCTORJJIQEATVNEC/bundle.json","state_url":"https://pith.science/pith/B4QKLSTUFRPCTORJJIQEATVNEC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B4QKLSTUFRPCTORJJIQEATVNEC/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":"2026-06-29T08:12:54Z","links":{"resolver":"https://pith.science/pith/B4QKLSTUFRPCTORJJIQEATVNEC","bundle":"https://pith.science/pith/B4QKLSTUFRPCTORJJIQEATVNEC/bundle.json","state":"https://pith.science/pith/B4QKLSTUFRPCTORJJIQEATVNEC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B4QKLSTUFRPCTORJJIQEATVNEC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:B4QKLSTUFRPCTORJJIQEATVNEC","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":"15f742f7f7634e63de1b05483ff235b406a4d9724fd83a2e8271ccf0f066de39","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-03T03:56:14Z","title_canon_sha256":"011101bf421dc040bfcfe5b77c9c0da51b5142ae1cd6dc5863fc43d7e44b690d"},"schema_version":"1.0","source":{"id":"2606.04418","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04418","created_at":"2026-06-04T01:09:07Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04418v1","created_at":"2026-06-04T01:09:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04418","created_at":"2026-06-04T01:09:07Z"},{"alias_kind":"pith_short_12","alias_value":"B4QKLSTUFRPC","created_at":"2026-06-04T01:09:07Z"},{"alias_kind":"pith_short_16","alias_value":"B4QKLSTUFRPCTORJ","created_at":"2026-06-04T01:09:07Z"},{"alias_kind":"pith_short_8","alias_value":"B4QKLSTU","created_at":"2026-06-04T01:09:07Z"}],"graph_snapshots":[{"event_id":"sha256:5bdf2d67b846b5b3f432c6a4702f7e234552be68c46833adff18169ac2c0037e","target":"graph","created_at":"2026-06-04T01:09:07Z","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/2606.04418/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural audio codecs are a key component of speech processing pipelines, compressing audio into discrete tokens for downstream modeling. However, existing codecs struggle to balance reconstruction quality with token efficiency, often encoding perceptually irrelevant information such as background noise and recording artifacts at the expense of linguistically and acoustically meaningful content. We reframe audio tokenization as a selective information bottleneck problem and propose CleanCodec, a denoising audio codec which learns to encode only perceptually important features and discard imperce","authors_text":"Eugene Kwek, Feng Liu, Rui Zhang, Wenpeng Yin","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-03T03:56:14Z","title":"CleanCodec: Efficient and Robust Speech Tokenization via Perceptually Guided Encoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04418","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:e2392546e2c7137026b2cf62006314ac67581cd4d96cbae43f73fa9cc50fbe28","target":"record","created_at":"2026-06-04T01:09:07Z","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":"15f742f7f7634e63de1b05483ff235b406a4d9724fd83a2e8271ccf0f066de39","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-03T03:56:14Z","title_canon_sha256":"011101bf421dc040bfcfe5b77c9c0da51b5142ae1cd6dc5863fc43d7e44b690d"},"schema_version":"1.0","source":{"id":"2606.04418","kind":"arxiv","version":1}},"canonical_sha256":"0f20a5ca742c5e29ba294a20404ead20b66a9b5b7fab216a3f9f90f2dbee7b29","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f20a5ca742c5e29ba294a20404ead20b66a9b5b7fab216a3f9f90f2dbee7b29","first_computed_at":"2026-06-04T01:09:07.387185Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:09:07.387185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Yv1mpJeJGbKpIWYxMtBpqMewxkpHz6+wrC+oXDg/RiTO6DVhuYUtoQ5x4I5ZpVXwr99IbMhonoZmdKDWEDjmBQ==","signature_status":"signed_v1","signed_at":"2026-06-04T01:09:07.387661Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.04418","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2392546e2c7137026b2cf62006314ac67581cd4d96cbae43f73fa9cc50fbe28","sha256:5bdf2d67b846b5b3f432c6a4702f7e234552be68c46833adff18169ac2c0037e"],"state_sha256":"a432c1ac33971433b54e9c99a43fe1c0a7b3474324463b9c60e3719794ce8133"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U8STldsvlQoYtxAY/xX4tOgpIhjBAh7U4A3+GEogPIe1txVrseryq/sdcwfBpRUsnKs0y+c3+rRXeGMnEBI3Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T08:12:54.149356Z","bundle_sha256":"f4e33df13fc47f7f5a20282835fcc66fa7d905612fe512d6de77c6ace93b1dc9"}}