{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:G5TAHVFRLEUHWG2TSIKOQSUCOT","short_pith_number":"pith:G5TAHVFR","canonical_record":{"source":{"id":"2409.02565","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-04T09:31:58Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"f3da693462886b187352953384f60783b34dee5d7f4bb199a3dc9ce96a18c559","abstract_canon_sha256":"0c9a7addf3bb5b80d40b1cf333e7745174a72b464fb7a1081354a12341c9f411"},"schema_version":"1.0"},"canonical_sha256":"376603d4b159287b1b539214e84a8274ebcb5073eb3870f489e0d4d87ddf3936","source":{"kind":"arxiv","id":"2409.02565","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.02565","created_at":"2026-07-05T10:09:47Z"},{"alias_kind":"arxiv_version","alias_value":"2409.02565v1","created_at":"2026-07-05T10:09:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.02565","created_at":"2026-07-05T10:09:47Z"},{"alias_kind":"pith_short_12","alias_value":"G5TAHVFRLEUH","created_at":"2026-07-05T10:09:47Z"},{"alias_kind":"pith_short_16","alias_value":"G5TAHVFRLEUHWG2T","created_at":"2026-07-05T10:09:47Z"},{"alias_kind":"pith_short_8","alias_value":"G5TAHVFR","created_at":"2026-07-05T10:09:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:G5TAHVFRLEUHWG2TSIKOQSUCOT","target":"record","payload":{"canonical_record":{"source":{"id":"2409.02565","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-04T09:31:58Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"f3da693462886b187352953384f60783b34dee5d7f4bb199a3dc9ce96a18c559","abstract_canon_sha256":"0c9a7addf3bb5b80d40b1cf333e7745174a72b464fb7a1081354a12341c9f411"},"schema_version":"1.0"},"canonical_sha256":"376603d4b159287b1b539214e84a8274ebcb5073eb3870f489e0d4d87ddf3936","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:47.232830Z","signature_b64":"uQQayh7t0D2Z/3fI2zNqWGlyB5uTwmUjTUDIUjC2JAQkojscSa6q5DHiV7ICWfMRqw8+Bn8DdUBO8mqZjbSJDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"376603d4b159287b1b539214e84a8274ebcb5073eb3870f489e0d4d87ddf3936","last_reissued_at":"2026-07-05T10:09:47.232365Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:47.232365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.02565","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":"2026-07-05T10:09:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BjmKwEDSjpAnPDWa1XK7dqoopfN0McOBgqKRB5k6MA2wabKEN+pHxGDv61UI86iv1pU/xOt+Wv4a9L5OWaLJDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T15:39:27.385703Z"},"content_sha256":"2816f925c7487da29ea1d332a7996fbd6cf572a4bf173cd828ddac48eb3374d6","schema_version":"1.0","event_id":"sha256:2816f925c7487da29ea1d332a7996fbd6cf572a4bf173cd828ddac48eb3374d6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:G5TAHVFRLEUHWG2TSIKOQSUCOT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Extraction of Noise-Robust Discrete Units from Self-Supervised Speech Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Hugo Van hamme, Jakob Poncelet, Yujun Wang","submitted_at":"2024-09-04T09:31:58Z","abstract_excerpt":"Continuous speech can be converted into a discrete sequence by deriving discrete units from the hidden features of self-supervised learned (SSL) speech models. Although SSL models are becoming larger and trained on more data, they are often sensitive to real-life distortions like additive noise or reverberation, which translates to a shift in discrete units. We propose a parameter-efficient approach to generate noise-robust discrete units from pre-trained SSL models by training a small encoder-decoder model, with or without adapters, to simultaneously denoise and discretise the hidden features"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.02565","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/2409.02565/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":"2026-07-05T10:09:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3xJn1HaDeZszKL5EH2rSish+wHeSZcXmpBkBgfsXtx3ZEBXVtMMrbXV1ykvnPr/BZF698Pntm3FlTZw44IdhBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T15:39:27.386230Z"},"content_sha256":"d5e396d3913484a3503dd013cfec1a816b277d9b742d240e241e6f865af54816","schema_version":"1.0","event_id":"sha256:d5e396d3913484a3503dd013cfec1a816b277d9b742d240e241e6f865af54816"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G5TAHVFRLEUHWG2TSIKOQSUCOT/bundle.json","state_url":"https://pith.science/pith/G5TAHVFRLEUHWG2TSIKOQSUCOT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G5TAHVFRLEUHWG2TSIKOQSUCOT/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":"2026-08-14T15:39:27Z","links":{"resolver":"https://pith.science/pith/G5TAHVFRLEUHWG2TSIKOQSUCOT","bundle":"https://pith.science/pith/G5TAHVFRLEUHWG2TSIKOQSUCOT/bundle.json","state":"https://pith.science/pith/G5TAHVFRLEUHWG2TSIKOQSUCOT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G5TAHVFRLEUHWG2TSIKOQSUCOT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:G5TAHVFRLEUHWG2TSIKOQSUCOT","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":"0c9a7addf3bb5b80d40b1cf333e7745174a72b464fb7a1081354a12341c9f411","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-04T09:31:58Z","title_canon_sha256":"f3da693462886b187352953384f60783b34dee5d7f4bb199a3dc9ce96a18c559"},"schema_version":"1.0","source":{"id":"2409.02565","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.02565","created_at":"2026-07-05T10:09:47Z"},{"alias_kind":"arxiv_version","alias_value":"2409.02565v1","created_at":"2026-07-05T10:09:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.02565","created_at":"2026-07-05T10:09:47Z"},{"alias_kind":"pith_short_12","alias_value":"G5TAHVFRLEUH","created_at":"2026-07-05T10:09:47Z"},{"alias_kind":"pith_short_16","alias_value":"G5TAHVFRLEUHWG2T","created_at":"2026-07-05T10:09:47Z"},{"alias_kind":"pith_short_8","alias_value":"G5TAHVFR","created_at":"2026-07-05T10:09:47Z"}],"graph_snapshots":[{"event_id":"sha256:d5e396d3913484a3503dd013cfec1a816b277d9b742d240e241e6f865af54816","target":"graph","created_at":"2026-07-05T10:09:47Z","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/2409.02565/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Continuous speech can be converted into a discrete sequence by deriving discrete units from the hidden features of self-supervised learned (SSL) speech models. Although SSL models are becoming larger and trained on more data, they are often sensitive to real-life distortions like additive noise or reverberation, which translates to a shift in discrete units. We propose a parameter-efficient approach to generate noise-robust discrete units from pre-trained SSL models by training a small encoder-decoder model, with or without adapters, to simultaneously denoise and discretise the hidden features","authors_text":"Hugo Van hamme, Jakob Poncelet, Yujun Wang","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-04T09:31:58Z","title":"Efficient Extraction of Noise-Robust Discrete Units from Self-Supervised Speech Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.02565","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":"sha256:2816f925c7487da29ea1d332a7996fbd6cf572a4bf173cd828ddac48eb3374d6","target":"record","created_at":"2026-07-05T10:09:47Z","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":"0c9a7addf3bb5b80d40b1cf333e7745174a72b464fb7a1081354a12341c9f411","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-04T09:31:58Z","title_canon_sha256":"f3da693462886b187352953384f60783b34dee5d7f4bb199a3dc9ce96a18c559"},"schema_version":"1.0","source":{"id":"2409.02565","kind":"arxiv","version":1}},"canonical_sha256":"376603d4b159287b1b539214e84a8274ebcb5073eb3870f489e0d4d87ddf3936","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"376603d4b159287b1b539214e84a8274ebcb5073eb3870f489e0d4d87ddf3936","first_computed_at":"2026-07-05T10:09:47.232365Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:47.232365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uQQayh7t0D2Z/3fI2zNqWGlyB5uTwmUjTUDIUjC2JAQkojscSa6q5DHiV7ICWfMRqw8+Bn8DdUBO8mqZjbSJDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:47.232830Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.02565","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2816f925c7487da29ea1d332a7996fbd6cf572a4bf173cd828ddac48eb3374d6","sha256:d5e396d3913484a3503dd013cfec1a816b277d9b742d240e241e6f865af54816"],"state_sha256":"6b160a49f9cd7f7815c72d0e52ee00b1463d77421c9acd15980d10872e16e3d2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"da218+c3LXW6YraazbpXR5mHRylLT4PDrSFcdndu5k62B1h0LLD3a6PmJOVkV8akIVOapruBtMwtLTVuladbBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T15:39:27.390406Z","bundle_sha256":"c5945f6a4960b89dec48f329f82464c81a67e299ee2ea4a74b378e5b525fe66e"}}