{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GGD75DDZTF24GHQ3ALY2GNSGRM","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":"fd8ffbf1a08b785005d4bcc4802f4ba78dd6169bf9b45787fe03012f9f8497a5","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-10-04T10:52:13Z","title_canon_sha256":"fa8fdde89d22d45c47e64f029f98683901f962e5669e057dee94dc3d3b06577e"},"schema_version":"1.0","source":{"id":"2310.02720","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.02720","created_at":"2026-07-05T07:38:52Z"},{"alias_kind":"arxiv_version","alias_value":"2310.02720v2","created_at":"2026-07-05T07:38:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02720","created_at":"2026-07-05T07:38:52Z"},{"alias_kind":"pith_short_12","alias_value":"GGD75DDZTF24","created_at":"2026-07-05T07:38:52Z"},{"alias_kind":"pith_short_16","alias_value":"GGD75DDZTF24GHQ3","created_at":"2026-07-05T07:38:52Z"},{"alias_kind":"pith_short_8","alias_value":"GGD75DDZ","created_at":"2026-07-05T07:38:52Z"}],"graph_snapshots":[{"event_id":"sha256:a8b4b214db173b287e27dbabb9cb786aff640314d69a12ad879776e5c2dada7c","target":"graph","created_at":"2026-07-05T07:38:52Z","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/2310.02720/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing Self-Supervised Learning (SSL) models for speech typically process speech signals at a fixed resolution of 20 milliseconds. This approach overlooks the varying informational content present at different resolutions in speech signals. In contrast, this paper aims to incorporate multi-resolution information into speech self-supervised representation learning. We introduce a SSL model that leverages a hierarchical Transformer architecture, complemented by HuBERT-style masked prediction objectives, to process speech at multiple resolutions. Experimental results indicate that the proposed ","authors_text":"Anna Sun, Hirofumi Inaguma, Ilia Kulikov, Jiatong Shi, Xutai Ma","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-10-04T10:52:13Z","title":"Multi-resolution HuBERT: Multi-resolution Speech Self-Supervised Learning with Masked Unit Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02720","kind":"arxiv","version":2},"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":"sha256:622bb66d1118288cf702952c3d477b1fcd14f238b22598ad497fe9b70f435bd8","target":"record","created_at":"2026-07-05T07:38:52Z","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":"fd8ffbf1a08b785005d4bcc4802f4ba78dd6169bf9b45787fe03012f9f8497a5","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-10-04T10:52:13Z","title_canon_sha256":"fa8fdde89d22d45c47e64f029f98683901f962e5669e057dee94dc3d3b06577e"},"schema_version":"1.0","source":{"id":"2310.02720","kind":"arxiv","version":2}},"canonical_sha256":"3187fe8c799975c31e1b02f1a336468b04a5de88eb008e40c8f6069ce9e38c42","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3187fe8c799975c31e1b02f1a336468b04a5de88eb008e40c8f6069ce9e38c42","first_computed_at":"2026-07-05T07:38:52.723292Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:38:52.723292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y4NBENUwM9I5SouHwomhVpIWZVD8IdeIwHeYdrmD2xeQqzGRiqrraCUegYELd8GCBAp0Zd0RguKj3j8IwJljDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:38:52.723857Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.02720","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:622bb66d1118288cf702952c3d477b1fcd14f238b22598ad497fe9b70f435bd8","sha256:a8b4b214db173b287e27dbabb9cb786aff640314d69a12ad879776e5c2dada7c"],"state_sha256":"2107ca5f84edfd80b34f438a314b88c8a78dc011fb4e187db620c5c05c606e91"}