{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:U7QWXXWAOYTAZHGZYH6TUORY6N","short_pith_number":"pith:U7QWXXWA","canonical_record":{"source":{"id":"2402.15725","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-02-24T05:30:23Z","cross_cats_sorted":[],"title_canon_sha256":"1705503c27175c0ed8b55459c6044395a7c778813d2c123d7dd4b7d628d8c5e9","abstract_canon_sha256":"291e10b77e11887ee04858c193b65bdfc2a5e5d94257d252d296077749be1e3c"},"schema_version":"1.0"},"canonical_sha256":"a7e16bdec076260c9cd9c1fd3a3a38f371ec47219896392371f5d969dd22da61","source":{"kind":"arxiv","id":"2402.15725","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15725","created_at":"2026-07-05T08:51:47Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15725v5","created_at":"2026-07-05T08:51:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15725","created_at":"2026-07-05T08:51:47Z"},{"alias_kind":"pith_short_12","alias_value":"U7QWXXWAOYTA","created_at":"2026-07-05T08:51:47Z"},{"alias_kind":"pith_short_16","alias_value":"U7QWXXWAOYTAZHGZ","created_at":"2026-07-05T08:51:47Z"},{"alias_kind":"pith_short_8","alias_value":"U7QWXXWA","created_at":"2026-07-05T08:51:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:U7QWXXWAOYTAZHGZYH6TUORY6N","target":"record","payload":{"canonical_record":{"source":{"id":"2402.15725","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-02-24T05:30:23Z","cross_cats_sorted":[],"title_canon_sha256":"1705503c27175c0ed8b55459c6044395a7c778813d2c123d7dd4b7d628d8c5e9","abstract_canon_sha256":"291e10b77e11887ee04858c193b65bdfc2a5e5d94257d252d296077749be1e3c"},"schema_version":"1.0"},"canonical_sha256":"a7e16bdec076260c9cd9c1fd3a3a38f371ec47219896392371f5d969dd22da61","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:51:47.912943Z","signature_b64":"FJ6O9PPhLZHNbtKChwJLbh6XjICvhnHd4fNeF6mQOr13FKqf/H1liQ5RcT6jKs27pd41dmX6RwTOxQKKFrjOAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7e16bdec076260c9cd9c1fd3a3a38f371ec47219896392371f5d969dd22da61","last_reissued_at":"2026-07-05T08:51:47.912446Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:51:47.912446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.15725","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:51:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1zIaisnIkaw/30PjZul5STSvPTNKDk0FLClMg8Y0Xj7Zt2DbQNnQ/+El/+1qDrEoLmAiS9nDvwuNSy5ayTFHDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T00:59:24.381763Z"},"content_sha256":"987b15f2ba32eb9992a6ccbf9f0b4e6e44465d9bcfa5870519791951611089c9","schema_version":"1.0","event_id":"sha256:987b15f2ba32eb9992a6ccbf9f0b4e6e44465d9bcfa5870519791951611089c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:U7QWXXWAOYTAZHGZYH6TUORY6N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Text-guided HuBERT: Self-Supervised Speech Pre-training via Generative Adversarial Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Duo Ma, Haizhou Li, Junyi Ao, Xianghu Yue, Xiaoxue Gao","submitted_at":"2024-02-24T05:30:23Z","abstract_excerpt":"Human language can be expressed in either written or spoken form, i.e. text or speech. Humans can acquire knowledge from text to improve speaking and listening. However, the quest for speech pre-trained models to leverage unpaired text has just started. In this paper, we investigate a new way to pre-train such a joint speech-text model to learn enhanced speech representations and benefit various speech-related downstream tasks. Specifically, we propose a novel pre-training method, text-guided HuBERT, or T-HuBERT, which performs self-supervised learning over speech to derive phoneme-like discre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15725","kind":"arxiv","version":5},"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/2402.15725/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":"2026-07-05T08:51:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R8r0qTlrKmETiK9NesRGccDHFG2cG86ezoGFJFlaFzsL95uHVSIlCkhKxEV80w8LC61kH3HOkgCf3h127pOFDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T00:59:24.382342Z"},"content_sha256":"7dfe0182b29811e505156f0267eb064d547508789bdb6b1b0080e04bd3c87d4c","schema_version":"1.0","event_id":"sha256:7dfe0182b29811e505156f0267eb064d547508789bdb6b1b0080e04bd3c87d4c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U7QWXXWAOYTAZHGZYH6TUORY6N/bundle.json","state_url":"https://pith.science/pith/U7QWXXWAOYTAZHGZYH6TUORY6N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U7QWXXWAOYTAZHGZYH6TUORY6N/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":"2026-08-21T00:59:24Z","links":{"resolver":"https://pith.science/pith/U7QWXXWAOYTAZHGZYH6TUORY6N","bundle":"https://pith.science/pith/U7QWXXWAOYTAZHGZYH6TUORY6N/bundle.json","state":"https://pith.science/pith/U7QWXXWAOYTAZHGZYH6TUORY6N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U7QWXXWAOYTAZHGZYH6TUORY6N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:U7QWXXWAOYTAZHGZYH6TUORY6N","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":"291e10b77e11887ee04858c193b65bdfc2a5e5d94257d252d296077749be1e3c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-02-24T05:30:23Z","title_canon_sha256":"1705503c27175c0ed8b55459c6044395a7c778813d2c123d7dd4b7d628d8c5e9"},"schema_version":"1.0","source":{"id":"2402.15725","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15725","created_at":"2026-07-05T08:51:47Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15725v5","created_at":"2026-07-05T08:51:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15725","created_at":"2026-07-05T08:51:47Z"},{"alias_kind":"pith_short_12","alias_value":"U7QWXXWAOYTA","created_at":"2026-07-05T08:51:47Z"},{"alias_kind":"pith_short_16","alias_value":"U7QWXXWAOYTAZHGZ","created_at":"2026-07-05T08:51:47Z"},{"alias_kind":"pith_short_8","alias_value":"U7QWXXWA","created_at":"2026-07-05T08:51:47Z"}],"graph_snapshots":[{"event_id":"sha256:7dfe0182b29811e505156f0267eb064d547508789bdb6b1b0080e04bd3c87d4c","target":"graph","created_at":"2026-07-05T08:51:47Z","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/2402.15725/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human language can be expressed in either written or spoken form, i.e. text or speech. Humans can acquire knowledge from text to improve speaking and listening. However, the quest for speech pre-trained models to leverage unpaired text has just started. In this paper, we investigate a new way to pre-train such a joint speech-text model to learn enhanced speech representations and benefit various speech-related downstream tasks. Specifically, we propose a novel pre-training method, text-guided HuBERT, or T-HuBERT, which performs self-supervised learning over speech to derive phoneme-like discre","authors_text":"Duo Ma, Haizhou Li, Junyi Ao, Xianghu Yue, Xiaoxue Gao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-02-24T05:30:23Z","title":"Text-guided HuBERT: Self-Supervised Speech Pre-training via Generative Adversarial Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15725","kind":"arxiv","version":5},"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":"sha256:987b15f2ba32eb9992a6ccbf9f0b4e6e44465d9bcfa5870519791951611089c9","target":"record","created_at":"2026-07-05T08:51:47Z","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":"291e10b77e11887ee04858c193b65bdfc2a5e5d94257d252d296077749be1e3c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-02-24T05:30:23Z","title_canon_sha256":"1705503c27175c0ed8b55459c6044395a7c778813d2c123d7dd4b7d628d8c5e9"},"schema_version":"1.0","source":{"id":"2402.15725","kind":"arxiv","version":5}},"canonical_sha256":"a7e16bdec076260c9cd9c1fd3a3a38f371ec47219896392371f5d969dd22da61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7e16bdec076260c9cd9c1fd3a3a38f371ec47219896392371f5d969dd22da61","first_computed_at":"2026-07-05T08:51:47.912446Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:51:47.912446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FJ6O9PPhLZHNbtKChwJLbh6XjICvhnHd4fNeF6mQOr13FKqf/H1liQ5RcT6jKs27pd41dmX6RwTOxQKKFrjOAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:51:47.912943Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.15725","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:987b15f2ba32eb9992a6ccbf9f0b4e6e44465d9bcfa5870519791951611089c9","sha256:7dfe0182b29811e505156f0267eb064d547508789bdb6b1b0080e04bd3c87d4c"],"state_sha256":"14e54fa1722c7f1972e2d618d38380ec385f4464122dcfcf82cf729538c67210"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B12evrPuwL3zrFCQI8s5Bw6g9V24Coy9boScKFClaclqam2eNmGG+XgaJrYMEN1rvf1YvqJabG8QjYrBVimQCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T00:59:24.387156Z","bundle_sha256":"91cadfaff9e3fc902bee84526ff4b6c0d53407f27dcb4a17c789808c5afdd508"}}