{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:T7D7DQXZEIHKZBRF7MSAJBKH6Z","short_pith_number":"pith:T7D7DQXZ","canonical_record":{"source":{"id":"2204.03240","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-04-07T06:12:05Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"59a452c8bdcfa8f0a9db955e039bd6219725d95c41abcb87d255eb83a8f3d159","abstract_canon_sha256":"eaee8202a6a8f76a5c0f8492d9165fe31de9c18256226deff844cd8acab68021"},"schema_version":"1.0"},"canonical_sha256":"9fc7f1c2f9220eac8625fb24048547f678604b043416413ec124670205d28cb0","source":{"kind":"arxiv","id":"2204.03240","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.03240","created_at":"2026-07-05T04:12:21Z"},{"alias_kind":"arxiv_version","alias_value":"2204.03240v1","created_at":"2026-07-05T04:12:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.03240","created_at":"2026-07-05T04:12:21Z"},{"alias_kind":"pith_short_12","alias_value":"T7D7DQXZEIHK","created_at":"2026-07-05T04:12:21Z"},{"alias_kind":"pith_short_16","alias_value":"T7D7DQXZEIHKZBRF","created_at":"2026-07-05T04:12:21Z"},{"alias_kind":"pith_short_8","alias_value":"T7D7DQXZ","created_at":"2026-07-05T04:12:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:T7D7DQXZEIHKZBRF7MSAJBKH6Z","target":"record","payload":{"canonical_record":{"source":{"id":"2204.03240","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-04-07T06:12:05Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"59a452c8bdcfa8f0a9db955e039bd6219725d95c41abcb87d255eb83a8f3d159","abstract_canon_sha256":"eaee8202a6a8f76a5c0f8492d9165fe31de9c18256226deff844cd8acab68021"},"schema_version":"1.0"},"canonical_sha256":"9fc7f1c2f9220eac8625fb24048547f678604b043416413ec124670205d28cb0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:12:21.304217Z","signature_b64":"2n8wXcIHTQ7CmKPsSnVOOQHiTb7pYO25mCOY6OMo4n7nfoz2LxprIJmRL2xuGCDZevj9Q4ZGIuOlHKo8FUUmBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fc7f1c2f9220eac8625fb24048547f678604b043416413ec124670205d28cb0","last_reissued_at":"2026-07-05T04:12:21.303696Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:12:21.303696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.03240","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":"2026-07-05T04:12:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"416Ijy2k7G2L+oEoeyf0zJyHkghahK5lOKNvGKbrB123OaXPy6WH074QmMCcdKvuOUwasPLF6gnqEnmEHWQqDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T03:25:54.345098Z"},"content_sha256":"f2650db739a68fd9c04ee692dc2f5010fe7d2ed2d90cc8d67c0e77c0042c70ba","schema_version":"1.0","event_id":"sha256:f2650db739a68fd9c04ee692dc2f5010fe7d2ed2d90cc8d67c0e77c0042c70ba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:T7D7DQXZEIHKZBRF7MSAJBKH6Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Speech Pre-training with Acoustic Piece","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Furu Wei, Long Zhou, Shujie Liu, Shuo Ren, Yu Wu","submitted_at":"2022-04-07T06:12:05Z","abstract_excerpt":"Previous speech pre-training methods, such as wav2vec2.0 and HuBERT, pre-train a Transformer encoder to learn deep representations from audio data, with objectives predicting either elements from latent vector quantized space or pre-generated labels (known as target codes) with offline clustering. However, those training signals (quantized elements or codes) are independent across different tokens without considering their relations. According to our observation and analysis, the target codes share obvious patterns aligned with phonemized text data. Based on that, we propose to leverage those "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.03240","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/2204.03240/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":"2026-07-05T04:12:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SFi0Z0NdQCeaj1+jna+KJCF5KdSFrlz/2+PAHZeeumN5K5J/k9vpMiDDttP6fNrU8xjg+oe7KvZZIy+RtBh9BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T03:25:54.345631Z"},"content_sha256":"10f96c4b12b9df0d4f24308b95c0c1b5fb9e22bc3e6f1e5cf1d644b94507f446","schema_version":"1.0","event_id":"sha256:10f96c4b12b9df0d4f24308b95c0c1b5fb9e22bc3e6f1e5cf1d644b94507f446"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T7D7DQXZEIHKZBRF7MSAJBKH6Z/bundle.json","state_url":"https://pith.science/pith/T7D7DQXZEIHKZBRF7MSAJBKH6Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T7D7DQXZEIHKZBRF7MSAJBKH6Z/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":"2026-08-10T03:25:54Z","links":{"resolver":"https://pith.science/pith/T7D7DQXZEIHKZBRF7MSAJBKH6Z","bundle":"https://pith.science/pith/T7D7DQXZEIHKZBRF7MSAJBKH6Z/bundle.json","state":"https://pith.science/pith/T7D7DQXZEIHKZBRF7MSAJBKH6Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T7D7DQXZEIHKZBRF7MSAJBKH6Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:T7D7DQXZEIHKZBRF7MSAJBKH6Z","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":"eaee8202a6a8f76a5c0f8492d9165fe31de9c18256226deff844cd8acab68021","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-04-07T06:12:05Z","title_canon_sha256":"59a452c8bdcfa8f0a9db955e039bd6219725d95c41abcb87d255eb83a8f3d159"},"schema_version":"1.0","source":{"id":"2204.03240","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.03240","created_at":"2026-07-05T04:12:21Z"},{"alias_kind":"arxiv_version","alias_value":"2204.03240v1","created_at":"2026-07-05T04:12:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.03240","created_at":"2026-07-05T04:12:21Z"},{"alias_kind":"pith_short_12","alias_value":"T7D7DQXZEIHK","created_at":"2026-07-05T04:12:21Z"},{"alias_kind":"pith_short_16","alias_value":"T7D7DQXZEIHKZBRF","created_at":"2026-07-05T04:12:21Z"},{"alias_kind":"pith_short_8","alias_value":"T7D7DQXZ","created_at":"2026-07-05T04:12:21Z"}],"graph_snapshots":[{"event_id":"sha256:10f96c4b12b9df0d4f24308b95c0c1b5fb9e22bc3e6f1e5cf1d644b94507f446","target":"graph","created_at":"2026-07-05T04:12:21Z","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/2204.03240/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Previous speech pre-training methods, such as wav2vec2.0 and HuBERT, pre-train a Transformer encoder to learn deep representations from audio data, with objectives predicting either elements from latent vector quantized space or pre-generated labels (known as target codes) with offline clustering. However, those training signals (quantized elements or codes) are independent across different tokens without considering their relations. According to our observation and analysis, the target codes share obvious patterns aligned with phonemized text data. Based on that, we propose to leverage those ","authors_text":"Furu Wei, Long Zhou, Shujie Liu, Shuo Ren, Yu Wu","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-04-07T06:12:05Z","title":"Speech Pre-training with Acoustic Piece"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.03240","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:f2650db739a68fd9c04ee692dc2f5010fe7d2ed2d90cc8d67c0e77c0042c70ba","target":"record","created_at":"2026-07-05T04:12:21Z","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":"eaee8202a6a8f76a5c0f8492d9165fe31de9c18256226deff844cd8acab68021","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-04-07T06:12:05Z","title_canon_sha256":"59a452c8bdcfa8f0a9db955e039bd6219725d95c41abcb87d255eb83a8f3d159"},"schema_version":"1.0","source":{"id":"2204.03240","kind":"arxiv","version":1}},"canonical_sha256":"9fc7f1c2f9220eac8625fb24048547f678604b043416413ec124670205d28cb0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9fc7f1c2f9220eac8625fb24048547f678604b043416413ec124670205d28cb0","first_computed_at":"2026-07-05T04:12:21.303696Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:12:21.303696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2n8wXcIHTQ7CmKPsSnVOOQHiTb7pYO25mCOY6OMo4n7nfoz2LxprIJmRL2xuGCDZevj9Q4ZGIuOlHKo8FUUmBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:12:21.304217Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.03240","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2650db739a68fd9c04ee692dc2f5010fe7d2ed2d90cc8d67c0e77c0042c70ba","sha256:10f96c4b12b9df0d4f24308b95c0c1b5fb9e22bc3e6f1e5cf1d644b94507f446"],"state_sha256":"ca01b1fa6d83c59b3972195d3f2b591830adf810847429d857f5c593cc8c8b86"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+QqtyvbvxhWp8baP8+zzj1hLFJg/wU5eA/wZ7B67Zuq8RxzBdstHhQEXcxjAdkWkgbNfpvsRIenkP772eiX8Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T03:25:54.349352Z","bundle_sha256":"1e04d614243ef32bd9ba2e176eb7884e1a661c65ccd2ffa7c926323f46d6b64b"}}