{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:3RHEBHWL433TH3QF3NBBTF37OB","short_pith_number":"pith:3RHEBHWL","canonical_record":{"source":{"id":"2210.04062","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-10-08T17:15:46Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"db4856cb2a5beed9a69a0771f0b2382625cc3e3a49ffa762cf26d76f1a07583f","abstract_canon_sha256":"c021e9bb88d314470657d6202ff5182b079d5f0c98b1d7a52f0a1c5dc33dc990"},"schema_version":"1.0"},"canonical_sha256":"dc4e409ecbe6f733ee05db4219977f7052b4a97c72c39665d34094e90439d841","source":{"kind":"arxiv","id":"2210.04062","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.04062","created_at":"2026-07-05T06:27:42Z"},{"alias_kind":"arxiv_version","alias_value":"2210.04062v3","created_at":"2026-07-05T06:27:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04062","created_at":"2026-07-05T06:27:42Z"},{"alias_kind":"pith_short_12","alias_value":"3RHEBHWL433T","created_at":"2026-07-05T06:27:42Z"},{"alias_kind":"pith_short_16","alias_value":"3RHEBHWL433TH3QF","created_at":"2026-07-05T06:27:42Z"},{"alias_kind":"pith_short_8","alias_value":"3RHEBHWL","created_at":"2026-07-05T06:27:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:3RHEBHWL433TH3QF3NBBTF37OB","target":"record","payload":{"canonical_record":{"source":{"id":"2210.04062","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-10-08T17:15:46Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"db4856cb2a5beed9a69a0771f0b2382625cc3e3a49ffa762cf26d76f1a07583f","abstract_canon_sha256":"c021e9bb88d314470657d6202ff5182b079d5f0c98b1d7a52f0a1c5dc33dc990"},"schema_version":"1.0"},"canonical_sha256":"dc4e409ecbe6f733ee05db4219977f7052b4a97c72c39665d34094e90439d841","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:27:42.625532Z","signature_b64":"j6Womz7wLIqASEXDmCLbUwexyT7rTJU4xSrvqZh0iFV1M24nZFhLMdhIV5Cx5zxa/Spcqps7ybKyTPvk3ZrJAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc4e409ecbe6f733ee05db4219977f7052b4a97c72c39665d34094e90439d841","last_reissued_at":"2026-07-05T06:27:42.625030Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:27:42.625030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.04062","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:27:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oLMEP+2R1i0WmoxlBYw9ZalJv8jvNZlxiDgsjfiXAdOdixWXN+4n54h4lk9MtYo69ZDtSiv2zCPKLFp6U+z2Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:29:01.607519Z"},"content_sha256":"f518e4e5176e1f62932b53b14aa27e2816fd644c4f69570fde239d315ffce867","schema_version":"1.0","event_id":"sha256:f518e4e5176e1f62932b53b14aa27e2816fd644c4f69570fde239d315ffce867"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:3RHEBHWL433TH3QF3NBBTF37OB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CoBERT: Self-Supervised Speech Representation Learning Through Code Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chutong Meng, Haizhou Li, Junyi Ao, Mingxuan Wang, Tom Ko","submitted_at":"2022-10-08T17:15:46Z","abstract_excerpt":"Speech is the surface form of a finite set of phonetic units, which can be represented by discrete codes. We propose the Code BERT (CoBERT) approach for self-supervised speech representation learning. The idea is to convert an utterance to a sequence of discrete codes, and perform code representation learning, where we predict the code representations based on a masked view of the original speech input. Unlike the prior self-distillation approaches of which the teacher and the student are of the same modality, our target model predicts representations from a different modality. CoBERT outperfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04062","kind":"arxiv","version":3},"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/2210.04062/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":"2026-07-05T06:27:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nzWMRgpZYpruHkTZ3GJGsddPo/Y3uvDox7P7Y5Rjxx1XjaFgPuvQQ7SgkBChUf41QTzmYosW9nedWWwjjv2BAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:29:01.607899Z"},"content_sha256":"b880075a6a44dec439ef8abf3d1da3bbd2c8b280b9c06f7a9a7a19e7e0ee71df","schema_version":"1.0","event_id":"sha256:b880075a6a44dec439ef8abf3d1da3bbd2c8b280b9c06f7a9a7a19e7e0ee71df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3RHEBHWL433TH3QF3NBBTF37OB/bundle.json","state_url":"https://pith.science/pith/3RHEBHWL433TH3QF3NBBTF37OB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3RHEBHWL433TH3QF3NBBTF37OB/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":"2026-07-07T06:29:01Z","links":{"resolver":"https://pith.science/pith/3RHEBHWL433TH3QF3NBBTF37OB","bundle":"https://pith.science/pith/3RHEBHWL433TH3QF3NBBTF37OB/bundle.json","state":"https://pith.science/pith/3RHEBHWL433TH3QF3NBBTF37OB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3RHEBHWL433TH3QF3NBBTF37OB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:3RHEBHWL433TH3QF3NBBTF37OB","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":"c021e9bb88d314470657d6202ff5182b079d5f0c98b1d7a52f0a1c5dc33dc990","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-10-08T17:15:46Z","title_canon_sha256":"db4856cb2a5beed9a69a0771f0b2382625cc3e3a49ffa762cf26d76f1a07583f"},"schema_version":"1.0","source":{"id":"2210.04062","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.04062","created_at":"2026-07-05T06:27:42Z"},{"alias_kind":"arxiv_version","alias_value":"2210.04062v3","created_at":"2026-07-05T06:27:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04062","created_at":"2026-07-05T06:27:42Z"},{"alias_kind":"pith_short_12","alias_value":"3RHEBHWL433T","created_at":"2026-07-05T06:27:42Z"},{"alias_kind":"pith_short_16","alias_value":"3RHEBHWL433TH3QF","created_at":"2026-07-05T06:27:42Z"},{"alias_kind":"pith_short_8","alias_value":"3RHEBHWL","created_at":"2026-07-05T06:27:42Z"}],"graph_snapshots":[{"event_id":"sha256:b880075a6a44dec439ef8abf3d1da3bbd2c8b280b9c06f7a9a7a19e7e0ee71df","target":"graph","created_at":"2026-07-05T06:27:42Z","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/2210.04062/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech is the surface form of a finite set of phonetic units, which can be represented by discrete codes. We propose the Code BERT (CoBERT) approach for self-supervised speech representation learning. The idea is to convert an utterance to a sequence of discrete codes, and perform code representation learning, where we predict the code representations based on a masked view of the original speech input. Unlike the prior self-distillation approaches of which the teacher and the student are of the same modality, our target model predicts representations from a different modality. CoBERT outperfo","authors_text":"Chutong Meng, Haizhou Li, Junyi Ao, Mingxuan Wang, Tom Ko","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-10-08T17:15:46Z","title":"CoBERT: Self-Supervised Speech Representation Learning Through Code Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04062","kind":"arxiv","version":3},"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:f518e4e5176e1f62932b53b14aa27e2816fd644c4f69570fde239d315ffce867","target":"record","created_at":"2026-07-05T06:27:42Z","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":"c021e9bb88d314470657d6202ff5182b079d5f0c98b1d7a52f0a1c5dc33dc990","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-10-08T17:15:46Z","title_canon_sha256":"db4856cb2a5beed9a69a0771f0b2382625cc3e3a49ffa762cf26d76f1a07583f"},"schema_version":"1.0","source":{"id":"2210.04062","kind":"arxiv","version":3}},"canonical_sha256":"dc4e409ecbe6f733ee05db4219977f7052b4a97c72c39665d34094e90439d841","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc4e409ecbe6f733ee05db4219977f7052b4a97c72c39665d34094e90439d841","first_computed_at":"2026-07-05T06:27:42.625030Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:27:42.625030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j6Womz7wLIqASEXDmCLbUwexyT7rTJU4xSrvqZh0iFV1M24nZFhLMdhIV5Cx5zxa/Spcqps7ybKyTPvk3ZrJAw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:27:42.625532Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.04062","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f518e4e5176e1f62932b53b14aa27e2816fd644c4f69570fde239d315ffce867","sha256:b880075a6a44dec439ef8abf3d1da3bbd2c8b280b9c06f7a9a7a19e7e0ee71df"],"state_sha256":"0e279c181c6d59114395f893adc394a333afe5d469d37d3fc26edebf44532627"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wPQ8IRmZUb2v6OzvHqGgbtMGNMtZsuvz43NV+cBmJbWXQnp+EbJ0G1Y7ybZt5LXByWzQsOtTbzLy0CnPfjaMCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T06:29:01.610134Z","bundle_sha256":"72c3e98352f78944bf796b3f113750e4f05a149c20b62c6cc86ecdf161da5ff1"}}