{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:AKECC7S7SGJ247Z7FEQX7FA6EA","short_pith_number":"pith:AKECC7S7","canonical_record":{"source":{"id":"2206.10125","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-21T06:08:30Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"dda3de787519daed9ab8facfd885393fc5c88789a564df0785a57f31b61978f8","abstract_canon_sha256":"f19996c5ba883e4fc1e42eebc926736c645a9537cf22b0b7aeed38a9e3d2fba9"},"schema_version":"1.0"},"canonical_sha256":"0288217e5f9193ae7f3f29217f941e20050bd50c2cec9691a3069eca66c0c374","source":{"kind":"arxiv","id":"2206.10125","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.10125","created_at":"2026-07-05T04:33:43Z"},{"alias_kind":"arxiv_version","alias_value":"2206.10125v1","created_at":"2026-07-05T04:33:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.10125","created_at":"2026-07-05T04:33:43Z"},{"alias_kind":"pith_short_12","alias_value":"AKECC7S7SGJ2","created_at":"2026-07-05T04:33:43Z"},{"alias_kind":"pith_short_16","alias_value":"AKECC7S7SGJ247Z7","created_at":"2026-07-05T04:33:43Z"},{"alias_kind":"pith_short_8","alias_value":"AKECC7S7","created_at":"2026-07-05T04:33:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:AKECC7S7SGJ247Z7FEQX7FA6EA","target":"record","payload":{"canonical_record":{"source":{"id":"2206.10125","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-21T06:08:30Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"dda3de787519daed9ab8facfd885393fc5c88789a564df0785a57f31b61978f8","abstract_canon_sha256":"f19996c5ba883e4fc1e42eebc926736c645a9537cf22b0b7aeed38a9e3d2fba9"},"schema_version":"1.0"},"canonical_sha256":"0288217e5f9193ae7f3f29217f941e20050bd50c2cec9691a3069eca66c0c374","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:33:43.869228Z","signature_b64":"e9l/Cy3a5lPPWOZjhZaJ6VML3oeJ7PtFt8zXrNHcakq09YhqO3IBwYArq0a2FtrUhO0k73kJYYf1fyQL5a7ZDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0288217e5f9193ae7f3f29217f941e20050bd50c2cec9691a3069eca66c0c374","last_reissued_at":"2026-07-05T04:33:43.868825Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:33:43.868825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.10125","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":"2026-07-05T04:33:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+zGoZ4y9wGPPa1viGUwPBld1jo6jV5EasHMxNyNS3qt0XZumnZFoXG5vKbJXn+BEmC04Vut7Uqdiby7OsKMRBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T15:42:28.588176Z"},"content_sha256":"8179acba0d0f36aaa3855a2610ff5afaf65c868762f149c052bee6a54db914c9","schema_version":"1.0","event_id":"sha256:8179acba0d0f36aaa3855a2610ff5afaf65c868762f149c052bee6a54db914c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:AKECC7S7SGJ247Z7FEQX7FA6EA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Supervision-Guided Codebooks for Masked Prediction in Speech Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chengyi Wang, Furu Wei, Jinyu Li, Sanyuan Chen, Shujie Liu, Yiming Wang, Yu Wu","submitted_at":"2022-06-21T06:08:30Z","abstract_excerpt":"Recently, masked prediction pre-training has seen remarkable progress in self-supervised learning (SSL) for speech recognition. It usually requires a codebook obtained in an unsupervised way, making it less accurate and difficult to interpret. We propose two supervision-guided codebook generation approaches to improve automatic speech recognition (ASR) performance and also the pre-training efficiency, either through decoding with a hybrid ASR system to generate phoneme-level alignments (named PBERT), or performing clustering on the supervised speech features extracted from an end-to-end CTC mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.10125","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/2206.10125/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":"2026-07-05T04:33:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+MfOO8IFtIYRZ2OYlUIcOX+HCvtsFaIxtJthdPxBaqXwEFkO1PaGYZOAIOf+q8sGFfGNERR/ns9BS3qduEfdAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T15:42:28.588779Z"},"content_sha256":"adf8772f99d58bfcf840d99c3d14cc51018e8e8e9069f6da71238cb2c301960a","schema_version":"1.0","event_id":"sha256:adf8772f99d58bfcf840d99c3d14cc51018e8e8e9069f6da71238cb2c301960a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AKECC7S7SGJ247Z7FEQX7FA6EA/bundle.json","state_url":"https://pith.science/pith/AKECC7S7SGJ247Z7FEQX7FA6EA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AKECC7S7SGJ247Z7FEQX7FA6EA/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":"2026-08-17T15:42:28Z","links":{"resolver":"https://pith.science/pith/AKECC7S7SGJ247Z7FEQX7FA6EA","bundle":"https://pith.science/pith/AKECC7S7SGJ247Z7FEQX7FA6EA/bundle.json","state":"https://pith.science/pith/AKECC7S7SGJ247Z7FEQX7FA6EA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AKECC7S7SGJ247Z7FEQX7FA6EA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:AKECC7S7SGJ247Z7FEQX7FA6EA","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":"f19996c5ba883e4fc1e42eebc926736c645a9537cf22b0b7aeed38a9e3d2fba9","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-21T06:08:30Z","title_canon_sha256":"dda3de787519daed9ab8facfd885393fc5c88789a564df0785a57f31b61978f8"},"schema_version":"1.0","source":{"id":"2206.10125","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.10125","created_at":"2026-07-05T04:33:43Z"},{"alias_kind":"arxiv_version","alias_value":"2206.10125v1","created_at":"2026-07-05T04:33:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.10125","created_at":"2026-07-05T04:33:43Z"},{"alias_kind":"pith_short_12","alias_value":"AKECC7S7SGJ2","created_at":"2026-07-05T04:33:43Z"},{"alias_kind":"pith_short_16","alias_value":"AKECC7S7SGJ247Z7","created_at":"2026-07-05T04:33:43Z"},{"alias_kind":"pith_short_8","alias_value":"AKECC7S7","created_at":"2026-07-05T04:33:43Z"}],"graph_snapshots":[{"event_id":"sha256:adf8772f99d58bfcf840d99c3d14cc51018e8e8e9069f6da71238cb2c301960a","target":"graph","created_at":"2026-07-05T04:33:43Z","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/2206.10125/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, masked prediction pre-training has seen remarkable progress in self-supervised learning (SSL) for speech recognition. It usually requires a codebook obtained in an unsupervised way, making it less accurate and difficult to interpret. We propose two supervision-guided codebook generation approaches to improve automatic speech recognition (ASR) performance and also the pre-training efficiency, either through decoding with a hybrid ASR system to generate phoneme-level alignments (named PBERT), or performing clustering on the supervised speech features extracted from an end-to-end CTC mo","authors_text":"Chengyi Wang, Furu Wei, Jinyu Li, Sanyuan Chen, Shujie Liu, Yiming Wang, Yu Wu","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-21T06:08:30Z","title":"Supervision-Guided Codebooks for Masked Prediction in Speech Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.10125","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":"sha256:8179acba0d0f36aaa3855a2610ff5afaf65c868762f149c052bee6a54db914c9","target":"record","created_at":"2026-07-05T04:33:43Z","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":"f19996c5ba883e4fc1e42eebc926736c645a9537cf22b0b7aeed38a9e3d2fba9","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-21T06:08:30Z","title_canon_sha256":"dda3de787519daed9ab8facfd885393fc5c88789a564df0785a57f31b61978f8"},"schema_version":"1.0","source":{"id":"2206.10125","kind":"arxiv","version":1}},"canonical_sha256":"0288217e5f9193ae7f3f29217f941e20050bd50c2cec9691a3069eca66c0c374","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0288217e5f9193ae7f3f29217f941e20050bd50c2cec9691a3069eca66c0c374","first_computed_at":"2026-07-05T04:33:43.868825Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:33:43.868825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e9l/Cy3a5lPPWOZjhZaJ6VML3oeJ7PtFt8zXrNHcakq09YhqO3IBwYArq0a2FtrUhO0k73kJYYf1fyQL5a7ZDw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:33:43.869228Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.10125","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8179acba0d0f36aaa3855a2610ff5afaf65c868762f149c052bee6a54db914c9","sha256:adf8772f99d58bfcf840d99c3d14cc51018e8e8e9069f6da71238cb2c301960a"],"state_sha256":"480bd6a3b5238dcc0646c732b6982a1b24cc94b9123333b2a6852a4e284d5349"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6+5y6bedoioSJIsxQxmHuJ01S88xSQqu4nMLksuvG3e2zfNzm5UmSBlH4D1vqfVPq4b59r9qNoCnK/msRQkcCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T15:42:28.592586Z","bundle_sha256":"9bed512773a0db8d68c7e2901dbe43013a1a44393c7f4ff9a4b84a72be3cb239"}}