{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5KFIVMQKD6VWLKKWJ4EBKVLYZT","short_pith_number":"pith:5KFIVMQK","canonical_record":{"source":{"id":"2406.02166","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-04T09:56:05Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"34caf419def1e2912db87cd5913b8e86ffb5ed1bc3914a29b188f7f430626654","abstract_canon_sha256":"bca483005dcf21faadd74a4df980c06de10d94f7dfa406a3d48da9094fa29709"},"schema_version":"1.0"},"canonical_sha256":"ea8a8ab20a1fab65a9564f08155578ccc36f6b40b76c4ffe9f103628bd3db158","source":{"kind":"arxiv","id":"2406.02166","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.02166","created_at":"2026-07-05T10:40:01Z"},{"alias_kind":"arxiv_version","alias_value":"2406.02166v2","created_at":"2026-07-05T10:40:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02166","created_at":"2026-07-05T10:40:01Z"},{"alias_kind":"pith_short_12","alias_value":"5KFIVMQKD6VW","created_at":"2026-07-05T10:40:01Z"},{"alias_kind":"pith_short_16","alias_value":"5KFIVMQKD6VWLKKW","created_at":"2026-07-05T10:40:01Z"},{"alias_kind":"pith_short_8","alias_value":"5KFIVMQK","created_at":"2026-07-05T10:40:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5KFIVMQKD6VWLKKWJ4EBKVLYZT","target":"record","payload":{"canonical_record":{"source":{"id":"2406.02166","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-04T09:56:05Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"34caf419def1e2912db87cd5913b8e86ffb5ed1bc3914a29b188f7f430626654","abstract_canon_sha256":"bca483005dcf21faadd74a4df980c06de10d94f7dfa406a3d48da9094fa29709"},"schema_version":"1.0"},"canonical_sha256":"ea8a8ab20a1fab65a9564f08155578ccc36f6b40b76c4ffe9f103628bd3db158","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:01.326488Z","signature_b64":"NqkrmKF4kY79QEDAmDKfdWOZOfyJ1h3qYkSWnGE/Z2Ipy5hpGbBDaBiD0tPF9JQim2gMYimeg9aEwTdHYkt3DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea8a8ab20a1fab65a9564f08155578ccc36f6b40b76c4ffe9f103628bd3db158","last_reissued_at":"2026-07-05T10:40:01.326068Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:01.326068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.02166","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:40:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KHGdVBO1jBg+CzmFjhelwA6nE1zsyGBRjCSnPn+6fFXmUY8+b61M+CHQeYUdEsrPCGiltAKchQlaLNqq+4sLCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T18:22:50.120436Z"},"content_sha256":"32387d22ac54976bc2aa6a8a7448e3da498214c827e5a1d101ffa6cdd5814e0c","schema_version":"1.0","event_id":"sha256:32387d22ac54976bc2aa6a8a7448e3da498214c827e5a1d101ffa6cdd5814e0c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5KFIVMQKD6VWLKKWJ4EBKVLYZT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Whistle: Data-Efficient Multilingual and Crosslingual Speech Recognition via Weakly Phonetic Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Hao Huang, Saierdaer Yusuyin, Te Ma, Wenbo Zhao, Zhijian Ou","submitted_at":"2024-06-04T09:56:05Z","abstract_excerpt":"There exist three approaches for multilingual and crosslingual automatic speech recognition (MCL-ASR) - supervised pretraining with phonetic or graphemic transcription, and self-supervised pretraining. We find that pretraining with phonetic supervision has been underappreciated so far for MCL-ASR, while conceptually it is more advantageous for information sharing between different languages. This paper explores the approach of pretraining with weakly phonetic supervision towards data-efficient MCL-ASR, which is called Whistle. We relax the requirement of gold-standard human-validated phonetic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02166","kind":"arxiv","version":2},"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/2406.02166/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":"2026-07-05T10:40:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y4Js+jyxejgpfmjJG8o0Ueb8Vkg7WRP3QWFUNHZI7d8tS+Tbbzmh/+cIBG3Ib0DGu0tCtD8Pk8tm1TEUMC4bDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T18:22:50.121101Z"},"content_sha256":"1d5a450bd28ab2d327a9235f4b9b7f084c8fb8afc516f65435555aed9ff096f4","schema_version":"1.0","event_id":"sha256:1d5a450bd28ab2d327a9235f4b9b7f084c8fb8afc516f65435555aed9ff096f4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5KFIVMQKD6VWLKKWJ4EBKVLYZT/bundle.json","state_url":"https://pith.science/pith/5KFIVMQKD6VWLKKWJ4EBKVLYZT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5KFIVMQKD6VWLKKWJ4EBKVLYZT/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":"2026-08-13T18:22:50Z","links":{"resolver":"https://pith.science/pith/5KFIVMQKD6VWLKKWJ4EBKVLYZT","bundle":"https://pith.science/pith/5KFIVMQKD6VWLKKWJ4EBKVLYZT/bundle.json","state":"https://pith.science/pith/5KFIVMQKD6VWLKKWJ4EBKVLYZT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5KFIVMQKD6VWLKKWJ4EBKVLYZT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5KFIVMQKD6VWLKKWJ4EBKVLYZT","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":"bca483005dcf21faadd74a4df980c06de10d94f7dfa406a3d48da9094fa29709","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-04T09:56:05Z","title_canon_sha256":"34caf419def1e2912db87cd5913b8e86ffb5ed1bc3914a29b188f7f430626654"},"schema_version":"1.0","source":{"id":"2406.02166","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.02166","created_at":"2026-07-05T10:40:01Z"},{"alias_kind":"arxiv_version","alias_value":"2406.02166v2","created_at":"2026-07-05T10:40:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02166","created_at":"2026-07-05T10:40:01Z"},{"alias_kind":"pith_short_12","alias_value":"5KFIVMQKD6VW","created_at":"2026-07-05T10:40:01Z"},{"alias_kind":"pith_short_16","alias_value":"5KFIVMQKD6VWLKKW","created_at":"2026-07-05T10:40:01Z"},{"alias_kind":"pith_short_8","alias_value":"5KFIVMQK","created_at":"2026-07-05T10:40:01Z"}],"graph_snapshots":[{"event_id":"sha256:1d5a450bd28ab2d327a9235f4b9b7f084c8fb8afc516f65435555aed9ff096f4","target":"graph","created_at":"2026-07-05T10:40:01Z","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/2406.02166/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There exist three approaches for multilingual and crosslingual automatic speech recognition (MCL-ASR) - supervised pretraining with phonetic or graphemic transcription, and self-supervised pretraining. We find that pretraining with phonetic supervision has been underappreciated so far for MCL-ASR, while conceptually it is more advantageous for information sharing between different languages. This paper explores the approach of pretraining with weakly phonetic supervision towards data-efficient MCL-ASR, which is called Whistle. We relax the requirement of gold-standard human-validated phonetic ","authors_text":"Hao Huang, Saierdaer Yusuyin, Te Ma, Wenbo Zhao, Zhijian Ou","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-04T09:56:05Z","title":"Whistle: Data-Efficient Multilingual and Crosslingual Speech Recognition via Weakly Phonetic Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02166","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":"sha256:32387d22ac54976bc2aa6a8a7448e3da498214c827e5a1d101ffa6cdd5814e0c","target":"record","created_at":"2026-07-05T10:40:01Z","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":"bca483005dcf21faadd74a4df980c06de10d94f7dfa406a3d48da9094fa29709","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-04T09:56:05Z","title_canon_sha256":"34caf419def1e2912db87cd5913b8e86ffb5ed1bc3914a29b188f7f430626654"},"schema_version":"1.0","source":{"id":"2406.02166","kind":"arxiv","version":2}},"canonical_sha256":"ea8a8ab20a1fab65a9564f08155578ccc36f6b40b76c4ffe9f103628bd3db158","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea8a8ab20a1fab65a9564f08155578ccc36f6b40b76c4ffe9f103628bd3db158","first_computed_at":"2026-07-05T10:40:01.326068Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:40:01.326068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NqkrmKF4kY79QEDAmDKfdWOZOfyJ1h3qYkSWnGE/Z2Ipy5hpGbBDaBiD0tPF9JQim2gMYimeg9aEwTdHYkt3DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:40:01.326488Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.02166","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32387d22ac54976bc2aa6a8a7448e3da498214c827e5a1d101ffa6cdd5814e0c","sha256:1d5a450bd28ab2d327a9235f4b9b7f084c8fb8afc516f65435555aed9ff096f4"],"state_sha256":"fb8be9aeb53afe55eab12e758d0c67eeb147ba11b9c313f77a2cd8f85c21470a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k9ropWmYiFAkso5CElWPEozUcQjQ2lR3JsfiRkhSjPZdJSLe1VfbK2Jf7AcbkTdrhvF+slzuC4CFetEKng/TAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T18:22:50.127163Z","bundle_sha256":"2153d27fcce6806fd9971f526754726a0e5d4fc59011b7067115e1d315b23400"}}