{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:7EBG5LMDXBR6LCAF5J2UIFQ5ON","short_pith_number":"pith:7EBG5LMD","canonical_record":{"source":{"id":"1908.01060","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-02T21:08:13Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"9396919bd9b896819e2b7a6cb5b0212f2c473fd26340ef5371e5a549586864b0","abstract_canon_sha256":"69a4cc18ee71ebf664bf7928e9acee73e118d6ace540c829df5640dc2743d545"},"schema_version":"1.0"},"canonical_sha256":"f9026ead83b863e58805ea7544161d73554b56e28f2055d651f3c44f603870f4","source":{"kind":"arxiv","id":"1908.01060","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.01060","created_at":"2026-07-04T23:51:25Z"},{"alias_kind":"arxiv_version","alias_value":"1908.01060v1","created_at":"2026-07-04T23:51:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.01060","created_at":"2026-07-04T23:51:25Z"},{"alias_kind":"pith_short_12","alias_value":"7EBG5LMDXBR6","created_at":"2026-07-04T23:51:25Z"},{"alias_kind":"pith_short_16","alias_value":"7EBG5LMDXBR6LCAF","created_at":"2026-07-04T23:51:25Z"},{"alias_kind":"pith_short_8","alias_value":"7EBG5LMD","created_at":"2026-07-04T23:51:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:7EBG5LMDXBR6LCAF5J2UIFQ5ON","target":"record","payload":{"canonical_record":{"source":{"id":"1908.01060","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-02T21:08:13Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"9396919bd9b896819e2b7a6cb5b0212f2c473fd26340ef5371e5a549586864b0","abstract_canon_sha256":"69a4cc18ee71ebf664bf7928e9acee73e118d6ace540c829df5640dc2743d545"},"schema_version":"1.0"},"canonical_sha256":"f9026ead83b863e58805ea7544161d73554b56e28f2055d651f3c44f603870f4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:51:25.988675Z","signature_b64":"QJpELKSa56y53kka9zkk9LcySqmn35r3qbCOYg3HftUyujmn8YwzvRxxuiDytWsQehlZQY2g16FuoYxt4XCzCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9026ead83b863e58805ea7544161d73554b56e28f2055d651f3c44f603870f4","last_reissued_at":"2026-07-04T23:51:25.988341Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:51:25.988341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.01060","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":"2026-07-04T23:51:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6xdyxDO0YgQKAOo2bUfWGhFsq3E+/TuI1yhsjREZ5J70Txy9y3gVhz9KcySOvr53PmvDs9EiZYROU2CBHtYcDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T01:43:07.764108Z"},"content_sha256":"d0867f69c67af9420ea69c5de0d12fdb48f9f288e88f8bbe417aab0cbd7c3493","schema_version":"1.0","event_id":"sha256:d0867f69c67af9420ea69c5de0d12fdb48f9f288e88f8bbe417aab0cbd7c3493"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:7EBG5LMDXBR6LCAF5J2UIFQ5ON","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multilingual Speech Recognition with Corpus Relatedness Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Alan W. Black, Florian Metze, Siddharth Dalmia, Xinjian Li","submitted_at":"2019-08-02T21:08:13Z","abstract_excerpt":"Multilingual acoustic models have been successfully applied to low-resource speech recognition. Most existing works have combined many small corpora together and pretrained a multilingual model by sampling from each corpus uniformly. The model is eventually fine-tuned on each target corpus. This approach, however, fails to exploit the relatedness and similarity among corpora in the training set. For example, the target corpus might benefit more from a corpus in the same domain or a corpus from a close language. In this work, we propose a simple but useful sampling strategy to take advantage of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.01060","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/1908.01060/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":"2026-07-04T23:51:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5/zqoUckm7AAxmNR/ETEB5FxRcZ5g3lk/bFTtdF5ExmvZ7ndkJJEglMk0xOCfztAo6pDU4Wui8ehB0hExeF0DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T01:43:07.764607Z"},"content_sha256":"c17e0c8a83f64d76526c74be85ac3afdf6b9c9b9a8316b644199bc9f9e421623","schema_version":"1.0","event_id":"sha256:c17e0c8a83f64d76526c74be85ac3afdf6b9c9b9a8316b644199bc9f9e421623"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7EBG5LMDXBR6LCAF5J2UIFQ5ON/bundle.json","state_url":"https://pith.science/pith/7EBG5LMDXBR6LCAF5J2UIFQ5ON/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7EBG5LMDXBR6LCAF5J2UIFQ5ON/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":"2026-08-17T01:43:07Z","links":{"resolver":"https://pith.science/pith/7EBG5LMDXBR6LCAF5J2UIFQ5ON","bundle":"https://pith.science/pith/7EBG5LMDXBR6LCAF5J2UIFQ5ON/bundle.json","state":"https://pith.science/pith/7EBG5LMDXBR6LCAF5J2UIFQ5ON/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7EBG5LMDXBR6LCAF5J2UIFQ5ON/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:7EBG5LMDXBR6LCAF5J2UIFQ5ON","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":"69a4cc18ee71ebf664bf7928e9acee73e118d6ace540c829df5640dc2743d545","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-02T21:08:13Z","title_canon_sha256":"9396919bd9b896819e2b7a6cb5b0212f2c473fd26340ef5371e5a549586864b0"},"schema_version":"1.0","source":{"id":"1908.01060","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.01060","created_at":"2026-07-04T23:51:25Z"},{"alias_kind":"arxiv_version","alias_value":"1908.01060v1","created_at":"2026-07-04T23:51:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.01060","created_at":"2026-07-04T23:51:25Z"},{"alias_kind":"pith_short_12","alias_value":"7EBG5LMDXBR6","created_at":"2026-07-04T23:51:25Z"},{"alias_kind":"pith_short_16","alias_value":"7EBG5LMDXBR6LCAF","created_at":"2026-07-04T23:51:25Z"},{"alias_kind":"pith_short_8","alias_value":"7EBG5LMD","created_at":"2026-07-04T23:51:25Z"}],"graph_snapshots":[{"event_id":"sha256:c17e0c8a83f64d76526c74be85ac3afdf6b9c9b9a8316b644199bc9f9e421623","target":"graph","created_at":"2026-07-04T23:51:25Z","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/1908.01060/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multilingual acoustic models have been successfully applied to low-resource speech recognition. Most existing works have combined many small corpora together and pretrained a multilingual model by sampling from each corpus uniformly. The model is eventually fine-tuned on each target corpus. This approach, however, fails to exploit the relatedness and similarity among corpora in the training set. For example, the target corpus might benefit more from a corpus in the same domain or a corpus from a close language. In this work, we propose a simple but useful sampling strategy to take advantage of","authors_text":"Alan W. Black, Florian Metze, Siddharth Dalmia, Xinjian Li","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-02T21:08:13Z","title":"Multilingual Speech Recognition with Corpus Relatedness Sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.01060","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:d0867f69c67af9420ea69c5de0d12fdb48f9f288e88f8bbe417aab0cbd7c3493","target":"record","created_at":"2026-07-04T23:51:25Z","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":"69a4cc18ee71ebf664bf7928e9acee73e118d6ace540c829df5640dc2743d545","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-02T21:08:13Z","title_canon_sha256":"9396919bd9b896819e2b7a6cb5b0212f2c473fd26340ef5371e5a549586864b0"},"schema_version":"1.0","source":{"id":"1908.01060","kind":"arxiv","version":1}},"canonical_sha256":"f9026ead83b863e58805ea7544161d73554b56e28f2055d651f3c44f603870f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9026ead83b863e58805ea7544161d73554b56e28f2055d651f3c44f603870f4","first_computed_at":"2026-07-04T23:51:25.988341Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:51:25.988341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QJpELKSa56y53kka9zkk9LcySqmn35r3qbCOYg3HftUyujmn8YwzvRxxuiDytWsQehlZQY2g16FuoYxt4XCzCQ==","signature_status":"signed_v1","signed_at":"2026-07-04T23:51:25.988675Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.01060","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d0867f69c67af9420ea69c5de0d12fdb48f9f288e88f8bbe417aab0cbd7c3493","sha256:c17e0c8a83f64d76526c74be85ac3afdf6b9c9b9a8316b644199bc9f9e421623"],"state_sha256":"7e7c409d2782603bdccd1dd3674283360dbf2c66c84d46cea154674878956ce6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"liY0ZhD/ruId3QneKgZ8rEfltMcpM3jcdm4+GUT3kB2BBZ6jew/RlAUYg3BetYpvShRdNWUhedoFDTqBKdqdCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T01:43:07.768556Z","bundle_sha256":"9b2b945c7d231ff16ba6850b507d407776912a04c1e08c97c8a838d43ca3a91f"}}