{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LG2UWFFSIO2ODVALDENI23J3UK","short_pith_number":"pith:LG2UWFFS","canonical_record":{"source":{"id":"2404.11619","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-03-25T21:08:06Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"66fab5f5532059e70fc33c86d7ebcf7d35f37ee4301ed3d8226fe764cf9e8100","abstract_canon_sha256":"9bd95b660e7d021f4cb80cc725329209d275bac61dbe36a5ab86a397b1ef8a3e"},"schema_version":"1.0"},"canonical_sha256":"59b54b14b243b4e1d40b191a8d6d3ba2a745834d142f4f40ebc1ddc6855bcb8a","source":{"kind":"arxiv","id":"2404.11619","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.11619","created_at":"2026-07-05T08:09:13Z"},{"alias_kind":"arxiv_version","alias_value":"2404.11619v1","created_at":"2026-07-05T08:09:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.11619","created_at":"2026-07-05T08:09:13Z"},{"alias_kind":"pith_short_12","alias_value":"LG2UWFFSIO2O","created_at":"2026-07-05T08:09:13Z"},{"alias_kind":"pith_short_16","alias_value":"LG2UWFFSIO2ODVAL","created_at":"2026-07-05T08:09:13Z"},{"alias_kind":"pith_short_8","alias_value":"LG2UWFFS","created_at":"2026-07-05T08:09:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LG2UWFFSIO2ODVALDENI23J3UK","target":"record","payload":{"canonical_record":{"source":{"id":"2404.11619","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-03-25T21:08:06Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"66fab5f5532059e70fc33c86d7ebcf7d35f37ee4301ed3d8226fe764cf9e8100","abstract_canon_sha256":"9bd95b660e7d021f4cb80cc725329209d275bac61dbe36a5ab86a397b1ef8a3e"},"schema_version":"1.0"},"canonical_sha256":"59b54b14b243b4e1d40b191a8d6d3ba2a745834d142f4f40ebc1ddc6855bcb8a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:09:13.672812Z","signature_b64":"50gx7ni44J0yTEVSRlEg4P4e3tjYKf2zhxCMjXVebBvsqutwA2Olv/cKPvpj7u8bqBptkjLiE9BIcDNNhxc0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59b54b14b243b4e1d40b191a8d6d3ba2a745834d142f4f40ebc1ddc6855bcb8a","last_reissued_at":"2026-07-05T08:09:13.672390Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:09:13.672390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.11619","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":"2026-07-05T08:09:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XWOjitdwrn++pr+LSIFtFAiEjPj7xskyXaZ4Fx3UmLsILlltRiWS/L/CcAXncmxryQL9b19mpw8sTWxwQmLTCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:29:58.888607Z"},"content_sha256":"54daca505c91bbdb722dcad045e3e4876c715e019ceb088e85bb71f60537254b","schema_version":"1.0","event_id":"sha256:54daca505c91bbdb722dcad045e3e4876c715e019ceb088e85bb71f60537254b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LG2UWFFSIO2ODVALDENI23J3UK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Advancing Speech Translation: A Corpus of Mandarin-English Conversational Telephone Speech","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Matthew Snover, Shannon Wotherspoon, William Hartmann","submitted_at":"2024-03-25T21:08:06Z","abstract_excerpt":"This paper introduces a set of English translations for a 123-hour subset of the CallHome Mandarin Chinese data and the HKUST Mandarin Telephone Speech data for the task of speech translation. Paired source-language speech and target-language text is essential for training end-to-end speech translation systems and can provide substantial performance improvements for cascaded systems as well, relative to training on more widely available text data sets. We demonstrate that fine-tuning a general-purpose translation model to our Mandarin-English conversational telephone speech training set improv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.11619","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/2404.11619/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":"2026-07-05T08:09:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oAdI1JjrZRALakh9rFO1M7nxLnqf9HUj7AGUhOKuh+wPIaRcC7mSXeNPiDXk2rTuPlIcYJ31tPEU3fHVjFsZDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:29:58.889120Z"},"content_sha256":"5d0a11bf6362ca2285735320793f53425858d8d5b0e05596c297e4d4a69b3f67","schema_version":"1.0","event_id":"sha256:5d0a11bf6362ca2285735320793f53425858d8d5b0e05596c297e4d4a69b3f67"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LG2UWFFSIO2ODVALDENI23J3UK/bundle.json","state_url":"https://pith.science/pith/LG2UWFFSIO2ODVALDENI23J3UK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LG2UWFFSIO2ODVALDENI23J3UK/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":"2026-08-08T09:29:58Z","links":{"resolver":"https://pith.science/pith/LG2UWFFSIO2ODVALDENI23J3UK","bundle":"https://pith.science/pith/LG2UWFFSIO2ODVALDENI23J3UK/bundle.json","state":"https://pith.science/pith/LG2UWFFSIO2ODVALDENI23J3UK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LG2UWFFSIO2ODVALDENI23J3UK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LG2UWFFSIO2ODVALDENI23J3UK","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":"9bd95b660e7d021f4cb80cc725329209d275bac61dbe36a5ab86a397b1ef8a3e","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-03-25T21:08:06Z","title_canon_sha256":"66fab5f5532059e70fc33c86d7ebcf7d35f37ee4301ed3d8226fe764cf9e8100"},"schema_version":"1.0","source":{"id":"2404.11619","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.11619","created_at":"2026-07-05T08:09:13Z"},{"alias_kind":"arxiv_version","alias_value":"2404.11619v1","created_at":"2026-07-05T08:09:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.11619","created_at":"2026-07-05T08:09:13Z"},{"alias_kind":"pith_short_12","alias_value":"LG2UWFFSIO2O","created_at":"2026-07-05T08:09:13Z"},{"alias_kind":"pith_short_16","alias_value":"LG2UWFFSIO2ODVAL","created_at":"2026-07-05T08:09:13Z"},{"alias_kind":"pith_short_8","alias_value":"LG2UWFFS","created_at":"2026-07-05T08:09:13Z"}],"graph_snapshots":[{"event_id":"sha256:5d0a11bf6362ca2285735320793f53425858d8d5b0e05596c297e4d4a69b3f67","target":"graph","created_at":"2026-07-05T08:09:13Z","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/2404.11619/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces a set of English translations for a 123-hour subset of the CallHome Mandarin Chinese data and the HKUST Mandarin Telephone Speech data for the task of speech translation. Paired source-language speech and target-language text is essential for training end-to-end speech translation systems and can provide substantial performance improvements for cascaded systems as well, relative to training on more widely available text data sets. We demonstrate that fine-tuning a general-purpose translation model to our Mandarin-English conversational telephone speech training set improv","authors_text":"Matthew Snover, Shannon Wotherspoon, William Hartmann","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-03-25T21:08:06Z","title":"Advancing Speech Translation: A Corpus of Mandarin-English Conversational Telephone Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.11619","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":"sha256:54daca505c91bbdb722dcad045e3e4876c715e019ceb088e85bb71f60537254b","target":"record","created_at":"2026-07-05T08:09:13Z","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":"9bd95b660e7d021f4cb80cc725329209d275bac61dbe36a5ab86a397b1ef8a3e","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-03-25T21:08:06Z","title_canon_sha256":"66fab5f5532059e70fc33c86d7ebcf7d35f37ee4301ed3d8226fe764cf9e8100"},"schema_version":"1.0","source":{"id":"2404.11619","kind":"arxiv","version":1}},"canonical_sha256":"59b54b14b243b4e1d40b191a8d6d3ba2a745834d142f4f40ebc1ddc6855bcb8a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59b54b14b243b4e1d40b191a8d6d3ba2a745834d142f4f40ebc1ddc6855bcb8a","first_computed_at":"2026-07-05T08:09:13.672390Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:09:13.672390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"50gx7ni44J0yTEVSRlEg4P4e3tjYKf2zhxCMjXVebBvsqutwA2Olv/cKPvpj7u8bqBptkjLiE9BIcDNNhxc0Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:09:13.672812Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.11619","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54daca505c91bbdb722dcad045e3e4876c715e019ceb088e85bb71f60537254b","sha256:5d0a11bf6362ca2285735320793f53425858d8d5b0e05596c297e4d4a69b3f67"],"state_sha256":"af79aa3001ef97480ee31fb000f283b0543d3c24ec91b6f3dc795c52f1f67289"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iIqQv3hshwI2/f778C4pUv/L0RRBPxn0f6xcrF3zOO3IrsRRBER5oZnz0VVM6PyRBEE8dh7Q6RrdXEJbiG4BDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:29:58.892871Z","bundle_sha256":"0c712c911c5b14ef2c98ee9800eb1961bd070947987b6a99d5d2a57a9aa4f9fb"}}