{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:B6UOLMKTPL426MFGIKQ2TP7OWA","short_pith_number":"pith:B6UOLMKT","canonical_record":{"source":{"id":"2210.11981","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-21T14:16:51Z","cross_cats_sorted":[],"title_canon_sha256":"aed917b4ba70b9e551858f7dd81f0ee51ba5bbada289281a6d75937e40d10548","abstract_canon_sha256":"990b86f7f35c833da3ca47eb3fcec041133efe9d910da31af3345c7bab8c0e49"},"schema_version":"1.0"},"canonical_sha256":"0fa8e5b1537af9af30a642a1a9bfeeb00899538d2f02201fa77ec9daf91aacb5","source":{"kind":"arxiv","id":"2210.11981","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.11981","created_at":"2026-07-05T05:50:09Z"},{"alias_kind":"arxiv_version","alias_value":"2210.11981v2","created_at":"2026-07-05T05:50:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.11981","created_at":"2026-07-05T05:50:09Z"},{"alias_kind":"pith_short_12","alias_value":"B6UOLMKTPL42","created_at":"2026-07-05T05:50:09Z"},{"alias_kind":"pith_short_16","alias_value":"B6UOLMKTPL426MFG","created_at":"2026-07-05T05:50:09Z"},{"alias_kind":"pith_short_8","alias_value":"B6UOLMKT","created_at":"2026-07-05T05:50:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:B6UOLMKTPL426MFGIKQ2TP7OWA","target":"record","payload":{"canonical_record":{"source":{"id":"2210.11981","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-21T14:16:51Z","cross_cats_sorted":[],"title_canon_sha256":"aed917b4ba70b9e551858f7dd81f0ee51ba5bbada289281a6d75937e40d10548","abstract_canon_sha256":"990b86f7f35c833da3ca47eb3fcec041133efe9d910da31af3345c7bab8c0e49"},"schema_version":"1.0"},"canonical_sha256":"0fa8e5b1537af9af30a642a1a9bfeeb00899538d2f02201fa77ec9daf91aacb5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:50:09.953456Z","signature_b64":"/f/ozZvB9gj9LVMTHvAzR5XUPek9UKjLvFZnaW9VXkvjxLUhjve/WJ4Hty80D1h/Oy5rn272ge2WTCviz3+HAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fa8e5b1537af9af30a642a1a9bfeeb00899538d2f02201fa77ec9daf91aacb5","last_reissued_at":"2026-07-05T05:50:09.952983Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:50:09.952983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.11981","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":"2026-07-05T05:50:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V58W5FOChX/w1/aBBJQ0NrDmVU3RKLGMMEo47m+/ijPUgqC/KFioK2yUhdPeULwNGVdGUjdsxfvCuRdVbcPtCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T04:12:37.224520Z"},"content_sha256":"b6fd13e5b27e99c5cd0fdb3da3ac96cee8cf76017fa1dd19887a080303ee8d2b","schema_version":"1.0","event_id":"sha256:b6fd13e5b27e99c5cd0fdb3da3ac96cee8cf76017fa1dd19887a080303ee8d2b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:B6UOLMKTPL426MFGIKQ2TP7OWA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Named Entity Detection and Injection for Direct Speech Translation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hirofumi Inaguma, Hongyu Gong, Ilia Kulikov, Marco Gaido, Rongqing Huang, Yun Tang","submitted_at":"2022-10-21T14:16:51Z","abstract_excerpt":"In a sentence, certain words are critical for its semantic. Among them, named entities (NEs) are notoriously challenging for neural models. Despite their importance, their accurate handling has been neglected in speech-to-text (S2T) translation research, and recent work has shown that S2T models perform poorly for locations and notably person names, whose spelling is challenging unless known in advance. In this work, we explore how to leverage dictionaries of NEs known to likely appear in a given context to improve S2T model outputs. Our experiments show that we can reliably detect NEs likely "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.11981","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/2210.11981/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":"2026-07-05T05:50:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PECv+Ud2a5idlhZkJFT8/Ad1ZL0iirdnWnP6myXhBoPRz8YfpRzy9XFMZwk/QJ1rFiFo8v9BOtOaxUmNWqGlBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T04:12:37.225011Z"},"content_sha256":"b6f29096dbf9300bb58b065eee34896198b1d31a5aae70aa88cde5f568fe4b30","schema_version":"1.0","event_id":"sha256:b6f29096dbf9300bb58b065eee34896198b1d31a5aae70aa88cde5f568fe4b30"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B6UOLMKTPL426MFGIKQ2TP7OWA/bundle.json","state_url":"https://pith.science/pith/B6UOLMKTPL426MFGIKQ2TP7OWA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B6UOLMKTPL426MFGIKQ2TP7OWA/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":"2026-08-13T04:12:37Z","links":{"resolver":"https://pith.science/pith/B6UOLMKTPL426MFGIKQ2TP7OWA","bundle":"https://pith.science/pith/B6UOLMKTPL426MFGIKQ2TP7OWA/bundle.json","state":"https://pith.science/pith/B6UOLMKTPL426MFGIKQ2TP7OWA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B6UOLMKTPL426MFGIKQ2TP7OWA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:B6UOLMKTPL426MFGIKQ2TP7OWA","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":"990b86f7f35c833da3ca47eb3fcec041133efe9d910da31af3345c7bab8c0e49","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-21T14:16:51Z","title_canon_sha256":"aed917b4ba70b9e551858f7dd81f0ee51ba5bbada289281a6d75937e40d10548"},"schema_version":"1.0","source":{"id":"2210.11981","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.11981","created_at":"2026-07-05T05:50:09Z"},{"alias_kind":"arxiv_version","alias_value":"2210.11981v2","created_at":"2026-07-05T05:50:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.11981","created_at":"2026-07-05T05:50:09Z"},{"alias_kind":"pith_short_12","alias_value":"B6UOLMKTPL42","created_at":"2026-07-05T05:50:09Z"},{"alias_kind":"pith_short_16","alias_value":"B6UOLMKTPL426MFG","created_at":"2026-07-05T05:50:09Z"},{"alias_kind":"pith_short_8","alias_value":"B6UOLMKT","created_at":"2026-07-05T05:50:09Z"}],"graph_snapshots":[{"event_id":"sha256:b6f29096dbf9300bb58b065eee34896198b1d31a5aae70aa88cde5f568fe4b30","target":"graph","created_at":"2026-07-05T05:50:09Z","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/2210.11981/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In a sentence, certain words are critical for its semantic. Among them, named entities (NEs) are notoriously challenging for neural models. Despite their importance, their accurate handling has been neglected in speech-to-text (S2T) translation research, and recent work has shown that S2T models perform poorly for locations and notably person names, whose spelling is challenging unless known in advance. In this work, we explore how to leverage dictionaries of NEs known to likely appear in a given context to improve S2T model outputs. Our experiments show that we can reliably detect NEs likely ","authors_text":"Hirofumi Inaguma, Hongyu Gong, Ilia Kulikov, Marco Gaido, Rongqing Huang, Yun Tang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-21T14:16:51Z","title":"Named Entity Detection and Injection for Direct Speech Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.11981","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:b6fd13e5b27e99c5cd0fdb3da3ac96cee8cf76017fa1dd19887a080303ee8d2b","target":"record","created_at":"2026-07-05T05:50:09Z","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":"990b86f7f35c833da3ca47eb3fcec041133efe9d910da31af3345c7bab8c0e49","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-21T14:16:51Z","title_canon_sha256":"aed917b4ba70b9e551858f7dd81f0ee51ba5bbada289281a6d75937e40d10548"},"schema_version":"1.0","source":{"id":"2210.11981","kind":"arxiv","version":2}},"canonical_sha256":"0fa8e5b1537af9af30a642a1a9bfeeb00899538d2f02201fa77ec9daf91aacb5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0fa8e5b1537af9af30a642a1a9bfeeb00899538d2f02201fa77ec9daf91aacb5","first_computed_at":"2026-07-05T05:50:09.952983Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:50:09.952983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/f/ozZvB9gj9LVMTHvAzR5XUPek9UKjLvFZnaW9VXkvjxLUhjve/WJ4Hty80D1h/Oy5rn272ge2WTCviz3+HAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:50:09.953456Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.11981","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6fd13e5b27e99c5cd0fdb3da3ac96cee8cf76017fa1dd19887a080303ee8d2b","sha256:b6f29096dbf9300bb58b065eee34896198b1d31a5aae70aa88cde5f568fe4b30"],"state_sha256":"565a0312e1838d954605312dec2c9ae33c73b2b4ff31edf9dacc7a039178a084"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zDleQgGoAYf+qeKgLpBWglAdjjJdTqMi07uptTswGzGKmvL8dStwEEl+enuaZyyWiEQ6R5/AoJ7NO0lJPictAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T04:12:37.237964Z","bundle_sha256":"b7821667a8041dd4bfeb2305d0c1817efb909e0e9c69e7f5afb3f02f7cbfcaa7"}}