{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HPPMS7OBS6AS2NG5WTKOF2O6QH","short_pith_number":"pith:HPPMS7OB","canonical_record":{"source":{"id":"2409.08107","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-12T15:00:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ebd272a5d07fa24e72b2a05c969034a35a9731efdec013bb0255c453e70001c6","abstract_canon_sha256":"c4850c983a01c7c6bd637b1694a82d91800d52c3077d9cfd9693e6615920aee2"},"schema_version":"1.0"},"canonical_sha256":"3bdec97dc197812d34ddb4d4e2e9de81e926c30f4b5fdfc35886311bf4f5312a","source":{"kind":"arxiv","id":"2409.08107","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.08107","created_at":"2026-07-05T11:49:46Z"},{"alias_kind":"arxiv_version","alias_value":"2409.08107v2","created_at":"2026-07-05T11:49:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08107","created_at":"2026-07-05T11:49:46Z"},{"alias_kind":"pith_short_12","alias_value":"HPPMS7OBS6AS","created_at":"2026-07-05T11:49:46Z"},{"alias_kind":"pith_short_16","alias_value":"HPPMS7OBS6AS2NG5","created_at":"2026-07-05T11:49:46Z"},{"alias_kind":"pith_short_8","alias_value":"HPPMS7OB","created_at":"2026-07-05T11:49:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HPPMS7OBS6AS2NG5WTKOF2O6QH","target":"record","payload":{"canonical_record":{"source":{"id":"2409.08107","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-12T15:00:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ebd272a5d07fa24e72b2a05c969034a35a9731efdec013bb0255c453e70001c6","abstract_canon_sha256":"c4850c983a01c7c6bd637b1694a82d91800d52c3077d9cfd9693e6615920aee2"},"schema_version":"1.0"},"canonical_sha256":"3bdec97dc197812d34ddb4d4e2e9de81e926c30f4b5fdfc35886311bf4f5312a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:46.664144Z","signature_b64":"SWi4osMDnzR3Z/j6cWrmDqnHG1lN43lw9q1w6K8I0mjTBJdZd7np5bf9EzQS+kcpTZ8hVf16BgEZEBP9pN0aAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3bdec97dc197812d34ddb4d4e2e9de81e926c30f4b5fdfc35886311bf4f5312a","last_reissued_at":"2026-07-05T11:49:46.663724Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:46.663724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.08107","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":"2026-07-05T11:49:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CMY1QTZWiCT7LwopVVq/95zvIO0L0MyK2NwY8jIVPDUh4dgmnb90w4wnOl7HOyVdO2oB7Al02ZZAbTpF1uVVBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T01:38:28.167061Z"},"content_sha256":"8e01e28ee14234c0d2581dd82d26559a91602c0187ffd33ddd3721520a6198b5","schema_version":"1.0","event_id":"sha256:8e01e28ee14234c0d2581dd82d26559a91602c0187ffd33ddd3721520a6198b5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HPPMS7OBS6AS2NG5WTKOF2O6QH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"WhisperNER: Unified Open Named Entity and Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aviv Navon, Aviv Shamsian, Gil Ayache, Gill Hetz, Joseph Keshet, Menachem Pirchi","submitted_at":"2024-09-12T15:00:56Z","abstract_excerpt":"Integrating named entity recognition (NER) with automatic speech recognition (ASR) can significantly enhance transcription accuracy and informativeness. In this paper, we introduce WhisperNER, a novel model that allows joint speech transcription and entity recognition. WhisperNER supports open-type NER, enabling recognition of diverse and evolving entities at inference. Building on recent advancements in open NER research, we augment a large synthetic dataset with synthetic speech samples. This allows us to train WhisperNER on a large number of examples with diverse NER tags. During training, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08107","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/2409.08107/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":"2026-07-05T11:49:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4KNISLtBAcoF1GpGPEiPKHLTrCVL6NXHHkrCEhoS7QCt7qMDPg9jt5QeUzyGaMTVjyRU/LkZ2yK8cUIAJ/dQAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T01:38:28.167461Z"},"content_sha256":"101f01921299b8b88c9c5e9d4e2e7fcb0cc6fed8094391f1de0830361d2b5dbe","schema_version":"1.0","event_id":"sha256:101f01921299b8b88c9c5e9d4e2e7fcb0cc6fed8094391f1de0830361d2b5dbe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HPPMS7OBS6AS2NG5WTKOF2O6QH/bundle.json","state_url":"https://pith.science/pith/HPPMS7OBS6AS2NG5WTKOF2O6QH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HPPMS7OBS6AS2NG5WTKOF2O6QH/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":"2026-07-26T01:38:28Z","links":{"resolver":"https://pith.science/pith/HPPMS7OBS6AS2NG5WTKOF2O6QH","bundle":"https://pith.science/pith/HPPMS7OBS6AS2NG5WTKOF2O6QH/bundle.json","state":"https://pith.science/pith/HPPMS7OBS6AS2NG5WTKOF2O6QH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HPPMS7OBS6AS2NG5WTKOF2O6QH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HPPMS7OBS6AS2NG5WTKOF2O6QH","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":"c4850c983a01c7c6bd637b1694a82d91800d52c3077d9cfd9693e6615920aee2","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-12T15:00:56Z","title_canon_sha256":"ebd272a5d07fa24e72b2a05c969034a35a9731efdec013bb0255c453e70001c6"},"schema_version":"1.0","source":{"id":"2409.08107","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.08107","created_at":"2026-07-05T11:49:46Z"},{"alias_kind":"arxiv_version","alias_value":"2409.08107v2","created_at":"2026-07-05T11:49:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08107","created_at":"2026-07-05T11:49:46Z"},{"alias_kind":"pith_short_12","alias_value":"HPPMS7OBS6AS","created_at":"2026-07-05T11:49:46Z"},{"alias_kind":"pith_short_16","alias_value":"HPPMS7OBS6AS2NG5","created_at":"2026-07-05T11:49:46Z"},{"alias_kind":"pith_short_8","alias_value":"HPPMS7OB","created_at":"2026-07-05T11:49:46Z"}],"graph_snapshots":[{"event_id":"sha256:101f01921299b8b88c9c5e9d4e2e7fcb0cc6fed8094391f1de0830361d2b5dbe","target":"graph","created_at":"2026-07-05T11:49:46Z","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/2409.08107/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Integrating named entity recognition (NER) with automatic speech recognition (ASR) can significantly enhance transcription accuracy and informativeness. In this paper, we introduce WhisperNER, a novel model that allows joint speech transcription and entity recognition. WhisperNER supports open-type NER, enabling recognition of diverse and evolving entities at inference. Building on recent advancements in open NER research, we augment a large synthetic dataset with synthetic speech samples. This allows us to train WhisperNER on a large number of examples with diverse NER tags. During training, ","authors_text":"Aviv Navon, Aviv Shamsian, Gil Ayache, Gill Hetz, Joseph Keshet, Menachem Pirchi","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-12T15:00:56Z","title":"WhisperNER: Unified Open Named Entity and Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08107","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":"sha256:8e01e28ee14234c0d2581dd82d26559a91602c0187ffd33ddd3721520a6198b5","target":"record","created_at":"2026-07-05T11:49:46Z","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":"c4850c983a01c7c6bd637b1694a82d91800d52c3077d9cfd9693e6615920aee2","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-12T15:00:56Z","title_canon_sha256":"ebd272a5d07fa24e72b2a05c969034a35a9731efdec013bb0255c453e70001c6"},"schema_version":"1.0","source":{"id":"2409.08107","kind":"arxiv","version":2}},"canonical_sha256":"3bdec97dc197812d34ddb4d4e2e9de81e926c30f4b5fdfc35886311bf4f5312a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3bdec97dc197812d34ddb4d4e2e9de81e926c30f4b5fdfc35886311bf4f5312a","first_computed_at":"2026-07-05T11:49:46.663724Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:46.663724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SWi4osMDnzR3Z/j6cWrmDqnHG1lN43lw9q1w6K8I0mjTBJdZd7np5bf9EzQS+kcpTZ8hVf16BgEZEBP9pN0aAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:46.664144Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.08107","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e01e28ee14234c0d2581dd82d26559a91602c0187ffd33ddd3721520a6198b5","sha256:101f01921299b8b88c9c5e9d4e2e7fcb0cc6fed8094391f1de0830361d2b5dbe"],"state_sha256":"0f4a3e6667946eb389b46bd8c5cc399edd5b595b364b652650a9e354e55dd8c3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fpj+YmOA84tVbbECKYaYtmCKlSunwXbLdBtvOvVM1/M86Q1SzkCph4+1KpEM2Zip1ICyiZyL9Lc2M+ogqOOUBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-26T01:38:28.170057Z","bundle_sha256":"a7aa7ff607085d033a2aeb0f81ac6ff891f05b71c67217a1da199e932fda0e0d"}}