{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GVCTDYKDJQXPXRCJMKXRAGN2XR","short_pith_number":"pith:GVCTDYKD","canonical_record":{"source":{"id":"2405.11519","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-19T11:17:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9da21a6e5560644fb37b90c2193d0b41b163fae0a26f14e30b6d9cca0222cf5d","abstract_canon_sha256":"14af125ecf5cdc8403df420158284e720a58c70de0c3ed7f84f394da71a5af98"},"schema_version":"1.0"},"canonical_sha256":"354531e1434c2efbc44962af1019babc5b25cdd35296a94e1decf94c80250e89","source":{"kind":"arxiv","id":"2405.11519","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.11519","created_at":"2026-07-05T08:20:41Z"},{"alias_kind":"arxiv_version","alias_value":"2405.11519v1","created_at":"2026-07-05T08:20:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11519","created_at":"2026-07-05T08:20:41Z"},{"alias_kind":"pith_short_12","alias_value":"GVCTDYKDJQXP","created_at":"2026-07-05T08:20:41Z"},{"alias_kind":"pith_short_16","alias_value":"GVCTDYKDJQXPXRCJ","created_at":"2026-07-05T08:20:41Z"},{"alias_kind":"pith_short_8","alias_value":"GVCTDYKD","created_at":"2026-07-05T08:20:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GVCTDYKDJQXPXRCJMKXRAGN2XR","target":"record","payload":{"canonical_record":{"source":{"id":"2405.11519","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-19T11:17:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9da21a6e5560644fb37b90c2193d0b41b163fae0a26f14e30b6d9cca0222cf5d","abstract_canon_sha256":"14af125ecf5cdc8403df420158284e720a58c70de0c3ed7f84f394da71a5af98"},"schema_version":"1.0"},"canonical_sha256":"354531e1434c2efbc44962af1019babc5b25cdd35296a94e1decf94c80250e89","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:20:41.009378Z","signature_b64":"3oPufwBEvs+rBja+fG4QPZLjOvotEpkde/YqNbQ0bZTRGn/AdFNENjd+yqr/A29nnoBOUUT3BE2lHN8if8A/AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"354531e1434c2efbc44962af1019babc5b25cdd35296a94e1decf94c80250e89","last_reissued_at":"2026-07-05T08:20:41.008907Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:20:41.008907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.11519","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":"2026-07-05T08:20:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hE/Yn6vh8GyvWRzUeaiXiARPFIWYtAJ9emiCkN821z1wUw7f2JF0wu/Omsh9sKvWd66tTyAij40xlfrdxgBOBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T21:07:27.046017Z"},"content_sha256":"55560872036d377e1bcc5e0642a93b2a2436d473c60aec3b0b09eef3a4974e5b","schema_version":"1.0","event_id":"sha256:55560872036d377e1bcc5e0642a93b2a2436d473c60aec3b0b09eef3a4974e5b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GVCTDYKDJQXPXRCJMKXRAGN2XR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MSNER: A Multilingual Speech Dataset for Named Entity Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hugo Van hamme, Marie-Francine Moens, Quentin Meeus","submitted_at":"2024-05-19T11:17:00Z","abstract_excerpt":"While extensively explored in text-based tasks, Named Entity Recognition (NER) remains largely neglected in spoken language understanding. Existing resources are limited to a single, English-only dataset. This paper addresses this gap by introducing MSNER, a freely available, multilingual speech corpus annotated with named entities. It provides annotations to the VoxPopuli dataset in four languages (Dutch, French, German, and Spanish). We have also releasing an efficient annotation tool that leverages automatic pre-annotations for faster manual refinement. This results in 590 and 15 hours of s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11519","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/2405.11519/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":"2026-07-05T08:20:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rbpqWA2Uqy4uBELezmUTPpp+dskEPpvsEl1Xpva7sjhDfuG5vKjo3hI3XCsPtuwuYgvYh9Z8LOGnapWMtsNCBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T21:07:27.046897Z"},"content_sha256":"ec0ee8e1d039e608b154ebb126fb98e24f506d847555fd0922338393ee049f70","schema_version":"1.0","event_id":"sha256:ec0ee8e1d039e608b154ebb126fb98e24f506d847555fd0922338393ee049f70"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GVCTDYKDJQXPXRCJMKXRAGN2XR/bundle.json","state_url":"https://pith.science/pith/GVCTDYKDJQXPXRCJMKXRAGN2XR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GVCTDYKDJQXPXRCJMKXRAGN2XR/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":"2026-08-20T21:07:27Z","links":{"resolver":"https://pith.science/pith/GVCTDYKDJQXPXRCJMKXRAGN2XR","bundle":"https://pith.science/pith/GVCTDYKDJQXPXRCJMKXRAGN2XR/bundle.json","state":"https://pith.science/pith/GVCTDYKDJQXPXRCJMKXRAGN2XR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GVCTDYKDJQXPXRCJMKXRAGN2XR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GVCTDYKDJQXPXRCJMKXRAGN2XR","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":"14af125ecf5cdc8403df420158284e720a58c70de0c3ed7f84f394da71a5af98","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-19T11:17:00Z","title_canon_sha256":"9da21a6e5560644fb37b90c2193d0b41b163fae0a26f14e30b6d9cca0222cf5d"},"schema_version":"1.0","source":{"id":"2405.11519","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.11519","created_at":"2026-07-05T08:20:41Z"},{"alias_kind":"arxiv_version","alias_value":"2405.11519v1","created_at":"2026-07-05T08:20:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11519","created_at":"2026-07-05T08:20:41Z"},{"alias_kind":"pith_short_12","alias_value":"GVCTDYKDJQXP","created_at":"2026-07-05T08:20:41Z"},{"alias_kind":"pith_short_16","alias_value":"GVCTDYKDJQXPXRCJ","created_at":"2026-07-05T08:20:41Z"},{"alias_kind":"pith_short_8","alias_value":"GVCTDYKD","created_at":"2026-07-05T08:20:41Z"}],"graph_snapshots":[{"event_id":"sha256:ec0ee8e1d039e608b154ebb126fb98e24f506d847555fd0922338393ee049f70","target":"graph","created_at":"2026-07-05T08:20:41Z","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/2405.11519/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While extensively explored in text-based tasks, Named Entity Recognition (NER) remains largely neglected in spoken language understanding. Existing resources are limited to a single, English-only dataset. This paper addresses this gap by introducing MSNER, a freely available, multilingual speech corpus annotated with named entities. It provides annotations to the VoxPopuli dataset in four languages (Dutch, French, German, and Spanish). We have also releasing an efficient annotation tool that leverages automatic pre-annotations for faster manual refinement. This results in 590 and 15 hours of s","authors_text":"Hugo Van hamme, Marie-Francine Moens, Quentin Meeus","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-19T11:17:00Z","title":"MSNER: A Multilingual Speech Dataset for Named Entity Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11519","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":"sha256:55560872036d377e1bcc5e0642a93b2a2436d473c60aec3b0b09eef3a4974e5b","target":"record","created_at":"2026-07-05T08:20:41Z","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":"14af125ecf5cdc8403df420158284e720a58c70de0c3ed7f84f394da71a5af98","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-19T11:17:00Z","title_canon_sha256":"9da21a6e5560644fb37b90c2193d0b41b163fae0a26f14e30b6d9cca0222cf5d"},"schema_version":"1.0","source":{"id":"2405.11519","kind":"arxiv","version":1}},"canonical_sha256":"354531e1434c2efbc44962af1019babc5b25cdd35296a94e1decf94c80250e89","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"354531e1434c2efbc44962af1019babc5b25cdd35296a94e1decf94c80250e89","first_computed_at":"2026-07-05T08:20:41.008907Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:20:41.008907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3oPufwBEvs+rBja+fG4QPZLjOvotEpkde/YqNbQ0bZTRGn/AdFNENjd+yqr/A29nnoBOUUT3BE2lHN8if8A/AA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:20:41.009378Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.11519","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55560872036d377e1bcc5e0642a93b2a2436d473c60aec3b0b09eef3a4974e5b","sha256:ec0ee8e1d039e608b154ebb126fb98e24f506d847555fd0922338393ee049f70"],"state_sha256":"451c1f86a596e592626f1663bdfe2dd6ca997a468bb7b66a17116db9686f583d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H7Ua9jiq/Qs1DMDVGinaUO7td0b6SmeBE3cilWuIaoB3kQ5JbbTZuwKW9zznGhb8hGkkcTijtryo/IVx00CtBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T21:07:27.052776Z","bundle_sha256":"0906a10153e41593540006d2ca04c2599b5a717f284d94b12bca07fed87ff51a"}}