{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:W53M73PSJGNQXDNIYT5BY7GUIZ","short_pith_number":"pith:W53M73PS","canonical_record":{"source":{"id":"2412.19102","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-26T07:43:18Z","cross_cats_sorted":[],"title_canon_sha256":"d7d3bfd79c83c7d234396bda6944d0cc8b828cf3aaebb2d02635276051985ea9","abstract_canon_sha256":"a99757fbe78d9a8a500ebbecdb24296a842d3fa6f2c2314d3b953e60ff316e26"},"schema_version":"1.0"},"canonical_sha256":"b776cfedf2499b0b8da8c4fa1c7cd446446d50db6592ce6b4ab217b14cdb9ca2","source":{"kind":"arxiv","id":"2412.19102","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19102","created_at":"2026-07-05T09:54:16Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19102v1","created_at":"2026-07-05T09:54:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19102","created_at":"2026-07-05T09:54:16Z"},{"alias_kind":"pith_short_12","alias_value":"W53M73PSJGNQ","created_at":"2026-07-05T09:54:16Z"},{"alias_kind":"pith_short_16","alias_value":"W53M73PSJGNQXDNI","created_at":"2026-07-05T09:54:16Z"},{"alias_kind":"pith_short_8","alias_value":"W53M73PS","created_at":"2026-07-05T09:54:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:W53M73PSJGNQXDNIYT5BY7GUIZ","target":"record","payload":{"canonical_record":{"source":{"id":"2412.19102","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-26T07:43:18Z","cross_cats_sorted":[],"title_canon_sha256":"d7d3bfd79c83c7d234396bda6944d0cc8b828cf3aaebb2d02635276051985ea9","abstract_canon_sha256":"a99757fbe78d9a8a500ebbecdb24296a842d3fa6f2c2314d3b953e60ff316e26"},"schema_version":"1.0"},"canonical_sha256":"b776cfedf2499b0b8da8c4fa1c7cd446446d50db6592ce6b4ab217b14cdb9ca2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:16.203926Z","signature_b64":"n+ERhtT/Day09b4FSru2aehiUIXY8NPeQzlQxT3kvqDzuQrWqZyEfyXUlm3IkQQILzXVGeUJxcxsRafItKG6Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b776cfedf2499b0b8da8c4fa1c7cd446446d50db6592ce6b4ab217b14cdb9ca2","last_reissued_at":"2026-07-05T09:54:16.203509Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:16.203509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.19102","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":"2026-07-05T09:54:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iTz11uauvZjbbwDLquQgjIbnEUdDvMlLjhUZfBGdweQ3wEOzywsilGW9HbXP6hcK+8XompH8258Qli05oLOuBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:32:47.507544Z"},"content_sha256":"4f16d359f247bc6c3f3ed72f6ea407a26d909b34b0f11fd69b142762ac078c12","schema_version":"1.0","event_id":"sha256:4f16d359f247bc6c3f3ed72f6ea407a26d909b34b0f11fd69b142762ac078c12"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:W53M73PSJGNQXDNIYT5BY7GUIZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"\"I've Heard of You!\": Generate Spoken Named Entity Recognition Data for Unseen Entities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Yang, Jiahuan Li, Jiawei Yu, Jinsong Su, Mengxin Ren, Min Zhang, Shujian Huang, Wei Tang, Xiang Geng, Yuang Li, Zhibin Lan","submitted_at":"2024-12-26T07:43:18Z","abstract_excerpt":"Spoken named entity recognition (NER) aims to identify named entities from speech, playing an important role in speech processing. New named entities appear every day, however, annotating their Spoken NER data is costly. In this paper, we demonstrate that existing Spoken NER systems perform poorly when dealing with previously unseen named entities. To tackle this challenge, we propose a method for generating Spoken NER data based on a named entity dictionary (NED) to reduce costs. Specifically, we first use a large language model (LLM) to generate sentences from the sampled named entities and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19102","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/2412.19102/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":"2026-07-05T09:54:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u4n5qpPD+gL+FLEo/yrrA0G+9jwgGuP6Rywa48yu2xJe0OhdtcpPW1iMgs12UqHEQk/HvrfGl59fGjS50T/JAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:32:47.508264Z"},"content_sha256":"093cf5bfb8830c606132c8d64704d22e387b47b2d243e37470317c37992113d7","schema_version":"1.0","event_id":"sha256:093cf5bfb8830c606132c8d64704d22e387b47b2d243e37470317c37992113d7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W53M73PSJGNQXDNIYT5BY7GUIZ/bundle.json","state_url":"https://pith.science/pith/W53M73PSJGNQXDNIYT5BY7GUIZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W53M73PSJGNQXDNIYT5BY7GUIZ/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":"2026-08-05T10:32:47Z","links":{"resolver":"https://pith.science/pith/W53M73PSJGNQXDNIYT5BY7GUIZ","bundle":"https://pith.science/pith/W53M73PSJGNQXDNIYT5BY7GUIZ/bundle.json","state":"https://pith.science/pith/W53M73PSJGNQXDNIYT5BY7GUIZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W53M73PSJGNQXDNIYT5BY7GUIZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:W53M73PSJGNQXDNIYT5BY7GUIZ","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":"a99757fbe78d9a8a500ebbecdb24296a842d3fa6f2c2314d3b953e60ff316e26","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-26T07:43:18Z","title_canon_sha256":"d7d3bfd79c83c7d234396bda6944d0cc8b828cf3aaebb2d02635276051985ea9"},"schema_version":"1.0","source":{"id":"2412.19102","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19102","created_at":"2026-07-05T09:54:16Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19102v1","created_at":"2026-07-05T09:54:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19102","created_at":"2026-07-05T09:54:16Z"},{"alias_kind":"pith_short_12","alias_value":"W53M73PSJGNQ","created_at":"2026-07-05T09:54:16Z"},{"alias_kind":"pith_short_16","alias_value":"W53M73PSJGNQXDNI","created_at":"2026-07-05T09:54:16Z"},{"alias_kind":"pith_short_8","alias_value":"W53M73PS","created_at":"2026-07-05T09:54:16Z"}],"graph_snapshots":[{"event_id":"sha256:093cf5bfb8830c606132c8d64704d22e387b47b2d243e37470317c37992113d7","target":"graph","created_at":"2026-07-05T09:54:16Z","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/2412.19102/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spoken named entity recognition (NER) aims to identify named entities from speech, playing an important role in speech processing. New named entities appear every day, however, annotating their Spoken NER data is costly. In this paper, we demonstrate that existing Spoken NER systems perform poorly when dealing with previously unseen named entities. To tackle this challenge, we propose a method for generating Spoken NER data based on a named entity dictionary (NED) to reduce costs. Specifically, we first use a large language model (LLM) to generate sentences from the sampled named entities and ","authors_text":"Hao Yang, Jiahuan Li, Jiawei Yu, Jinsong Su, Mengxin Ren, Min Zhang, Shujian Huang, Wei Tang, Xiang Geng, Yuang Li, Zhibin Lan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-26T07:43:18Z","title":"\"I've Heard of You!\": Generate Spoken Named Entity Recognition Data for Unseen Entities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19102","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":"sha256:4f16d359f247bc6c3f3ed72f6ea407a26d909b34b0f11fd69b142762ac078c12","target":"record","created_at":"2026-07-05T09:54:16Z","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":"a99757fbe78d9a8a500ebbecdb24296a842d3fa6f2c2314d3b953e60ff316e26","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-26T07:43:18Z","title_canon_sha256":"d7d3bfd79c83c7d234396bda6944d0cc8b828cf3aaebb2d02635276051985ea9"},"schema_version":"1.0","source":{"id":"2412.19102","kind":"arxiv","version":1}},"canonical_sha256":"b776cfedf2499b0b8da8c4fa1c7cd446446d50db6592ce6b4ab217b14cdb9ca2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b776cfedf2499b0b8da8c4fa1c7cd446446d50db6592ce6b4ab217b14cdb9ca2","first_computed_at":"2026-07-05T09:54:16.203509Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:16.203509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n+ERhtT/Day09b4FSru2aehiUIXY8NPeQzlQxT3kvqDzuQrWqZyEfyXUlm3IkQQILzXVGeUJxcxsRafItKG6Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:16.203926Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.19102","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f16d359f247bc6c3f3ed72f6ea407a26d909b34b0f11fd69b142762ac078c12","sha256:093cf5bfb8830c606132c8d64704d22e387b47b2d243e37470317c37992113d7"],"state_sha256":"ed3334455566ed7b1cd65a219667c1980928f7e9c12310dff5c9a952340d6061"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"39Qw1uDzk+AjMakKfBaGf4EnCmOUNdQCyLvbXi8P0brNHf14kJtu2/w32Dywte5HouACETbs/BOFqouCEQcdDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T10:32:47.517326Z","bundle_sha256":"132f50f0a6dc1c54cfd8e110657a50bee17ce99c721f0222924852d2af2ffb59"}}