{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AHXH2G7J6BFJXQCQLLXGJWJ5VT","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":"9e3b456fb20b0e06c2ee75415c4954edf7bfcd1a8642fdb2b95bc3f25ac2f67d","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-13T07:28:28Z","title_canon_sha256":"2918f42bf05debcd9f038e79d500eb0659d9ecf1822c2c645325b13112a3bbeb"},"schema_version":"1.0","source":{"id":"2409.08596","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.08596","created_at":"2026-07-05T10:43:25Z"},{"alias_kind":"arxiv_version","alias_value":"2409.08596v2","created_at":"2026-07-05T10:43:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08596","created_at":"2026-07-05T10:43:25Z"},{"alias_kind":"pith_short_12","alias_value":"AHXH2G7J6BFJ","created_at":"2026-07-05T10:43:25Z"},{"alias_kind":"pith_short_16","alias_value":"AHXH2G7J6BFJXQCQ","created_at":"2026-07-05T10:43:25Z"},{"alias_kind":"pith_short_8","alias_value":"AHXH2G7J","created_at":"2026-07-05T10:43:25Z"}],"graph_snapshots":[{"event_id":"sha256:b1c807c92d1ca79c18846a83d89d69b64d406311b2247928fb2bad8e8b72f92f","target":"graph","created_at":"2026-07-05T10:43:25Z","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/2409.08596/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in large language models (LLMs) have revolutionized various domains, bringing significant progress and new opportunities. Despite progress in speech-related tasks, LLMs have not been sufficiently explored in multi-talker scenarios. In this work, we present a pioneering effort to investigate the capability of LLMs in transcribing speech in multi-talker environments, following versatile instructions related to multi-talker automatic speech recognition (ASR), target talker ASR, and ASR based on specific talker attributes such as sex, occurrence order, language, and keyword spo","authors_text":"Helen Meng, Jiawen Kang, Lingwei Meng, Shujie Hu, Wenxuan Wu, Xixin Wu, Xunying Liu, Yuejiao Wang, Zhaoqing Li","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-13T07:28:28Z","title":"Large Language Model Can Transcribe Speech in Multi-Talker Scenarios with Versatile Instructions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08596","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:d2d7773cf0a985c0bcca31b5e547a27ecc5ed62579d1591176589eca5416d576","target":"record","created_at":"2026-07-05T10:43:25Z","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":"9e3b456fb20b0e06c2ee75415c4954edf7bfcd1a8642fdb2b95bc3f25ac2f67d","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-13T07:28:28Z","title_canon_sha256":"2918f42bf05debcd9f038e79d500eb0659d9ecf1822c2c645325b13112a3bbeb"},"schema_version":"1.0","source":{"id":"2409.08596","kind":"arxiv","version":2}},"canonical_sha256":"01ee7d1be9f04a9bc0505aee64d93dacf0e4838ddea5136c4bcaedb37f35dc35","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01ee7d1be9f04a9bc0505aee64d93dacf0e4838ddea5136c4bcaedb37f35dc35","first_computed_at":"2026-07-05T10:43:25.421809Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:43:25.421809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Cekhd4UO3LlqUXGwA2V34oSecekTW3t+Cq6uxpFKdO++h8kutwPf45QNymesdY2hpTV5jpmmm7VuEaAxDWORBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:43:25.422307Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.08596","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2d7773cf0a985c0bcca31b5e547a27ecc5ed62579d1591176589eca5416d576","sha256:b1c807c92d1ca79c18846a83d89d69b64d406311b2247928fb2bad8e8b72f92f"],"state_sha256":"8867715b5011296e4f1217eab8c5580563a30e766a49f8140ffabf6243522417"}