{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LASCAYAJPHPQKKUC5TXM47XKUE","short_pith_number":"pith:LASCAYAJ","canonical_record":{"source":{"id":"2406.04927","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-07T13:33:22Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a155861779d18d335c97fe7d614f4a98430ce4ea26c3f5b2cf13250e9ea36358","abstract_canon_sha256":"5047640cfa7b3b71f85a18d01ab77762cd3ae1db134a1d9ac8cc0dda2c5c304a"},"schema_version":"1.0"},"canonical_sha256":"582420600979df052a82eceece7eeaa10123065ba7c83e08340bd611a1cf0e9f","source":{"kind":"arxiv","id":"2406.04927","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04927","created_at":"2026-07-05T10:32:27Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04927v3","created_at":"2026-07-05T10:32:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04927","created_at":"2026-07-05T10:32:27Z"},{"alias_kind":"pith_short_12","alias_value":"LASCAYAJPHPQ","created_at":"2026-07-05T10:32:27Z"},{"alias_kind":"pith_short_16","alias_value":"LASCAYAJPHPQKKUC","created_at":"2026-07-05T10:32:27Z"},{"alias_kind":"pith_short_8","alias_value":"LASCAYAJ","created_at":"2026-07-05T10:32:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LASCAYAJPHPQKKUC5TXM47XKUE","target":"record","payload":{"canonical_record":{"source":{"id":"2406.04927","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-07T13:33:22Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a155861779d18d335c97fe7d614f4a98430ce4ea26c3f5b2cf13250e9ea36358","abstract_canon_sha256":"5047640cfa7b3b71f85a18d01ab77762cd3ae1db134a1d9ac8cc0dda2c5c304a"},"schema_version":"1.0"},"canonical_sha256":"582420600979df052a82eceece7eeaa10123065ba7c83e08340bd611a1cf0e9f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:27.339938Z","signature_b64":"6dmnFDry0WpVu3MMtJi7rxz0HGQF/eYsnqUGzmkEYHtqVRGJH+NUJGLk745+NM7+nW1u/E8IaHxB0CWeQPyeBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"582420600979df052a82eceece7eeaa10123065ba7c83e08340bd611a1cf0e9f","last_reissued_at":"2026-07-05T10:32:27.339057Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:27.339057Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.04927","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:32:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XXoVADRr1kSpfSzbqvF3ZwVQZR0ZueAOYHuX97q09dHxcWucfQ0GBmjz0llodIruXTmdYa+7I939DKHrxFefAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:26:10.540866Z"},"content_sha256":"01ab0dbc032ba7615dd5fde5eec17e46eb17fbefe6202e93746fa05c98512884","schema_version":"1.0","event_id":"sha256:01ab0dbc032ba7615dd5fde5eec17e46eb17fbefe6202e93746fa05c98512884"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LASCAYAJPHPQKKUC5TXM47XKUE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM-based speaker diarization correction: A generalizable approach","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Anzar Abbas, Georgios Efstathiadis, Vijay Yadav","submitted_at":"2024-06-07T13:33:22Z","abstract_excerpt":"Speaker diarization is necessary for interpreting conversations transcribed using automated speech recognition (ASR) tools. Despite significant developments in diarization methods, diarization accuracy remains an issue. Here, we investigate the use of large language models (LLMs) for diarization correction as a post-processing step. LLMs were fine-tuned using the Fisher corpus, a large dataset of transcribed conversations. The ability of the models to improve diarization accuracy in a holdout dataset from the Fisher corpus as well as an independent dataset was measured. We report that fine-tun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04927","kind":"arxiv","version":3},"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/2406.04927/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":"2026-07-05T10:32:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oB1woJVc+gz/RcWNyHn6KoB/ITiGp1bpxqKrRiYxKkZR/U9g4YEBAUVAjxh4yRxs4LhI0vXF5s26YBvdkt2uDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:26:10.541367Z"},"content_sha256":"403800126d82970fe6fd59af0b09d66a0786b7f25a5c932c7953d2ec17dc7aa0","schema_version":"1.0","event_id":"sha256:403800126d82970fe6fd59af0b09d66a0786b7f25a5c932c7953d2ec17dc7aa0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LASCAYAJPHPQKKUC5TXM47XKUE/bundle.json","state_url":"https://pith.science/pith/LASCAYAJPHPQKKUC5TXM47XKUE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LASCAYAJPHPQKKUC5TXM47XKUE/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":"2026-08-03T15:26:10Z","links":{"resolver":"https://pith.science/pith/LASCAYAJPHPQKKUC5TXM47XKUE","bundle":"https://pith.science/pith/LASCAYAJPHPQKKUC5TXM47XKUE/bundle.json","state":"https://pith.science/pith/LASCAYAJPHPQKKUC5TXM47XKUE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LASCAYAJPHPQKKUC5TXM47XKUE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LASCAYAJPHPQKKUC5TXM47XKUE","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":"5047640cfa7b3b71f85a18d01ab77762cd3ae1db134a1d9ac8cc0dda2c5c304a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-07T13:33:22Z","title_canon_sha256":"a155861779d18d335c97fe7d614f4a98430ce4ea26c3f5b2cf13250e9ea36358"},"schema_version":"1.0","source":{"id":"2406.04927","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04927","created_at":"2026-07-05T10:32:27Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04927v3","created_at":"2026-07-05T10:32:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04927","created_at":"2026-07-05T10:32:27Z"},{"alias_kind":"pith_short_12","alias_value":"LASCAYAJPHPQ","created_at":"2026-07-05T10:32:27Z"},{"alias_kind":"pith_short_16","alias_value":"LASCAYAJPHPQKKUC","created_at":"2026-07-05T10:32:27Z"},{"alias_kind":"pith_short_8","alias_value":"LASCAYAJ","created_at":"2026-07-05T10:32:27Z"}],"graph_snapshots":[{"event_id":"sha256:403800126d82970fe6fd59af0b09d66a0786b7f25a5c932c7953d2ec17dc7aa0","target":"graph","created_at":"2026-07-05T10:32:27Z","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/2406.04927/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speaker diarization is necessary for interpreting conversations transcribed using automated speech recognition (ASR) tools. Despite significant developments in diarization methods, diarization accuracy remains an issue. Here, we investigate the use of large language models (LLMs) for diarization correction as a post-processing step. LLMs were fine-tuned using the Fisher corpus, a large dataset of transcribed conversations. The ability of the models to improve diarization accuracy in a holdout dataset from the Fisher corpus as well as an independent dataset was measured. We report that fine-tun","authors_text":"Anzar Abbas, Georgios Efstathiadis, Vijay Yadav","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-07T13:33:22Z","title":"LLM-based speaker diarization correction: A generalizable approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04927","kind":"arxiv","version":3},"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":"sha256:01ab0dbc032ba7615dd5fde5eec17e46eb17fbefe6202e93746fa05c98512884","target":"record","created_at":"2026-07-05T10:32:27Z","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":"5047640cfa7b3b71f85a18d01ab77762cd3ae1db134a1d9ac8cc0dda2c5c304a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-07T13:33:22Z","title_canon_sha256":"a155861779d18d335c97fe7d614f4a98430ce4ea26c3f5b2cf13250e9ea36358"},"schema_version":"1.0","source":{"id":"2406.04927","kind":"arxiv","version":3}},"canonical_sha256":"582420600979df052a82eceece7eeaa10123065ba7c83e08340bd611a1cf0e9f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"582420600979df052a82eceece7eeaa10123065ba7c83e08340bd611a1cf0e9f","first_computed_at":"2026-07-05T10:32:27.339057Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:32:27.339057Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6dmnFDry0WpVu3MMtJi7rxz0HGQF/eYsnqUGzmkEYHtqVRGJH+NUJGLk745+NM7+nW1u/E8IaHxB0CWeQPyeBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:32:27.339938Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.04927","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:01ab0dbc032ba7615dd5fde5eec17e46eb17fbefe6202e93746fa05c98512884","sha256:403800126d82970fe6fd59af0b09d66a0786b7f25a5c932c7953d2ec17dc7aa0"],"state_sha256":"a01b752cac62792d03d126714ebd733005573b03accf9594a36d3cfb9f5f47a8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZW5Ar9eKVP3wmIEUe6pjS2zONeFo9YKib2iwo2ITeCjjQ3p4t49/ExzdU8hACR4uTGoMNuCUAt1qZAbxwEZmCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:26:10.546119Z","bundle_sha256":"0d8cbb2d24ba3c812bd1570a94ea33dea07d610a4bee6e0baea1ced0d172f496"}}