{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6B2T4LO7UPI3KLXKO4BT2IFHHX","short_pith_number":"pith:6B2T4LO7","canonical_record":{"source":{"id":"2401.03506","kind":"arxiv","version":11},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-01-07T14:54:57Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"00e96ca05f4d0746d21c504fca273f99f320790bd1ad5947d17c9d0e08f5c019","abstract_canon_sha256":"0a86f07ddf05c7f52b0492c7eda68c6a5bc581ab349c7763eb6779df44f6e0dc"},"schema_version":"1.0"},"canonical_sha256":"f0753e2ddfa3d1b52eea77033d20a73de3cdc3c1d7473c1fe316134ceeef2d3d","source":{"kind":"arxiv","id":"2401.03506","version":11},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.03506","created_at":"2026-07-05T09:58:40Z"},{"alias_kind":"arxiv_version","alias_value":"2401.03506v11","created_at":"2026-07-05T09:58:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.03506","created_at":"2026-07-05T09:58:40Z"},{"alias_kind":"pith_short_12","alias_value":"6B2T4LO7UPI3","created_at":"2026-07-05T09:58:40Z"},{"alias_kind":"pith_short_16","alias_value":"6B2T4LO7UPI3KLXK","created_at":"2026-07-05T09:58:40Z"},{"alias_kind":"pith_short_8","alias_value":"6B2T4LO7","created_at":"2026-07-05T09:58:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6B2T4LO7UPI3KLXKO4BT2IFHHX","target":"record","payload":{"canonical_record":{"source":{"id":"2401.03506","kind":"arxiv","version":11},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-01-07T14:54:57Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"00e96ca05f4d0746d21c504fca273f99f320790bd1ad5947d17c9d0e08f5c019","abstract_canon_sha256":"0a86f07ddf05c7f52b0492c7eda68c6a5bc581ab349c7763eb6779df44f6e0dc"},"schema_version":"1.0"},"canonical_sha256":"f0753e2ddfa3d1b52eea77033d20a73de3cdc3c1d7473c1fe316134ceeef2d3d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:40.541857Z","signature_b64":"h5c9GA+A+XAZiLUv4KeRDYJ5DEGI4vER22RpZunJ0NzCHRIt7xgYSCYBJpDjFMKfajWFHOKE6Gkat6+NxJTuBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0753e2ddfa3d1b52eea77033d20a73de3cdc3c1d7473c1fe316134ceeef2d3d","last_reissued_at":"2026-07-05T09:58:40.541326Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:40.541326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.03506","source_version":11,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:58:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OZg/NS1StUxYTBePGd3mgvZJheEo7knw0rJ3ZLv4uy05dAwaMqcrGicaTkxjuhuI0SspEHOEpnVLWoxcUd7eDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:59:52.384344Z"},"content_sha256":"891c1d9ff13c24f6f2997903caa5375373ddf965c0762038a9fde822dc70438b","schema_version":"1.0","event_id":"sha256:891c1d9ff13c24f6f2997903caa5375373ddf965c0762038a9fde822dc70438b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6B2T4LO7UPI3KLXKO4BT2IFHHX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DiarizationLM: Speaker Diarization Post-Processing with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Evan Clark, Guanlong Zhao, Hank Liao, Quan Wang, Wei Xia, Yiling Huang","submitted_at":"2024-01-07T14:54:57Z","abstract_excerpt":"In this paper, we introduce DiarizationLM, a framework to leverage large language models (LLM) to post-process the outputs from a speaker diarization system. Various goals can be achieved with the proposed framework, such as improving the readability of the diarized transcript, or reducing the word diarization error rate (WDER). In this framework, the outputs of the automatic speech recognition (ASR) and speaker diarization systems are represented as a compact textual format, which is included in the prompt to an optionally finetuned LLM. The outputs of the LLM can be used as the refined diari"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.03506","kind":"arxiv","version":11},"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/2401.03506/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":"2026-07-05T09:58:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VKXZ5m9RxIMlC3daNQQz2ziHsScCpI+uJd6RJONvnbKrVY4Obj5iSdRYE6VKk+uzjeb4txAzYqmGEa5NQgh3Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:59:52.385360Z"},"content_sha256":"f533ec8f6b38482d1a26e04c91f1386f754a71ac926375c2470004696b9ca02f","schema_version":"1.0","event_id":"sha256:f533ec8f6b38482d1a26e04c91f1386f754a71ac926375c2470004696b9ca02f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6B2T4LO7UPI3KLXKO4BT2IFHHX/bundle.json","state_url":"https://pith.science/pith/6B2T4LO7UPI3KLXKO4BT2IFHHX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6B2T4LO7UPI3KLXKO4BT2IFHHX/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":"2026-08-08T17:59:52Z","links":{"resolver":"https://pith.science/pith/6B2T4LO7UPI3KLXKO4BT2IFHHX","bundle":"https://pith.science/pith/6B2T4LO7UPI3KLXKO4BT2IFHHX/bundle.json","state":"https://pith.science/pith/6B2T4LO7UPI3KLXKO4BT2IFHHX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6B2T4LO7UPI3KLXKO4BT2IFHHX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6B2T4LO7UPI3KLXKO4BT2IFHHX","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":"0a86f07ddf05c7f52b0492c7eda68c6a5bc581ab349c7763eb6779df44f6e0dc","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-01-07T14:54:57Z","title_canon_sha256":"00e96ca05f4d0746d21c504fca273f99f320790bd1ad5947d17c9d0e08f5c019"},"schema_version":"1.0","source":{"id":"2401.03506","kind":"arxiv","version":11}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.03506","created_at":"2026-07-05T09:58:40Z"},{"alias_kind":"arxiv_version","alias_value":"2401.03506v11","created_at":"2026-07-05T09:58:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.03506","created_at":"2026-07-05T09:58:40Z"},{"alias_kind":"pith_short_12","alias_value":"6B2T4LO7UPI3","created_at":"2026-07-05T09:58:40Z"},{"alias_kind":"pith_short_16","alias_value":"6B2T4LO7UPI3KLXK","created_at":"2026-07-05T09:58:40Z"},{"alias_kind":"pith_short_8","alias_value":"6B2T4LO7","created_at":"2026-07-05T09:58:40Z"}],"graph_snapshots":[{"event_id":"sha256:f533ec8f6b38482d1a26e04c91f1386f754a71ac926375c2470004696b9ca02f","target":"graph","created_at":"2026-07-05T09:58:40Z","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/2401.03506/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce DiarizationLM, a framework to leverage large language models (LLM) to post-process the outputs from a speaker diarization system. Various goals can be achieved with the proposed framework, such as improving the readability of the diarized transcript, or reducing the word diarization error rate (WDER). In this framework, the outputs of the automatic speech recognition (ASR) and speaker diarization systems are represented as a compact textual format, which is included in the prompt to an optionally finetuned LLM. The outputs of the LLM can be used as the refined diari","authors_text":"Evan Clark, Guanlong Zhao, Hank Liao, Quan Wang, Wei Xia, Yiling Huang","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-01-07T14:54:57Z","title":"DiarizationLM: Speaker Diarization Post-Processing with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.03506","kind":"arxiv","version":11},"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":"sha256:891c1d9ff13c24f6f2997903caa5375373ddf965c0762038a9fde822dc70438b","target":"record","created_at":"2026-07-05T09:58:40Z","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":"0a86f07ddf05c7f52b0492c7eda68c6a5bc581ab349c7763eb6779df44f6e0dc","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-01-07T14:54:57Z","title_canon_sha256":"00e96ca05f4d0746d21c504fca273f99f320790bd1ad5947d17c9d0e08f5c019"},"schema_version":"1.0","source":{"id":"2401.03506","kind":"arxiv","version":11}},"canonical_sha256":"f0753e2ddfa3d1b52eea77033d20a73de3cdc3c1d7473c1fe316134ceeef2d3d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0753e2ddfa3d1b52eea77033d20a73de3cdc3c1d7473c1fe316134ceeef2d3d","first_computed_at":"2026-07-05T09:58:40.541326Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:58:40.541326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h5c9GA+A+XAZiLUv4KeRDYJ5DEGI4vER22RpZunJ0NzCHRIt7xgYSCYBJpDjFMKfajWFHOKE6Gkat6+NxJTuBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:58:40.541857Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.03506","source_kind":"arxiv","source_version":11}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:891c1d9ff13c24f6f2997903caa5375373ddf965c0762038a9fde822dc70438b","sha256:f533ec8f6b38482d1a26e04c91f1386f754a71ac926375c2470004696b9ca02f"],"state_sha256":"e5effea8b4252927a9ceded9b18cb20aacfb86c562ed8cd5189b8e8e4ac10902"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VKJuwHGJ4cwfMiGDkj0P9kaktQAlZL7w+o5X9y2W2xWT+KhCDrmKspio8Sv84naU7IcYR7ThL7kJrQYmwP93CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T17:59:52.391322Z","bundle_sha256":"ed657d7ac6de2525d3821044c2ac5ca99932067022844dfb882f8d8a8c10d7ae"}}