{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PCVCBVPV6DLDGIVDQBLWSR6R3P","short_pith_number":"pith:PCVCBVPV","canonical_record":{"source":{"id":"2309.05248","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-11T05:47:56Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"9b7d873119b347f193a723e2a403ff02eb58910a49bb43858a0306571a3a9130","abstract_canon_sha256":"93ab925f28886a63aac1eca3aba6c3daee7a38194b5ce0c00ff7804ea200e3e9"},"schema_version":"1.0"},"canonical_sha256":"78aa20d5f5f0d63322a380576947d1dbedef2aba8ea87578b3214c52abd55170","source":{"kind":"arxiv","id":"2309.05248","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.05248","created_at":"2026-07-05T06:50:30Z"},{"alias_kind":"arxiv_version","alias_value":"2309.05248v3","created_at":"2026-07-05T06:50:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.05248","created_at":"2026-07-05T06:50:30Z"},{"alias_kind":"pith_short_12","alias_value":"PCVCBVPV6DLD","created_at":"2026-07-05T06:50:30Z"},{"alias_kind":"pith_short_16","alias_value":"PCVCBVPV6DLDGIVD","created_at":"2026-07-05T06:50:30Z"},{"alias_kind":"pith_short_8","alias_value":"PCVCBVPV","created_at":"2026-07-05T06:50:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PCVCBVPV6DLDGIVDQBLWSR6R3P","target":"record","payload":{"canonical_record":{"source":{"id":"2309.05248","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-11T05:47:56Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"9b7d873119b347f193a723e2a403ff02eb58910a49bb43858a0306571a3a9130","abstract_canon_sha256":"93ab925f28886a63aac1eca3aba6c3daee7a38194b5ce0c00ff7804ea200e3e9"},"schema_version":"1.0"},"canonical_sha256":"78aa20d5f5f0d63322a380576947d1dbedef2aba8ea87578b3214c52abd55170","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:50:30.460134Z","signature_b64":"MuU/eYofn5bbA7X+G9QhbM5jq7ecKGkCtqF+P12HrHFWJyqwNqiO/jPL+fMTQ4OVrFqjwbJZrXlVBbeq7QcvDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78aa20d5f5f0d63322a380576947d1dbedef2aba8ea87578b3214c52abd55170","last_reissued_at":"2026-07-05T06:50:30.459648Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:50:30.459648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.05248","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":"2026-07-05T06:50:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ktRepXivwl1sp004Z39osvgUdrv2KLqaMfxgcjf5TVMq95icrTGaW6PKWa4+w7XQSUzjvxUgbfBUwc32XNaPAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T12:25:15.901685Z"},"content_sha256":"0e71cd5300de1de107005b7655a37141e2ffeda5ee5a57e08ffbfd9527b43c7a","schema_version":"1.0","event_id":"sha256:0e71cd5300de1de107005b7655a37141e2ffeda5ee5a57e08ffbfd9527b43c7a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PCVCBVPV6DLDGIVDQBLWSR6R3P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Speaker Diarization with Large Language Models: A Contextual Beam Search Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jagadeesh Balam, Kunal Dhawan, Nithin Koluguri, Tae Jin Park","submitted_at":"2023-09-11T05:47:56Z","abstract_excerpt":"Large language models (LLMs) have shown great promise for capturing contextual information in natural language processing tasks. We propose a novel approach to speaker diarization that incorporates the prowess of LLMs to exploit contextual cues in human dialogues. Our method builds upon an acoustic-based speaker diarization system by adding lexical information from an LLM in the inference stage. We model the multi-modal decoding process probabilistically and perform joint acoustic and lexical beam search to incorporate cues from both modalities: audio and text. Our experiments demonstrate that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.05248","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/2309.05248/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":"2026-07-05T06:50:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9NGsvuk7evXRvl2tEbqaQfGdUCNtqyRLQ56DBwhkLlCp60ZG/8ANJc1jbF+dGOiD6Aa4SMbOfq8xFwBKyqfGDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T12:25:15.902074Z"},"content_sha256":"3a541ae8832a450594f13db211981b48511e149fffc5ba3c68de6e1b4e609de3","schema_version":"1.0","event_id":"sha256:3a541ae8832a450594f13db211981b48511e149fffc5ba3c68de6e1b4e609de3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PCVCBVPV6DLDGIVDQBLWSR6R3P/bundle.json","state_url":"https://pith.science/pith/PCVCBVPV6DLDGIVDQBLWSR6R3P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PCVCBVPV6DLDGIVDQBLWSR6R3P/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":"2026-07-08T12:25:15Z","links":{"resolver":"https://pith.science/pith/PCVCBVPV6DLDGIVDQBLWSR6R3P","bundle":"https://pith.science/pith/PCVCBVPV6DLDGIVDQBLWSR6R3P/bundle.json","state":"https://pith.science/pith/PCVCBVPV6DLDGIVDQBLWSR6R3P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PCVCBVPV6DLDGIVDQBLWSR6R3P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PCVCBVPV6DLDGIVDQBLWSR6R3P","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":"93ab925f28886a63aac1eca3aba6c3daee7a38194b5ce0c00ff7804ea200e3e9","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-11T05:47:56Z","title_canon_sha256":"9b7d873119b347f193a723e2a403ff02eb58910a49bb43858a0306571a3a9130"},"schema_version":"1.0","source":{"id":"2309.05248","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.05248","created_at":"2026-07-05T06:50:30Z"},{"alias_kind":"arxiv_version","alias_value":"2309.05248v3","created_at":"2026-07-05T06:50:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.05248","created_at":"2026-07-05T06:50:30Z"},{"alias_kind":"pith_short_12","alias_value":"PCVCBVPV6DLD","created_at":"2026-07-05T06:50:30Z"},{"alias_kind":"pith_short_16","alias_value":"PCVCBVPV6DLDGIVD","created_at":"2026-07-05T06:50:30Z"},{"alias_kind":"pith_short_8","alias_value":"PCVCBVPV","created_at":"2026-07-05T06:50:30Z"}],"graph_snapshots":[{"event_id":"sha256:3a541ae8832a450594f13db211981b48511e149fffc5ba3c68de6e1b4e609de3","target":"graph","created_at":"2026-07-05T06:50:30Z","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/2309.05248/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have shown great promise for capturing contextual information in natural language processing tasks. We propose a novel approach to speaker diarization that incorporates the prowess of LLMs to exploit contextual cues in human dialogues. Our method builds upon an acoustic-based speaker diarization system by adding lexical information from an LLM in the inference stage. We model the multi-modal decoding process probabilistically and perform joint acoustic and lexical beam search to incorporate cues from both modalities: audio and text. Our experiments demonstrate that","authors_text":"Jagadeesh Balam, Kunal Dhawan, Nithin Koluguri, Tae Jin Park","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-11T05:47:56Z","title":"Enhancing Speaker Diarization with Large Language Models: A Contextual Beam Search Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.05248","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":"sha256:0e71cd5300de1de107005b7655a37141e2ffeda5ee5a57e08ffbfd9527b43c7a","target":"record","created_at":"2026-07-05T06:50:30Z","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":"93ab925f28886a63aac1eca3aba6c3daee7a38194b5ce0c00ff7804ea200e3e9","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-11T05:47:56Z","title_canon_sha256":"9b7d873119b347f193a723e2a403ff02eb58910a49bb43858a0306571a3a9130"},"schema_version":"1.0","source":{"id":"2309.05248","kind":"arxiv","version":3}},"canonical_sha256":"78aa20d5f5f0d63322a380576947d1dbedef2aba8ea87578b3214c52abd55170","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78aa20d5f5f0d63322a380576947d1dbedef2aba8ea87578b3214c52abd55170","first_computed_at":"2026-07-05T06:50:30.459648Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:50:30.459648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MuU/eYofn5bbA7X+G9QhbM5jq7ecKGkCtqF+P12HrHFWJyqwNqiO/jPL+fMTQ4OVrFqjwbJZrXlVBbeq7QcvDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:50:30.460134Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.05248","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e71cd5300de1de107005b7655a37141e2ffeda5ee5a57e08ffbfd9527b43c7a","sha256:3a541ae8832a450594f13db211981b48511e149fffc5ba3c68de6e1b4e609de3"],"state_sha256":"889e63d3b0beeddcebcd7f7d4a70520c29783e5b8b8bcc5fadf09b670b12792e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oHMN1FvMqpNxig/J5Zd3lMyw55CVyLfVbGby5QqFOWUSZvaoA/BWTjHMbDOdcQ/c6LzulfhjWjOmSUmQyiQUAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T12:25:15.904166Z","bundle_sha256":"f70a0f97e0790e17df02cb211e079602f2d1c80ec2fc7a56217c5611d6065e3c"}}