{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:C7M5NEFPRSQHNWWSOG4YPW47ML","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":"ab00db6ce6a3eba0abca10a26b9359bc5f4ea9b4be87eeb2e94a12e97e88c2fe","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-16T19:29:33Z","title_canon_sha256":"9df16eba6f1566ae7223dff23e5ecc58dfd24af5fb19b70db918aca26dbb6ce4"},"schema_version":"1.0","source":{"id":"2005.08072","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.08072","created_at":"2026-07-05T01:49:16Z"},{"alias_kind":"arxiv_version","alias_value":"2005.08072v2","created_at":"2026-07-05T01:49:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.08072","created_at":"2026-07-05T01:49:16Z"},{"alias_kind":"pith_short_12","alias_value":"C7M5NEFPRSQH","created_at":"2026-07-05T01:49:16Z"},{"alias_kind":"pith_short_16","alias_value":"C7M5NEFPRSQHNWWS","created_at":"2026-07-05T01:49:16Z"},{"alias_kind":"pith_short_8","alias_value":"C7M5NEFP","created_at":"2026-07-05T01:49:16Z"}],"graph_snapshots":[{"event_id":"sha256:6e91307ff4130954c1c55e5d03027f6bd6fc46c3db755351b9293851aa2ecde7","target":"graph","created_at":"2026-07-05T01:49:16Z","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/2005.08072/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech recognition (ASR) and speaker diarization (SD) models have traditionally been trained separately to produce rich conversation transcripts with speaker labels. Recent advances have shown that joint ASR and SD models can learn to leverage audio-lexical inter-dependencies to improve word diarization performance. We introduce a new benchmark of hour-long podcasts collected from the weekly This American Life radio program to better compare these approaches when applied to extended multi-speaker conversations. We find that training separate ASR and SD models perform better when utterance boun","authors_text":"Garrison Cottrell, Huanru Henry Mao, Julian McAuley, Shuyang Li","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-16T19:29:33Z","title":"Speech Recognition and Multi-Speaker Diarization of Long Conversations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.08072","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":"sha256:270785098120256cbca29822de7b4825cfd7e371af5b5afeeaffe5f86be5aaae","target":"record","created_at":"2026-07-05T01:49:16Z","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":"ab00db6ce6a3eba0abca10a26b9359bc5f4ea9b4be87eeb2e94a12e97e88c2fe","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-16T19:29:33Z","title_canon_sha256":"9df16eba6f1566ae7223dff23e5ecc58dfd24af5fb19b70db918aca26dbb6ce4"},"schema_version":"1.0","source":{"id":"2005.08072","kind":"arxiv","version":2}},"canonical_sha256":"17d9d690af8ca076dad271b987db9f62e393542f1025b3e2bc0b449d2f5cb59a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"17d9d690af8ca076dad271b987db9f62e393542f1025b3e2bc0b449d2f5cb59a","first_computed_at":"2026-07-05T01:49:16.398464Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:49:16.398464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ttTFhYEu1jtRA/UDMaJ2z2ONSl42vqh/NfTe8BB18X6HiICSx75Wnje8N5vBKi5VtWQLRDD6ylDo9X3pSRU0Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:49:16.398868Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.08072","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:270785098120256cbca29822de7b4825cfd7e371af5b5afeeaffe5f86be5aaae","sha256:6e91307ff4130954c1c55e5d03027f6bd6fc46c3db755351b9293851aa2ecde7"],"state_sha256":"31dca771a0ea22fb7194a64bc8ea00486597d604c0c9f9493d11576105df8915"}