{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:V7KALELZOVZRCBVCKEVW73VC5E","short_pith_number":"pith:V7KALELZ","schema_version":"1.0","canonical_sha256":"afd405917975731106a2512b6feea2e92de798b3203316450815be5b89b5a1e1","source":{"kind":"arxiv","id":"2510.23320","version":2},"attestation_state":"computed","paper":{"title":"LibriConvo: Simulating Conversations from Read Literature for ASR and Diarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"M\\'at\\'e Gedeon, P\\'eter Mihajlik","submitted_at":"2025-10-27T13:35:22Z","abstract_excerpt":"We introduce LibriConvo, a synthetic conversational speech corpus for speaker diarization and automatic speech recognition (ASR), built by instantiating the previously proposed Speaker-Aware Simulated Conversation (SASC) framework in a dataset and benchmarking setting. The main contribution of this paper is a corpus construction pipeline and benchmark derived from that framework. To make the data more suitable for downstream ASR and diarization, conversational timing statistics are estimated from English CallHome using external voice activity detection, long pauses are compressed, LibriTTS utt"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2510.23320","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-10-27T13:35:22Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"a7780d953d9f9e68cce75ccfed73ca82f0588d5da38e1dfec0bd3d8de2d12c39","abstract_canon_sha256":"38da700bd7544c40ee8176b3ab0890d1bdafd828eede0885e4122e49a24e751a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:10:29.114311Z","signature_b64":"NegvmJicl+80Xc2u4rrXUqKi7W9kotO+cLovPJtaauWYZ5p5a/QQTf0e/R1aQsLDyv8crooZ42fRlR3j35C/DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afd405917975731106a2512b6feea2e92de798b3203316450815be5b89b5a1e1","last_reissued_at":"2026-06-11T01:10:29.113403Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:10:29.113403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LibriConvo: Simulating Conversations from Read Literature for ASR and Diarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"M\\'at\\'e Gedeon, P\\'eter Mihajlik","submitted_at":"2025-10-27T13:35:22Z","abstract_excerpt":"We introduce LibriConvo, a synthetic conversational speech corpus for speaker diarization and automatic speech recognition (ASR), built by instantiating the previously proposed Speaker-Aware Simulated Conversation (SASC) framework in a dataset and benchmarking setting. The main contribution of this paper is a corpus construction pipeline and benchmark derived from that framework. To make the data more suitable for downstream ASR and diarization, conversational timing statistics are estimated from English CallHome using external voice activity detection, long pauses are compressed, LibriTTS utt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.23320","kind":"arxiv","version":2},"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/2510.23320/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2510.23320","created_at":"2026-06-11T01:10:29.113522+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.23320v2","created_at":"2026-06-11T01:10:29.113522+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.23320","created_at":"2026-06-11T01:10:29.113522+00:00"},{"alias_kind":"pith_short_12","alias_value":"V7KALELZOVZR","created_at":"2026-06-11T01:10:29.113522+00:00"},{"alias_kind":"pith_short_16","alias_value":"V7KALELZOVZRCBVC","created_at":"2026-06-11T01:10:29.113522+00:00"},{"alias_kind":"pith_short_8","alias_value":"V7KALELZ","created_at":"2026-06-11T01:10:29.113522+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V7KALELZOVZRCBVCKEVW73VC5E","json":"https://pith.science/pith/V7KALELZOVZRCBVCKEVW73VC5E.json","graph_json":"https://pith.science/api/pith-number/V7KALELZOVZRCBVCKEVW73VC5E/graph.json","events_json":"https://pith.science/api/pith-number/V7KALELZOVZRCBVCKEVW73VC5E/events.json","paper":"https://pith.science/paper/V7KALELZ"},"agent_actions":{"view_html":"https://pith.science/pith/V7KALELZOVZRCBVCKEVW73VC5E","download_json":"https://pith.science/pith/V7KALELZOVZRCBVCKEVW73VC5E.json","view_paper":"https://pith.science/paper/V7KALELZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.23320&json=true","fetch_graph":"https://pith.science/api/pith-number/V7KALELZOVZRCBVCKEVW73VC5E/graph.json","fetch_events":"https://pith.science/api/pith-number/V7KALELZOVZRCBVCKEVW73VC5E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V7KALELZOVZRCBVCKEVW73VC5E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V7KALELZOVZRCBVCKEVW73VC5E/action/storage_attestation","attest_author":"https://pith.science/pith/V7KALELZOVZRCBVCKEVW73VC5E/action/author_attestation","sign_citation":"https://pith.science/pith/V7KALELZOVZRCBVCKEVW73VC5E/action/citation_signature","submit_replication":"https://pith.science/pith/V7KALELZOVZRCBVCKEVW73VC5E/action/replication_record"}},"created_at":"2026-06-11T01:10:29.113522+00:00","updated_at":"2026-06-11T01:10:29.113522+00:00"}